Patch (#947)

* Fix preview when using frame enhancer

* Fix version conflict numpy vs. cv2

* Use latest numpy

* Introduce scale_face() to match size of temp frames and target frames

* Remove hardcoded backend for camera under Windows

* Up and downgrade some dependencies

* Up and downgrade some dependencies

* Up and downgrade some dependencies

.flake8

@@ -1,5 +1,5 @@
 [flake8]
-select = E3, E4, F, I1, I2
+select = E22, E23, E24, E27, E3, E4, E7, F, I1, I2
 per-file-ignores = facefusion.py:E402, install.py:E402
 plugins = flake8-import-order
 application_import_names = facefusion

LICENSE.md

@@ -1,3 +1,3 @@
-MIT license
+OpenRAIL-AS license
 
-Copyright (c) 2024 Henry Ruhs
+Copyright (c) 2025 Henry Ruhs

README.md

@@ -5,7 +5,7 @@ FaceFusion
 
 [![Build Status](https://img.shields.io/github/actions/workflow/status/facefusion/facefusion/ci.yml.svg?branch=master)](https://github.com/facefusion/facefusion/actions?query=workflow:ci)
 [![Coverage Status](https://img.shields.io/coveralls/facefusion/facefusion.svg)](https://coveralls.io/r/facefusion/facefusion)
-![License](https://img.shields.io/badge/license-MIT-green)
+![License](https://img.shields.io/badge/license-OpenRAIL--AS-green)
 
 
 Preview
@@ -37,6 +37,7 @@ commands:
     headless-run                                  run the program in headless mode
     batch-run                                     run the program in batch mode
     force-download                                force automate downloads and exit
+    benchmark                                     benchmark the program
     job-list                                      list jobs by status
     job-create                                    create a drafted job
     job-submit                                    submit a drafted job to become a queued job

facefusion.ini

@@ -35,9 +35,13 @@ reference_frame_number =
 face_occluder_model =
 face_parser_model =
 face_mask_types =
+face_mask_areas =
+face_mask_regions =
 face_mask_blur =
 face_mask_padding =
-face_mask_regions =
+
+[voice_extractor]
+voice_extractor_model =
 
 [frame_extraction]
 trim_frame_start =
@@ -47,14 +51,15 @@ keep_temp =
 
 [output_creation]
 output_image_quality =
-output_image_resolution =
+output_image_scale =
 output_audio_encoder =
+output_audio_quality =
+output_audio_volume =
 output_video_encoder =
 output_video_preset =
 output_video_quality =
-output_video_resolution =
+output_video_scale =
 output_video_fps =
-skip_audio =
 
 [processors]
 processors =
@@ -64,6 +69,7 @@ deep_swapper_model =
 deep_swapper_morph =
 expression_restorer_model =
 expression_restorer_factor =
+expression_restorer_areas =
 face_debugger_items =
 face_editor_model =
 face_editor_eyebrow_direction =
@@ -85,31 +91,38 @@ face_enhancer_blend =
 face_enhancer_weight =
 face_swapper_model =
 face_swapper_pixel_boost =
+face_swapper_weight =
 frame_colorizer_model =
 frame_colorizer_size =
 frame_colorizer_blend =
 frame_enhancer_model =
 frame_enhancer_blend =
 lip_syncer_model =
+lip_syncer_weight =
 
 [uis]
 open_browser =
 ui_layouts =
 ui_workflow =
 
-[execution]
-execution_device_id =
-execution_providers =
-execution_thread_count =
-execution_queue_count =
-
 [download]
 download_providers =
 download_scope =
 
+[benchmark]
+benchmark_mode =
+benchmark_resolutions =
+benchmark_cycle_count =
+
+[execution]
+execution_device_ids =
+execution_providers =
+execution_thread_count =
+
 [memory]
 video_memory_strategy =
 system_memory_limit =
 
 [misc]
 log_level =
+halt_on_error =

facefusion/app_context.py

@@ -1,7 +1,7 @@
 import os
 import sys
 
-from facefusion.typing import AppContext
+from facefusion.types import AppContext
 
 
 def detect_app_context() -> AppContext:

facefusion/args.py

@@ -1,10 +1,10 @@
 from facefusion import state_manager
-from facefusion.filesystem import is_image, is_video, list_directory
+from facefusion.filesystem import get_file_name, is_video, resolve_file_paths
 from facefusion.jobs import job_store
 from facefusion.normalizer import normalize_fps, normalize_padding
 from facefusion.processors.core import get_processors_modules
-from facefusion.typing import ApplyStateItem, Args
-from facefusion.vision import create_image_resolutions, create_video_resolutions, detect_image_resolution, detect_video_fps, detect_video_resolution, pack_resolution
+from facefusion.types import ApplyStateItem, Args
+from facefusion.vision import detect_video_fps
 
 
 def reduce_step_args(args : Args) -> Args:
@@ -74,9 +74,12 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_occluder_model', args.get('face_occluder_model'))
 	apply_state_item('face_parser_model', args.get('face_parser_model'))
 	apply_state_item('face_mask_types', args.get('face_mask_types'))
+	apply_state_item('face_mask_areas', args.get('face_mask_areas'))
+	apply_state_item('face_mask_regions', args.get('face_mask_regions'))
 	apply_state_item('face_mask_blur', args.get('face_mask_blur'))
 	apply_state_item('face_mask_padding', normalize_padding(args.get('face_mask_padding')))
-	apply_state_item('face_mask_regions', args.get('face_mask_regions'))
+	# voice extractor
+	apply_state_item('voice_extractor_model', args.get('voice_extractor_model'))
 	# frame extraction
 	apply_state_item('trim_frame_start', args.get('trim_frame_start'))
 	apply_state_item('trim_frame_end', args.get('trim_frame_end'))
@@ -84,30 +87,19 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('keep_temp', args.get('keep_temp'))
 	# output creation
 	apply_state_item('output_image_quality', args.get('output_image_quality'))
-	if is_image(args.get('target_path')):
-		output_image_resolution = detect_image_resolution(args.get('target_path'))
-		output_image_resolutions = create_image_resolutions(output_image_resolution)
-		if args.get('output_image_resolution') in output_image_resolutions:
-			apply_state_item('output_image_resolution', args.get('output_image_resolution'))
-		else:
-			apply_state_item('output_image_resolution', pack_resolution(output_image_resolution))
+	apply_state_item('output_image_scale', args.get('output_image_scale'))
 	apply_state_item('output_audio_encoder', args.get('output_audio_encoder'))
+	apply_state_item('output_audio_quality', args.get('output_audio_quality'))
+	apply_state_item('output_audio_volume', args.get('output_audio_volume'))
 	apply_state_item('output_video_encoder', args.get('output_video_encoder'))
 	apply_state_item('output_video_preset', args.get('output_video_preset'))
 	apply_state_item('output_video_quality', args.get('output_video_quality'))
-	if is_video(args.get('target_path')):
-		output_video_resolution = detect_video_resolution(args.get('target_path'))
-		output_video_resolutions = create_video_resolutions(output_video_resolution)
-		if args.get('output_video_resolution') in output_video_resolutions:
-			apply_state_item('output_video_resolution', args.get('output_video_resolution'))
-		else:
-			apply_state_item('output_video_resolution', pack_resolution(output_video_resolution))
+	apply_state_item('output_video_scale', args.get('output_video_scale'))
 	if args.get('output_video_fps') or is_video(args.get('target_path')):
 		output_video_fps = normalize_fps(args.get('output_video_fps')) or detect_video_fps(args.get('target_path'))
 		apply_state_item('output_video_fps', output_video_fps)
-	apply_state_item('skip_audio', args.get('skip_audio'))
 	# processors
-	available_processors = [ file.get('name') for file in list_directory('facefusion/processors/modules') ]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	apply_state_item('processors', args.get('processors'))
 	for processor_module in get_processors_modules(available_processors):
 		processor_module.apply_args(args, apply_state_item)
@@ -116,18 +108,22 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('ui_layouts', args.get('ui_layouts'))
 	apply_state_item('ui_workflow', args.get('ui_workflow'))
 	# execution
-	apply_state_item('execution_device_id', args.get('execution_device_id'))
+	apply_state_item('execution_device_ids', args.get('execution_device_ids'))
 	apply_state_item('execution_providers', args.get('execution_providers'))
 	apply_state_item('execution_thread_count', args.get('execution_thread_count'))
-	apply_state_item('execution_queue_count', args.get('execution_queue_count'))
 	# download
 	apply_state_item('download_providers', args.get('download_providers'))
 	apply_state_item('download_scope', args.get('download_scope'))
+	# benchmark
+	apply_state_item('benchmark_mode', args.get('benchmark_mode'))
+	apply_state_item('benchmark_resolutions', args.get('benchmark_resolutions'))
+	apply_state_item('benchmark_cycle_count', args.get('benchmark_cycle_count'))
 	# memory
 	apply_state_item('video_memory_strategy', args.get('video_memory_strategy'))
 	apply_state_item('system_memory_limit', args.get('system_memory_limit'))
 	# misc
 	apply_state_item('log_level', args.get('log_level'))
+	apply_state_item('halt_on_error', args.get('halt_on_error'))
 	# jobs
 	apply_state_item('job_id', args.get('job_id'))
 	apply_state_item('job_status', args.get('job_status'))

facefusion/audio.py

@@ -3,25 +3,26 @@ from typing import Any, List, Optional
 
 import numpy
 import scipy
-from numpy._typing import NDArray
+from numpy.typing import NDArray
 
 from facefusion.ffmpeg import read_audio_buffer
 from facefusion.filesystem import is_audio
-from facefusion.typing import Audio, AudioFrame, Fps, Mel, MelFilterBank, Spectrogram
+from facefusion.types import Audio, AudioFrame, Fps, Mel, MelFilterBank, Spectrogram
 from facefusion.voice_extractor import batch_extract_voice
 
 
-@lru_cache(maxsize = 128)
+@lru_cache()
 def read_static_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
 	return read_audio(audio_path, fps)
 
 
 def read_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
-	sample_rate = 48000
-	channel_total = 2
+	audio_sample_rate = 48000
+	audio_sample_size = 16
+	audio_channel_total = 2
 
 	if is_audio(audio_path):
-		audio_buffer = read_audio_buffer(audio_path, sample_rate, channel_total)
+		audio_buffer = read_audio_buffer(audio_path, audio_sample_rate, audio_sample_size, audio_channel_total)
 		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
 		audio = prepare_audio(audio)
 		spectrogram = create_spectrogram(audio)
@@ -30,21 +31,22 @@ def read_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
 	return None
 
 
-@lru_cache(maxsize = 128)
+@lru_cache()
 def read_static_voice(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
 	return read_voice(audio_path, fps)
 
 
 def read_voice(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
-	sample_rate = 48000
-	channel_total = 2
-	chunk_size = 240 * 1024
-	step_size = 180 * 1024
+	voice_sample_rate = 48000
+	voice_sample_size = 16
+	voice_channel_total = 2
+	voice_chunk_size = 240 * 1024
+	voice_step_size = 180 * 1024
 
 	if is_audio(audio_path):
-		audio_buffer = read_audio_buffer(audio_path, sample_rate, channel_total)
+		audio_buffer = read_audio_buffer(audio_path, voice_sample_rate, voice_sample_size, voice_channel_total)
 		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
-		audio = batch_extract_voice(audio, chunk_size, step_size)
+		audio = batch_extract_voice(audio, voice_chunk_size, voice_step_size)
 		audio = prepare_voice(audio)
 		spectrogram = create_spectrogram(audio)
 		audio_frames = extract_audio_frames(spectrogram, fps)
@@ -60,6 +62,20 @@ def get_audio_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Opti
 	return None
 
 
+def extract_audio_frames(spectrogram : Spectrogram, fps : Fps) -> List[AudioFrame]:
+	audio_frames = []
+	mel_filter_total = 80
+	audio_step_size = 16
+	indices = numpy.arange(0, spectrogram.shape[1], mel_filter_total / fps).astype(numpy.int16)
+	indices = indices[indices >= audio_step_size]
+
+	for index in indices:
+		start = max(0, index - audio_step_size)
+		audio_frames.append(spectrogram[:, start:index])
+
+	return audio_frames
+
+
 def get_voice_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Optional[AudioFrame]:
 	if is_audio(audio_path):
 		voice_frames = read_static_voice(audio_path, fps)
@@ -70,8 +86,8 @@ def get_voice_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Opti
 
 def create_empty_audio_frame() -> AudioFrame:
 	mel_filter_total = 80
-	step_size = 16
-	audio_frame = numpy.zeros((mel_filter_total, step_size)).astype(numpy.int16)
+	audio_step_size = 16
+	audio_frame = numpy.zeros((mel_filter_total, audio_step_size)).astype(numpy.int16)
 	return audio_frame
 
 
@@ -84,10 +100,10 @@ def prepare_audio(audio : Audio) -> Audio:
 
 
 def prepare_voice(audio : Audio) -> Audio:
-	sample_rate = 48000
-	resample_rate = 16000
-
-	audio = scipy.signal.resample(audio, int(len(audio) * resample_rate / sample_rate))
+	audio_sample_rate = 48000
+	audio_resample_rate = 16000
+	audio_resample_factor = round(len(audio) * audio_resample_rate / audio_sample_rate)
+	audio = scipy.signal.resample(audio, audio_resample_factor)
 	audio = prepare_audio(audio)
 	return audio
 
@@ -101,19 +117,20 @@ def convert_mel_to_hertz(mel : Mel) -> NDArray[Any]:
 
 
 def create_mel_filter_bank() -> MelFilterBank:
+	audio_sample_rate = 16000
+	audio_frequency_min = 55.0
+	audio_frequency_max = 7600.0
 	mel_filter_total = 80
 	mel_bin_total = 800
-	sample_rate = 16000
-	min_frequency = 55.0
-	max_frequency = 7600.0
 	mel_filter_bank = numpy.zeros((mel_filter_total, mel_bin_total // 2 + 1))
-	mel_frequency_range = numpy.linspace(convert_hertz_to_mel(min_frequency), convert_hertz_to_mel(max_frequency), mel_filter_total + 2)
-	indices = numpy.floor((mel_bin_total + 1) * convert_mel_to_hertz(mel_frequency_range) / sample_rate).astype(numpy.int16)
+	mel_frequency_range = numpy.linspace(convert_hertz_to_mel(audio_frequency_min), convert_hertz_to_mel(audio_frequency_max), mel_filter_total + 2)
+	indices = numpy.floor((mel_bin_total + 1) * convert_mel_to_hertz(mel_frequency_range) / audio_sample_rate).astype(numpy.int16)
 
 	for index in range(mel_filter_total):
 		start = indices[index]
 		end = indices[index + 1]
 		mel_filter_bank[index, start:end] = scipy.signal.windows.triang(end - start)
+
 	return mel_filter_bank
 
 
@@ -124,16 +141,3 @@ def create_spectrogram(audio : Audio) -> Spectrogram:
 	spectrogram = scipy.signal.stft(audio, nperseg = mel_bin_total, nfft = mel_bin_total, noverlap = mel_bin_overlap)[2]
 	spectrogram = numpy.dot(mel_filter_bank, numpy.abs(spectrogram))
 	return spectrogram
-
-
-def extract_audio_frames(spectrogram : Spectrogram, fps : Fps) -> List[AudioFrame]:
-	mel_filter_total = 80
-	step_size = 16
-	audio_frames = []
-	indices = numpy.arange(0, spectrogram.shape[1], mel_filter_total / fps).astype(numpy.int16)
-	indices = indices[indices >= step_size]
-
-	for index in indices:
-		start = max(0, index - step_size)
-		audio_frames.append(spectrogram[:, start:index])
-	return audio_frames

facefusion/benchmarker.py

@@ -0,0 +1,111 @@
+import hashlib
+import os
+import statistics
+import tempfile
+from time import perf_counter
+from typing import Generator, List
+
+import facefusion.choices
+from facefusion import content_analyser, core, state_manager
+from facefusion.cli_helper import render_table
+from facefusion.download import conditional_download, resolve_download_url
+from facefusion.face_store import clear_static_faces
+from facefusion.filesystem import get_file_extension
+from facefusion.types import BenchmarkCycleSet
+from facefusion.vision import count_video_frame_total, detect_video_fps
+
+
+def pre_check() -> bool:
+	conditional_download('.assets/examples',
+	[
+		resolve_download_url('examples-3.0.0', 'source.jpg'),
+		resolve_download_url('examples-3.0.0', 'source.mp3'),
+		resolve_download_url('examples-3.0.0', 'target-240p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-360p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-540p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-720p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-1080p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-1440p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-2160p.mp4')
+	])
+	return True
+
+
+def run() -> Generator[List[BenchmarkCycleSet], None, None]:
+	benchmark_resolutions = state_manager.get_item('benchmark_resolutions')
+	benchmark_cycle_count = state_manager.get_item('benchmark_cycle_count')
+
+	state_manager.init_item('source_paths', [ '.assets/examples/source.jpg', '.assets/examples/source.mp3' ])
+	state_manager.init_item('face_landmarker_score', 0)
+	state_manager.init_item('temp_frame_format', 'bmp')
+	state_manager.init_item('output_audio_volume', 0)
+	state_manager.init_item('output_video_preset', 'ultrafast')
+	state_manager.init_item('video_memory_strategy', 'tolerant')
+
+	benchmarks = []
+	target_paths = [ facefusion.choices.benchmark_set.get(benchmark_resolution) for benchmark_resolution in benchmark_resolutions if benchmark_resolution in facefusion.choices.benchmark_set ]
+
+	for target_path in target_paths:
+		state_manager.init_item('target_path', target_path)
+		state_manager.init_item('output_path', suggest_output_path(state_manager.get_item('target_path')))
+		benchmarks.append(cycle(benchmark_cycle_count))
+		yield benchmarks
+
+
+def cycle(cycle_count : int) -> BenchmarkCycleSet:
+	process_times = []
+	video_frame_total = count_video_frame_total(state_manager.get_item('target_path'))
+	state_manager.init_item('output_video_fps', detect_video_fps(state_manager.get_item('target_path')))
+
+	if state_manager.get_item('benchmark_mode') == 'warm':
+		core.conditional_process()
+
+	for index in range(cycle_count):
+		if state_manager.get_item('benchmark_mode') == 'cold':
+			content_analyser.analyse_image.cache_clear()
+			content_analyser.analyse_video.cache_clear()
+			clear_static_faces()
+
+		start_time = perf_counter()
+		core.conditional_process()
+		end_time = perf_counter()
+		process_times.append(end_time - start_time)
+
+	average_run = round(statistics.mean(process_times), 2)
+	fastest_run = round(min(process_times), 2)
+	slowest_run = round(max(process_times), 2)
+	relative_fps = round(video_frame_total * cycle_count / sum(process_times), 2)
+
+	return\
+	{
+		'target_path': state_manager.get_item('target_path'),
+		'cycle_count': cycle_count,
+		'average_run': average_run,
+		'fastest_run': fastest_run,
+		'slowest_run': slowest_run,
+		'relative_fps': relative_fps
+	}
+
+
+def suggest_output_path(target_path : str) -> str:
+	target_file_extension = get_file_extension(target_path)
+	return os.path.join(tempfile.gettempdir(), hashlib.sha1().hexdigest()[:8] + target_file_extension)
+
+
+def render() -> None:
+	benchmarks = []
+	headers =\
+	[
+		'target_path',
+		'cycle_count',
+		'average_run',
+		'fastest_run',
+		'slowest_run',
+		'relative_fps'
+	]
+
+	for benchmark in run():
+		benchmarks = benchmark
+
+	contents = [ list(benchmark_set.values()) for benchmark_set in benchmarks ]
+	render_table(headers, contents)

facefusion/camera_manager.py

@@ -0,0 +1,53 @@
+from typing import List
+
+import cv2
+
+from facefusion.types import CameraPoolSet
+
+CAMERA_POOL_SET : CameraPoolSet =\
+{
+	'capture': {}
+}
+
+
+def get_local_camera_capture(camera_id : int) -> cv2.VideoCapture:
+	camera_key = str(camera_id)
+
+	if camera_key not in CAMERA_POOL_SET.get('capture'):
+		camera_capture = cv2.VideoCapture(camera_id)
+
+		if camera_capture.isOpened():
+			CAMERA_POOL_SET['capture'][camera_key] = camera_capture
+
+	return CAMERA_POOL_SET.get('capture').get(camera_key)
+
+
+def get_remote_camera_capture(camera_url : str) -> cv2.VideoCapture:
+	if camera_url not in CAMERA_POOL_SET.get('capture'):
+		camera_capture = cv2.VideoCapture(camera_url)
+
+		if camera_capture.isOpened():
+			CAMERA_POOL_SET['capture'][camera_url] = camera_capture
+
+	return CAMERA_POOL_SET.get('capture').get(camera_url)
+
+
+def clear_camera_pool() -> None:
+	for camera_capture in CAMERA_POOL_SET.get('capture').values():
+		camera_capture.release()
+
+	CAMERA_POOL_SET['capture'].clear()
+
+
+def detect_local_camera_ids(id_start : int, id_end : int) -> List[int]:
+	local_camera_ids = []
+
+	for camera_id in range(id_start, id_end):
+		cv2.setLogLevel(0)
+		camera_capture = get_local_camera_capture(camera_id)
+		cv2.setLogLevel(3)
+
+		if camera_capture and camera_capture.isOpened():
+			local_camera_ids.append(camera_id)
+
+	return local_camera_ids

facefusion/choices.py

@@ -2,14 +2,15 @@ import logging
 from typing import List, Sequence
 
 from facefusion.common_helper import create_float_range, create_int_range
-from facefusion.typing import Angle, DownloadProvider, DownloadProviderSet, DownloadScope, ExecutionProvider, ExecutionProviderSet, FaceDetectorModel, FaceDetectorSet, FaceLandmarkerModel, FaceMaskRegion, FaceMaskRegionSet, FaceMaskType, FaceOccluderModel, FaceParserModel, FaceSelectorMode, FaceSelectorOrder, Gender, JobStatus, LogLevel, LogLevelSet, OutputAudioEncoder, OutputVideoEncoder, OutputVideoPreset, Race, Score, TempFrameFormat, UiWorkflow, VideoMemoryStrategy
+from facefusion.types import Angle, AudioEncoder, AudioFormat, AudioTypeSet, BenchmarkMode, BenchmarkResolution, BenchmarkSet, DownloadProvider, DownloadProviderSet, DownloadScope, EncoderSet, ExecutionProvider, ExecutionProviderSet, FaceDetectorModel, FaceDetectorSet, FaceLandmarkerModel, FaceMaskArea, FaceMaskAreaSet, FaceMaskRegion, FaceMaskRegionSet, FaceMaskType, FaceOccluderModel, FaceParserModel, FaceSelectorMode, FaceSelectorOrder, Gender, ImageFormat, ImageTypeSet, JobStatus, LogLevel, LogLevelSet, Race, Score, TempFrameFormat, UiWorkflow, VideoEncoder, VideoFormat, VideoMemoryStrategy, VideoPreset, VideoTypeSet, VoiceExtractorModel
 
 face_detector_set : FaceDetectorSet =\
 {
 	'many': [ '640x640' ],
 	'retinaface': [ '160x160', '320x320', '480x480', '512x512', '640x640' ],
 	'scrfd': [ '160x160', '320x320', '480x480', '512x512', '640x640' ],
-	'yoloface': [ '640x640' ]
+	'yolo_face': [ '640x640' ],
+	'yunet': [ '640x640' ]
 }
 face_detector_models : List[FaceDetectorModel] = list(face_detector_set.keys())
 face_landmarker_models : List[FaceLandmarkerModel] = [ 'many', '2dfan4', 'peppa_wutz' ]
@@ -17,9 +18,15 @@ face_selector_modes : List[FaceSelectorMode] = [ 'many', 'one', 'reference' ]
 face_selector_orders : List[FaceSelectorOrder] = [ 'left-right', 'right-left', 'top-bottom', 'bottom-top', 'small-large', 'large-small', 'best-worst', 'worst-best' ]
 face_selector_genders : List[Gender] = [ 'female', 'male' ]
 face_selector_races : List[Race] = [ 'white', 'black', 'latino', 'asian', 'indian', 'arabic' ]
-face_occluder_models : List[FaceOccluderModel] = [ 'xseg_1', 'xseg_2' ]
+face_occluder_models : List[FaceOccluderModel] = [ 'many', 'xseg_1', 'xseg_2', 'xseg_3' ]
 face_parser_models : List[FaceParserModel] = [ 'bisenet_resnet_18', 'bisenet_resnet_34' ]
-face_mask_types : List[FaceMaskType] = [ 'box', 'occlusion', 'region' ]
+face_mask_types : List[FaceMaskType] = [ 'box', 'occlusion', 'area', 'region' ]
+face_mask_area_set : FaceMaskAreaSet =\
+{
+	'upper-face': [ 0, 1, 2, 31, 32, 33, 34, 35, 14, 15, 16, 26, 25, 24, 23, 22, 21, 20, 19, 18, 17 ],
+	'lower-face': [ 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 35, 34, 33, 32, 31 ],
+	'mouth': [ 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67 ]
+}
 face_mask_region_set : FaceMaskRegionSet =\
 {
 	'skin': 1,
@@ -33,36 +40,94 @@ face_mask_region_set : FaceMaskRegionSet =\
 	'upper-lip': 12,
 	'lower-lip': 13
 }
+face_mask_areas : List[FaceMaskArea] = list(face_mask_area_set.keys())
 face_mask_regions : List[FaceMaskRegion] = list(face_mask_region_set.keys())
-temp_frame_formats : List[TempFrameFormat] = [ 'bmp', 'jpg', 'png' ]
-output_audio_encoders : List[OutputAudioEncoder] = [ 'aac', 'libmp3lame', 'libopus', 'libvorbis' ]
-output_video_encoders : List[OutputVideoEncoder] = [ 'libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_qsv', 'hevc_qsv', 'h264_videotoolbox', 'hevc_videotoolbox' ]
-output_video_presets : List[OutputVideoPreset] = [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]
 
-image_template_sizes : List[float] = [ 0.25, 0.5, 0.75, 1, 1.5, 2, 2.5, 3, 3.5, 4 ]
-video_template_sizes : List[int] = [ 240, 360, 480, 540, 720, 1080, 1440, 2160, 4320 ]
+voice_extractor_models : List[VoiceExtractorModel] = [ 'kim_vocal_1', 'kim_vocal_2', 'uvr_mdxnet' ]
+
+audio_type_set : AudioTypeSet =\
+{
+	'flac': 'audio/flac',
+	'm4a': 'audio/mp4',
+	'mp3': 'audio/mpeg',
+	'ogg': 'audio/ogg',
+	'opus': 'audio/opus',
+	'wav': 'audio/x-wav'
+}
+image_type_set : ImageTypeSet =\
+{
+	'bmp': 'image/bmp',
+	'jpeg': 'image/jpeg',
+	'png': 'image/png',
+	'tiff': 'image/tiff',
+	'webp': 'image/webp'
+}
+video_type_set : VideoTypeSet =\
+{
+	'avi': 'video/x-msvideo',
+	'm4v': 'video/mp4',
+	'mkv': 'video/x-matroska',
+	'mp4': 'video/mp4',
+	'mov': 'video/quicktime',
+	'webm': 'video/webm',
+	'wmv': 'video/x-ms-wmv'
+}
+audio_formats : List[AudioFormat] = list(audio_type_set.keys())
+image_formats : List[ImageFormat] = list(image_type_set.keys())
+video_formats : List[VideoFormat] = list(video_type_set.keys())
+temp_frame_formats : List[TempFrameFormat] = [ 'bmp', 'jpeg', 'png', 'tiff' ]
+
+output_encoder_set : EncoderSet =\
+{
+	'audio': [ 'flac', 'aac', 'libmp3lame', 'libopus', 'libvorbis', 'pcm_s16le', 'pcm_s32le' ],
+	'video': [ 'libx264', 'libx264rgb', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_qsv', 'hevc_qsv', 'h264_videotoolbox', 'hevc_videotoolbox', 'rawvideo' ]
+}
+output_audio_encoders : List[AudioEncoder] = output_encoder_set.get('audio')
+output_video_encoders : List[VideoEncoder] = output_encoder_set.get('video')
+output_video_presets : List[VideoPreset] = [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]
+
+benchmark_modes : List[BenchmarkMode] = [ 'warm', 'cold' ]
+benchmark_set : BenchmarkSet =\
+{
+	'240p': '.assets/examples/target-240p.mp4',
+	'360p': '.assets/examples/target-360p.mp4',
+	'540p': '.assets/examples/target-540p.mp4',
+	'720p': '.assets/examples/target-720p.mp4',
+	'1080p': '.assets/examples/target-1080p.mp4',
+	'1440p': '.assets/examples/target-1440p.mp4',
+	'2160p': '.assets/examples/target-2160p.mp4'
+}
+benchmark_resolutions : List[BenchmarkResolution] = list(benchmark_set.keys())
 
 execution_provider_set : ExecutionProviderSet =\
 {
-	'cpu': 'CPUExecutionProvider',
-	'coreml': 'CoreMLExecutionProvider',
 	'cuda': 'CUDAExecutionProvider',
+	'tensorrt': 'TensorrtExecutionProvider',
 	'directml': 'DmlExecutionProvider',
-	'openvino': 'OpenVINOExecutionProvider',
 	'rocm': 'ROCMExecutionProvider',
-	'tensorrt': 'TensorrtExecutionProvider'
+	'migraphx': 'MIGraphXExecutionProvider',
+	'openvino': 'OpenVINOExecutionProvider',
+	'coreml': 'CoreMLExecutionProvider',
+	'cpu': 'CPUExecutionProvider'
 }
 execution_providers : List[ExecutionProvider] = list(execution_provider_set.keys())
 download_provider_set : DownloadProviderSet =\
 {
 	'github':
 	{
-		'url': 'https://github.com',
+		'urls':
+		[
+			'https://github.com'
+		],
 		'path': '/facefusion/facefusion-assets/releases/download/{base_name}/{file_name}'
 	},
 	'huggingface':
 	{
-		'url': 'https://huggingface.co',
+		'urls':
+		[
+			'https://huggingface.co',
+			'https://hf-mirror.com'
+		],
 		'path': '/facefusion/{base_name}/resolve/main/{file_name}'
 	}
 }
@@ -83,8 +148,8 @@ log_levels : List[LogLevel] = list(log_level_set.keys())
 ui_workflows : List[UiWorkflow] = [ 'instant_runner', 'job_runner', 'job_manager' ]
 job_statuses : List[JobStatus] = [ 'drafted', 'queued', 'completed', 'failed' ]
 
+benchmark_cycle_count_range : Sequence[int] = create_int_range(1, 10, 1)
 execution_thread_count_range : Sequence[int] = create_int_range(1, 32, 1)
-execution_queue_count_range : Sequence[int] = create_int_range(1, 4, 1)
 system_memory_limit_range : Sequence[int] = create_int_range(0, 128, 4)
 face_detector_angles : Sequence[Angle] = create_int_range(0, 270, 90)
 face_detector_score_range : Sequence[Score] = create_float_range(0.0, 1.0, 0.05)
@@ -92,6 +157,10 @@ face_landmarker_score_range : Sequence[Score] = create_float_range(0.0, 1.0, 0.0
 face_mask_blur_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
 face_mask_padding_range : Sequence[int] = create_int_range(0, 100, 1)
 face_selector_age_range : Sequence[int] = create_int_range(0, 100, 1)
-reference_face_distance_range : Sequence[float] = create_float_range(0.0, 1.5, 0.05)
+reference_face_distance_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
 output_image_quality_range : Sequence[int] = create_int_range(0, 100, 1)
+output_image_scale_range : Sequence[float] = create_float_range(0.25, 8.0, 0.25)
+output_audio_quality_range : Sequence[int] = create_int_range(0, 100, 1)
+output_audio_volume_range : Sequence[int] = create_int_range(0, 100, 1)
 output_video_quality_range : Sequence[int] = create_int_range(0, 100, 1)
+output_video_scale_range : Sequence[float] = create_float_range(0.25, 8.0, 0.25)

facefusion/cli_helper.py

@@ -0,0 +1,35 @@
+from typing import Tuple
+
+from facefusion.logger import get_package_logger
+from facefusion.types import TableContents, TableHeaders
+
+
+def render_table(headers : TableHeaders, contents : TableContents) -> None:
+	package_logger = get_package_logger()
+	table_column, table_separator = create_table_parts(headers, contents)
+
+	package_logger.critical(table_separator)
+	package_logger.critical(table_column.format(*headers))
+	package_logger.critical(table_separator)
+
+	for content in contents:
+		content = [ str(value) for value in content ]
+		package_logger.critical(table_column.format(*content))
+
+	package_logger.critical(table_separator)
+
+
+def create_table_parts(headers : TableHeaders, contents : TableContents) -> Tuple[str, str]:
+	column_parts = []
+	separator_parts = []
+	widths = [ len(header) for header in headers ]
+
+	for content in contents:
+		for index, value in enumerate(content):
+			widths[index] = max(widths[index], len(str(value)))
+
+	for width in widths:
+		column_parts.append('{:<' + str(width) + '}')
+		separator_parts.append('-' * width)
+
+	return '| ' + ' | '.join(column_parts) + ' |', '+-' + '-+-'.join(separator_parts) + '-+'

facefusion/common_helper.py

@@ -1,5 +1,5 @@
 import platform
-from typing import Any, Optional, Sequence
+from typing import Any, Iterable, Optional, Reversible, Sequence
 
 
 def is_linux() -> bool:
@@ -15,11 +15,11 @@ def is_windows() -> bool:
 
 
 def create_int_metavar(int_range : Sequence[int]) -> str:
-	return '[' + str(int_range[0]) + '..' + str(int_range[-1]) + ':' + str(calc_int_step(int_range)) + ']'
+	return '[' + str(int_range[0]) + '..' + str(int_range[-1]) + ':' + str(calculate_int_step(int_range)) + ']'
 
 
 def create_float_metavar(float_range : Sequence[float]) -> str:
-	return '[' + str(float_range[0]) + '..' + str(float_range[-1]) + ':' + str(calc_float_step(float_range)) + ']'
+	return '[' + str(float_range[0]) + '..' + str(float_range[-1]) + ':' + str(calculate_float_step(float_range)) + ']'
 
 
 def create_int_range(start : int, end : int, step : int) -> Sequence[int]:
@@ -42,31 +42,43 @@ def create_float_range(start : float, end : float, step : float) -> Sequence[flo
 	return float_range
 
 
-def calc_int_step(int_range : Sequence[int]) -> int:
+def calculate_int_step(int_range : Sequence[int]) -> int:
 	return int_range[1] - int_range[0]
 
 
-def calc_float_step(float_range : Sequence[float]) -> float:
+def calculate_float_step(float_range : Sequence[float]) -> float:
 	return round(float_range[1] - float_range[0], 2)
 
 
-def cast_int(value : Any) -> Optional[Any]:
+def cast_int(value : Any) -> Optional[int]:
 	try:
 		return int(value)
 	except (ValueError, TypeError):
 		return None
 
 
-def cast_float(value : Any) -> Optional[Any]:
+def cast_float(value : Any) -> Optional[float]:
 	try:
 		return float(value)
 	except (ValueError, TypeError):
 		return None
 
 
+def cast_bool(value : Any) -> Optional[bool]:
+	if value == 'True':
+		return True
+	if value == 'False':
+		return False
+	return None
+
+
 def get_first(__list__ : Any) -> Any:
-	return next(iter(__list__), None)
+	if isinstance(__list__, Iterable):
+		return next(iter(__list__), None)
+	return None
 
 
 def get_last(__list__ : Any) -> Any:
-	return next(reversed(__list__), None)
+	if isinstance(__list__, Reversible):
+		return next(reversed(__list__), None)
+	return None

facefusion/config.py

@@ -1,92 +1,74 @@
 from configparser import ConfigParser
-from typing import Any, List, Optional
+from typing import List, Optional
 
 from facefusion import state_manager
-from facefusion.common_helper import cast_float, cast_int
+from facefusion.common_helper import cast_bool, cast_float, cast_int
 
-CONFIG = None
+CONFIG_PARSER = None
 
 
-def get_config() -> ConfigParser:
-	global CONFIG
+def get_config_parser() -> ConfigParser:
+	global CONFIG_PARSER
 
-	if CONFIG is None:
-		CONFIG = ConfigParser()
-		CONFIG.read(state_manager.get_item('config_path'), encoding = 'utf-8')
-	return CONFIG
+	if CONFIG_PARSER is None:
+		CONFIG_PARSER = ConfigParser()
+		CONFIG_PARSER.read(state_manager.get_item('config_path'), encoding = 'utf-8')
+	return CONFIG_PARSER
 
 
-def clear_config() -> None:
-	global CONFIG
+def clear_config_parser() -> None:
+	global CONFIG_PARSER
 
-	CONFIG = None
+	CONFIG_PARSER = None
 
 
-def get_str_value(key : str, fallback : Optional[str] = None) -> Optional[str]:
-	value = get_value_by_notation(key)
+def get_str_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[str]:
+	config_parser = get_config_parser()
 
-	if value or fallback:
-		return str(value or fallback)
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.get(section, option)
+	return fallback
+
+
+def get_int_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[int]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.getint(section, option)
+	return cast_int(fallback)
+
+
+def get_float_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[float]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.getfloat(section, option)
+	return cast_float(fallback)
+
+
+def get_bool_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[bool]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.getboolean(section, option)
+	return cast_bool(fallback)
+
+
+def get_str_list(section : str, option : str, fallback : Optional[str] = None) -> Optional[List[str]]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.get(section, option).split()
+	if fallback:
+		return fallback.split()
 	return None
 
 
-def get_int_value(key : str, fallback : Optional[str] = None) -> Optional[int]:
-	value = get_value_by_notation(key)
+def get_int_list(section : str, option : str, fallback : Optional[str] = None) -> Optional[List[int]]:
+	config_parser = get_config_parser()
 
-	if value or fallback:
-		return cast_int(value or fallback)
-	return None
-
-
-def get_float_value(key : str, fallback : Optional[str] = None) -> Optional[float]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return cast_float(value or fallback)
-	return None
-
-
-def get_bool_value(key : str, fallback : Optional[str] = None) -> Optional[bool]:
-	value = get_value_by_notation(key)
-
-	if value == 'True' or fallback == 'True':
-		return True
-	if value == 'False' or fallback == 'False':
-		return False
-	return None
-
-
-def get_str_list(key : str, fallback : Optional[str] = None) -> Optional[List[str]]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return [ str(value) for value in (value or fallback).split(' ') ]
-	return None
-
-
-def get_int_list(key : str, fallback : Optional[str] = None) -> Optional[List[int]]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return [ cast_int(value) for value in (value or fallback).split(' ') ]
-	return None
-
-
-def get_float_list(key : str, fallback : Optional[str] = None) -> Optional[List[float]]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return [ cast_float(value) for value in (value or fallback).split(' ') ]
-	return None
-
-
-def get_value_by_notation(key : str) -> Optional[Any]:
-	config = get_config()
-
-	if '.' in key:
-		section, name = key.split('.')
-		if section in config and name in config[section]:
-			return config[section][name]
-	if key in config:
-		return config[key]
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return list(map(int, config_parser.get(section, option).split()))
+	if fallback:
+		return list(map(int, fallback.split()))
 	return None

facefusion/content_analyser.py

@@ -1,67 +1,128 @@
 from functools import lru_cache
+from typing import List, Tuple
 
-import cv2
 import numpy
 from tqdm import tqdm
 
 from facefusion import inference_manager, state_manager, wording
+from facefusion.common_helper import is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
+from facefusion.execution import has_execution_provider
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import DownloadScope, Fps, InferencePool, ModelOptions, ModelSet, VisionFrame
-from facefusion.vision import detect_video_fps, get_video_frame, read_image
+from facefusion.types import Detection, DownloadScope, DownloadSet, ExecutionProvider, Fps, InferencePool, ModelSet, VisionFrame
+from facefusion.vision import detect_video_fps, fit_contain_frame, read_image, read_video_frame
 
-PROBABILITY_LIMIT = 0.80
-RATE_LIMIT = 10
 STREAM_COUNTER = 0
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
-		'open_nsfw':
+		'nsfw_1':
 		{
 			'hashes':
 			{
 				'content_analyser':
 				{
-					'url': resolve_download_url('models-3.0.0', 'open_nsfw.hash'),
-					'path': resolve_relative_path('../.assets/models/open_nsfw.hash')
+					'url': resolve_download_url('models-3.3.0', 'nsfw_1.hash'),
+					'path': resolve_relative_path('../.assets/models/nsfw_1.hash')
 				}
 			},
 			'sources':
 			{
 				'content_analyser':
 				{
-					'url': resolve_download_url('models-3.0.0', 'open_nsfw.onnx'),
-					'path': resolve_relative_path('../.assets/models/open_nsfw.onnx')
+					'url': resolve_download_url('models-3.3.0', 'nsfw_1.onnx'),
+					'path': resolve_relative_path('../.assets/models/nsfw_1.onnx')
 				}
 			},
-			'size': (224, 224),
-			'mean': [ 104, 117, 123 ]
+			'size': (640, 640),
+			'mean': (0.0, 0.0, 0.0),
+			'standard_deviation': (1.0, 1.0, 1.0)
+		},
+		'nsfw_2':
+		{
+			'hashes':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_2.hash'),
+					'path': resolve_relative_path('../.assets/models/nsfw_2.hash')
+				}
+			},
+			'sources':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_2.onnx'),
+					'path': resolve_relative_path('../.assets/models/nsfw_2.onnx')
+				}
+			},
+			'size': (384, 384),
+			'mean': (0.5, 0.5, 0.5),
+			'standard_deviation': (0.5, 0.5, 0.5)
+		},
+		'nsfw_3':
+		{
+			'hashes':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_3.hash'),
+					'path': resolve_relative_path('../.assets/models/nsfw_3.hash')
+				}
+			},
+			'sources':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_3.onnx'),
+					'path': resolve_relative_path('../.assets/models/nsfw_3.onnx')
+				}
+			},
+			'size': (448, 448),
+			'mean': (0.48145466, 0.4578275, 0.40821073),
+			'standard_deviation': (0.26862954, 0.26130258, 0.27577711)
 		}
 	}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ 'nsfw_1', 'nsfw_2', 'nsfw_3' ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ 'nsfw_1', 'nsfw_2', 'nsfw_3' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
-def get_model_options() -> ModelOptions:
-	return create_static_model_set('full').get('open_nsfw')
+def resolve_execution_providers() -> List[ExecutionProvider]:
+	if is_macos() and has_execution_provider('coreml'):
+		return [ 'cpu' ]
+	return state_manager.get_item('execution_providers')
+
+
+def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
+	model_set = create_static_model_set('full')
+	model_hash_set = {}
+	model_source_set = {}
+
+	for content_analyser_model in [ 'nsfw_1', 'nsfw_2', 'nsfw_3' ]:
+		model_hash_set[content_analyser_model] = model_set.get(content_analyser_model).get('hashes').get('content_analyser')
+		model_source_set[content_analyser_model] = model_set.get(content_analyser_model).get('sources').get('content_analyser')
+
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def analyse_stream(vision_frame : VisionFrame, video_fps : Fps) -> bool:
@@ -74,53 +135,92 @@ def analyse_stream(vision_frame : VisionFrame, video_fps : Fps) -> bool:
 
 
 def analyse_frame(vision_frame : VisionFrame) -> bool:
-	vision_frame = prepare_frame(vision_frame)
-	probability = forward(vision_frame)
-
-	return probability > PROBABILITY_LIMIT
+	return detect_nsfw(vision_frame)
 
 
-def forward(vision_frame : VisionFrame) -> float:
-	content_analyser = get_inference_pool().get('content_analyser')
-
-	with conditional_thread_semaphore():
-		probability = content_analyser.run(None,
-		{
-			'input': vision_frame
-		})[0][0][1]
-
-	return probability
-
-
-def prepare_frame(vision_frame : VisionFrame) -> VisionFrame:
-	model_size = get_model_options().get('size')
-	model_mean = get_model_options().get('mean')
-	vision_frame = cv2.resize(vision_frame, model_size).astype(numpy.float32)
-	vision_frame -= numpy.array(model_mean).astype(numpy.float32)
-	vision_frame = numpy.expand_dims(vision_frame, axis = 0)
-	return vision_frame
-
-
-@lru_cache(maxsize = None)
+@lru_cache()
 def analyse_image(image_path : str) -> bool:
 	vision_frame = read_image(image_path)
 	return analyse_frame(vision_frame)
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def analyse_video(video_path : str, trim_frame_start : int, trim_frame_end : int) -> bool:
 	video_fps = detect_video_fps(video_path)
 	frame_range = range(trim_frame_start, trim_frame_end)
 	rate = 0.0
+	total = 0
 	counter = 0
 
 	with tqdm(total = len(frame_range), desc = wording.get('analysing'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+
 		for frame_number in frame_range:
 			if frame_number % int(video_fps) == 0:
-				vision_frame = get_video_frame(video_path, frame_number)
+				vision_frame = read_video_frame(video_path, frame_number)
+				total += 1
 				if analyse_frame(vision_frame):
 					counter += 1
-			rate = counter * int(video_fps) / len(frame_range) * 100
-			progress.update()
+			if counter > 0 and total > 0:
+				rate = counter / total * 100
 			progress.set_postfix(rate = rate)
-	return rate > RATE_LIMIT
+			progress.update()
+
+	return bool(rate > 10.0)
+
+
+def detect_nsfw(vision_frame : VisionFrame) -> bool:
+	is_nsfw_1 = detect_with_nsfw_1(vision_frame)
+	is_nsfw_2 = detect_with_nsfw_2(vision_frame)
+	is_nsfw_3 = detect_with_nsfw_3(vision_frame)
+
+	return is_nsfw_1 and is_nsfw_2 or is_nsfw_1 and is_nsfw_3 or is_nsfw_2 and is_nsfw_3
+
+
+def detect_with_nsfw_1(vision_frame : VisionFrame) -> bool:
+	detect_vision_frame = prepare_detect_frame(vision_frame, 'nsfw_1')
+	detection = forward_nsfw(detect_vision_frame, 'nsfw_1')
+	detection_score = numpy.max(numpy.amax(detection[:, 4:], axis = 1))
+	return bool(detection_score > 0.2)
+
+
+def detect_with_nsfw_2(vision_frame : VisionFrame) -> bool:
+	detect_vision_frame = prepare_detect_frame(vision_frame, 'nsfw_2')
+	detection = forward_nsfw(detect_vision_frame, 'nsfw_2')
+	detection_score = detection[0] - detection[1]
+	return bool(detection_score > 0.25)
+
+
+def detect_with_nsfw_3(vision_frame : VisionFrame) -> bool:
+	detect_vision_frame = prepare_detect_frame(vision_frame, 'nsfw_3')
+	detection = forward_nsfw(detect_vision_frame, 'nsfw_3')
+	detection_score = (detection[2] + detection[3]) - (detection[0] + detection[1])
+	return bool(detection_score > 10.5)
+
+
+def forward_nsfw(vision_frame : VisionFrame, model_name : str) -> Detection:
+	content_analyser = get_inference_pool().get(model_name)
+
+	with conditional_thread_semaphore():
+		detection = content_analyser.run(None,
+		{
+			'input': vision_frame
+		})[0]
+
+	if model_name in [ 'nsfw_2', 'nsfw_3' ]:
+		return detection[0]
+
+	return detection
+
+
+def prepare_detect_frame(temp_vision_frame : VisionFrame, model_name : str) -> VisionFrame:
+	model_set = create_static_model_set('full').get(model_name)
+	model_size = model_set.get('size')
+	model_mean = model_set.get('mean')
+	model_standard_deviation = model_set.get('standard_deviation')
+
+	detect_vision_frame = fit_contain_frame(temp_vision_frame, model_size)
+	detect_vision_frame = detect_vision_frame[:, :, ::-1] / 255.0
+	detect_vision_frame -= model_mean
+	detect_vision_frame /= model_standard_deviation
+	detect_vision_frame = numpy.expand_dims(detect_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
+	return detect_vision_frame

facefusion/core.py

@@ -1,85 +1,99 @@
+import inspect
 import itertools
 import shutil
 import signal
 import sys
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from time import time
 
 import numpy
+from tqdm import tqdm
 
-from facefusion import content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, process_manager, state_manager, voice_extractor, wording
+from facefusion import benchmarker, cli_helper, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, hash_helper, logger, process_manager, state_manager, video_manager, voice_extractor, wording
 from facefusion.args import apply_args, collect_job_args, reduce_job_args, reduce_step_args
+from facefusion.audio import create_empty_audio_frame, get_audio_frame, get_voice_frame
 from facefusion.common_helper import get_first
 from facefusion.content_analyser import analyse_image, analyse_video
 from facefusion.download import conditional_download_hashes, conditional_download_sources
-from facefusion.exit_helper import conditional_exit, graceful_exit, hard_exit
-from facefusion.face_analyser import get_average_face, get_many_faces, get_one_face
-from facefusion.face_selector import sort_and_filter_faces
-from facefusion.face_store import append_reference_face, clear_reference_faces, get_reference_faces
+from facefusion.exit_helper import hard_exit, signal_exit
 from facefusion.ffmpeg import copy_image, extract_frames, finalize_image, merge_video, replace_audio, restore_audio
-from facefusion.filesystem import filter_audio_paths, is_image, is_video, list_directory, resolve_file_pattern
+from facefusion.filesystem import filter_audio_paths, get_file_name, is_image, is_video, resolve_file_paths, resolve_file_pattern
 from facefusion.jobs import job_helper, job_manager, job_runner
 from facefusion.jobs.job_list import compose_job_list
 from facefusion.memory import limit_system_memory
 from facefusion.processors.core import get_processors_modules
 from facefusion.program import create_program
 from facefusion.program_helper import validate_args
-from facefusion.statistics import conditional_log_statistics
-from facefusion.temp_helper import clear_temp_directory, create_temp_directory, get_temp_file_path, get_temp_frame_paths, move_temp_file
-from facefusion.typing import Args, ErrorCode
-from facefusion.vision import get_video_frame, pack_resolution, read_image, read_static_images, restrict_image_resolution, restrict_trim_frame, restrict_video_fps, restrict_video_resolution, unpack_resolution
+from facefusion.temp_helper import clear_temp_directory, create_temp_directory, get_temp_file_path, move_temp_file, resolve_temp_frame_paths
+from facefusion.time_helper import calculate_end_time
+from facefusion.types import Args, ErrorCode
+from facefusion.vision import detect_image_resolution, detect_video_resolution, pack_resolution, read_static_image, read_static_images, read_static_video_frame, restrict_image_resolution, restrict_trim_frame, restrict_video_fps, restrict_video_resolution, scale_resolution, write_image
 
 
 def cli() -> None:
-	signal.signal(signal.SIGINT, lambda signal_number, frame: graceful_exit(0))
-	program = create_program()
+	if pre_check():
+		signal.signal(signal.SIGINT, signal_exit)
+		program = create_program()
 
-	if validate_args(program):
-		args = vars(program.parse_args())
-		apply_args(args, state_manager.init_item)
+		if validate_args(program):
+			args = vars(program.parse_args())
+			apply_args(args, state_manager.init_item)
 
-		if state_manager.get_item('command'):
-			logger.init(state_manager.get_item('log_level'))
-			route(args)
+			if state_manager.get_item('command'):
+				logger.init(state_manager.get_item('log_level'))
+				route(args)
+			else:
+				program.print_help()
 		else:
-			program.print_help()
+			hard_exit(2)
 	else:
 		hard_exit(2)
 
 
 def route(args : Args) -> None:
 	system_memory_limit = state_manager.get_item('system_memory_limit')
+
 	if system_memory_limit and system_memory_limit > 0:
 		limit_system_memory(system_memory_limit)
+
 	if state_manager.get_item('command') == 'force-download':
 		error_code = force_download()
-		return conditional_exit(error_code)
+		hard_exit(error_code)
+
+	if state_manager.get_item('command') == 'benchmark':
+		if not common_pre_check() or not processors_pre_check() or not benchmarker.pre_check():
+			hard_exit(2)
+		benchmarker.render()
+
 	if state_manager.get_item('command') in [ 'job-list', 'job-create', 'job-submit', 'job-submit-all', 'job-delete', 'job-delete-all', 'job-add-step', 'job-remix-step', 'job-insert-step', 'job-remove-step' ]:
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
 		error_code = route_job_manager(args)
 		hard_exit(error_code)
-	if not pre_check():
-		return conditional_exit(2)
+
 	if state_manager.get_item('command') == 'run':
 		import facefusion.uis.core as ui
 
 		if not common_pre_check() or not processors_pre_check():
-			return conditional_exit(2)
+			hard_exit(2)
 		for ui_layout in ui.get_ui_layouts_modules(state_manager.get_item('ui_layouts')):
 			if not ui_layout.pre_check():
-				return conditional_exit(2)
+				hard_exit(2)
 		ui.init()
 		ui.launch()
+
 	if state_manager.get_item('command') == 'headless-run':
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
 		error_core = process_headless(args)
 		hard_exit(error_core)
+
 	if state_manager.get_item('command') == 'batch-run':
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
 		error_core = process_batch(args)
 		hard_exit(error_core)
+
 	if state_manager.get_item('command') in [ 'job-run', 'job-run-all', 'job-retry', 'job-retry-all' ]:
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
@@ -91,9 +105,11 @@ def pre_check() -> bool:
 	if sys.version_info < (3, 10):
 		logger.error(wording.get('python_not_supported').format(version = '3.10'), __name__)
 		return False
+
 	if not shutil.which('curl'):
 		logger.error(wording.get('curl_not_installed'), __name__)
 		return False
+
 	if not shutil.which('ffmpeg'):
 		logger.error(wording.get('ffmpeg_not_installed'), __name__)
 		return False
@@ -112,7 +128,10 @@ def common_pre_check() -> bool:
 		voice_extractor
 	]
 
-	return all(module.pre_check() for module in common_modules)
+	content_analyser_content = inspect.getsource(content_analyser).encode()
+	content_analyser_hash = hash_helper.create_hash(content_analyser_content)
+
+	return all(module.pre_check() for module in common_modules) and content_analyser_hash == '803b5ec7'
 
 
 def processors_pre_check() -> bool:
@@ -133,17 +152,17 @@ def force_download() -> ErrorCode:
 		face_recognizer,
 		voice_extractor
 	]
-	available_processors = [ file.get('name') for file in list_directory('facefusion/processors/modules') ]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	processor_modules = get_processors_modules(available_processors)
 
 	for module in common_modules + processor_modules:
 		if hasattr(module, 'create_static_model_set'):
 			for model in module.create_static_model_set(state_manager.get_item('download_scope')).values():
-				model_hashes = model.get('hashes')
-				model_sources = model.get('sources')
+				model_hash_set = model.get('hashes')
+				model_source_set = model.get('sources')
 
-				if model_hashes and model_sources:
-					if not conditional_download_hashes(model_hashes) or not conditional_download_sources(model_sources):
+				if model_hash_set and model_source_set:
+					if not conditional_download_hashes(model_hash_set) or not conditional_download_sources(model_source_set):
 						return 1
 
 	return 0
@@ -154,39 +173,45 @@ def route_job_manager(args : Args) -> ErrorCode:
 		job_headers, job_contents = compose_job_list(state_manager.get_item('job_status'))
 
 		if job_contents:
-			logger.table(job_headers, job_contents)
+			cli_helper.render_table(job_headers, job_contents)
 			return 0
 		return 1
+
 	if state_manager.get_item('command') == 'job-create':
 		if job_manager.create_job(state_manager.get_item('job_id')):
 			logger.info(wording.get('job_created').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.error(wording.get('job_not_created').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-submit':
 		if job_manager.submit_job(state_manager.get_item('job_id')):
 			logger.info(wording.get('job_submitted').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.error(wording.get('job_not_submitted').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-submit-all':
-		if job_manager.submit_jobs():
+		if job_manager.submit_jobs(state_manager.get_item('halt_on_error')):
 			logger.info(wording.get('job_all_submitted'), __name__)
 			return 0
 		logger.error(wording.get('job_all_not_submitted'), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-delete':
 		if job_manager.delete_job(state_manager.get_item('job_id')):
 			logger.info(wording.get('job_deleted').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.error(wording.get('job_not_deleted').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-delete-all':
-		if job_manager.delete_jobs():
+		if job_manager.delete_jobs(state_manager.get_item('halt_on_error')):
 			logger.info(wording.get('job_all_deleted'), __name__)
 			return 0
 		logger.error(wording.get('job_all_not_deleted'), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-add-step':
 		step_args = reduce_step_args(args)
 
@@ -195,6 +220,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 			return 0
 		logger.error(wording.get('job_step_not_added').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-remix-step':
 		step_args = reduce_step_args(args)
 
@@ -203,6 +229,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 			return 0
 		logger.error(wording.get('job_remix_step_not_added').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-insert-step':
 		step_args = reduce_step_args(args)
 
@@ -211,6 +238,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 			return 0
 		logger.error(wording.get('job_step_not_inserted').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-remove-step':
 		if job_manager.remove_step(state_manager.get_item('job_id'), state_manager.get_item('step_index')):
 			logger.info(wording.get('job_step_removed').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
@@ -224,28 +252,31 @@ def route_job_runner() -> ErrorCode:
 	if state_manager.get_item('command') == 'job-run':
 		logger.info(wording.get('running_job').format(job_id = state_manager.get_item('job_id')), __name__)
 		if job_runner.run_job(state_manager.get_item('job_id'), process_step):
-			logger.info(wording.get('processing_job_succeed').format(job_id = state_manager.get_item('job_id')), __name__)
+			logger.info(wording.get('processing_job_succeeded').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.info(wording.get('processing_job_failed').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-run-all':
 		logger.info(wording.get('running_jobs'), __name__)
-		if job_runner.run_jobs(process_step):
-			logger.info(wording.get('processing_jobs_succeed'), __name__)
+		if job_runner.run_jobs(process_step, state_manager.get_item('halt_on_error')):
+			logger.info(wording.get('processing_jobs_succeeded'), __name__)
 			return 0
 		logger.info(wording.get('processing_jobs_failed'), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-retry':
 		logger.info(wording.get('retrying_job').format(job_id = state_manager.get_item('job_id')), __name__)
 		if job_runner.retry_job(state_manager.get_item('job_id'), process_step):
-			logger.info(wording.get('processing_job_succeed').format(job_id = state_manager.get_item('job_id')), __name__)
+			logger.info(wording.get('processing_job_succeeded').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.info(wording.get('processing_job_failed').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-retry-all':
 		logger.info(wording.get('retrying_jobs'), __name__)
-		if job_runner.retry_jobs(process_step):
-			logger.info(wording.get('processing_jobs_succeed'), __name__)
+		if job_runner.retry_jobs(process_step, state_manager.get_item('halt_on_error')):
+			logger.info(wording.get('processing_jobs_succeeded'), __name__)
 			return 0
 		logger.info(wording.get('processing_jobs_failed'), __name__)
 		return 1
@@ -291,7 +322,6 @@ def process_batch(args : Args) -> ErrorCode:
 
 
 def process_step(job_id : str, step_index : int, step_args : Args) -> bool:
-	clear_reference_faces()
 	step_total = job_manager.count_step_total(job_id)
 	step_args.update(collect_job_args())
 	apply_args(step_args, state_manager.set_item)
@@ -305,81 +335,78 @@ def process_step(job_id : str, step_index : int, step_args : Args) -> bool:
 
 def conditional_process() -> ErrorCode:
 	start_time = time()
+
 	for processor_module in get_processors_modules(state_manager.get_item('processors')):
 		if not processor_module.pre_process('output'):
 			return 2
-	conditional_append_reference_faces()
+
 	if is_image(state_manager.get_item('target_path')):
 		return process_image(start_time)
 	if is_video(state_manager.get_item('target_path')):
 		return process_video(start_time)
+
 	return 0
 
 
-def conditional_append_reference_faces() -> None:
-	if 'reference' in state_manager.get_item('face_selector_mode') and not get_reference_faces():
-		source_frames = read_static_images(state_manager.get_item('source_paths'))
-		source_faces = get_many_faces(source_frames)
-		source_face = get_average_face(source_faces)
-		if is_video(state_manager.get_item('target_path')):
-			reference_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
-		else:
-			reference_frame = read_image(state_manager.get_item('target_path'))
-		reference_faces = sort_and_filter_faces(get_many_faces([ reference_frame ]))
-		reference_face = get_one_face(reference_faces, state_manager.get_item('reference_face_position'))
-		append_reference_face('origin', reference_face)
-
-		if source_face and reference_face:
-			for processor_module in get_processors_modules(state_manager.get_item('processors')):
-				abstract_reference_frame = processor_module.get_reference_frame(source_face, reference_face, reference_frame)
-				if numpy.any(abstract_reference_frame):
-					abstract_reference_faces = sort_and_filter_faces(get_many_faces([ abstract_reference_frame ]))
-					abstract_reference_face = get_one_face(abstract_reference_faces, state_manager.get_item('reference_face_position'))
-					append_reference_face(processor_module.__name__, abstract_reference_face)
-
-
 def process_image(start_time : float) -> ErrorCode:
 	if analyse_image(state_manager.get_item('target_path')):
 		return 3
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# create temp
 	logger.debug(wording.get('creating_temp'), __name__)
 	create_temp_directory(state_manager.get_item('target_path'))
-	# copy image
+
 	process_manager.start()
-	temp_image_resolution = pack_resolution(restrict_image_resolution(state_manager.get_item('target_path'), unpack_resolution(state_manager.get_item('output_image_resolution'))))
-	logger.info(wording.get('copying_image').format(resolution = temp_image_resolution), __name__)
+
+	output_image_resolution = scale_resolution(detect_image_resolution(state_manager.get_item('target_path')), state_manager.get_item('output_image_scale'))
+	temp_image_resolution = restrict_image_resolution(state_manager.get_item('target_path'), output_image_resolution)
+	logger.info(wording.get('copying_image').format(resolution = pack_resolution(temp_image_resolution)), __name__)
 	if copy_image(state_manager.get_item('target_path'), temp_image_resolution):
-		logger.debug(wording.get('copying_image_succeed'), __name__)
+		logger.debug(wording.get('copying_image_succeeded'), __name__)
 	else:
 		logger.error(wording.get('copying_image_failed'), __name__)
 		process_manager.end()
 		return 1
-	# process image
-	temp_file_path = get_temp_file_path(state_manager.get_item('target_path'))
+
+	temp_image_path = get_temp_file_path(state_manager.get_item('target_path'))
+	reference_vision_frame = read_static_image(temp_image_path)
+	source_vision_frames = read_static_images(state_manager.get_item('source_paths'))
+	source_audio_frame = create_empty_audio_frame()
+	source_voice_frame = create_empty_audio_frame()
+	target_vision_frame = read_static_image(temp_image_path)
+	temp_vision_frame = target_vision_frame.copy()
+
 	for processor_module in get_processors_modules(state_manager.get_item('processors')):
 		logger.info(wording.get('processing'), processor_module.__name__)
-		processor_module.process_image(state_manager.get_item('source_paths'), temp_file_path, temp_file_path)
+
+		temp_vision_frame = processor_module.process_frame(
+		{
+			'reference_vision_frame': reference_vision_frame,
+			'source_vision_frames': source_vision_frames,
+			'source_audio_frame': source_audio_frame,
+			'source_voice_frame': source_voice_frame,
+			'target_vision_frame': target_vision_frame,
+			'temp_vision_frame': temp_vision_frame
+		})
+
 		processor_module.post_process()
+
+	write_image(temp_image_path, temp_vision_frame)
 	if is_process_stopping():
-		process_manager.end()
 		return 4
-	# finalize image
-	logger.info(wording.get('finalizing_image').format(resolution = state_manager.get_item('output_image_resolution')), __name__)
-	if finalize_image(state_manager.get_item('target_path'), state_manager.get_item('output_path'), state_manager.get_item('output_image_resolution')):
-		logger.debug(wording.get('finalizing_image_succeed'), __name__)
+
+	logger.info(wording.get('finalizing_image').format(resolution = pack_resolution(output_image_resolution)), __name__)
+	if finalize_image(state_manager.get_item('target_path'), state_manager.get_item('output_path'), output_image_resolution):
+		logger.debug(wording.get('finalizing_image_succeeded'), __name__)
 	else:
 		logger.warn(wording.get('finalizing_image_skipped'), __name__)
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# validate image
+
 	if is_image(state_manager.get_item('output_path')):
-		seconds = '{:.2f}'.format((time() - start_time) % 60)
-		logger.info(wording.get('processing_image_succeed').format(seconds = seconds), __name__)
-		conditional_log_statistics()
+		logger.info(wording.get('processing_image_succeeded').format(seconds = calculate_end_time(start_time)), __name__)
 	else:
 		logger.error(wording.get('processing_image_failed'), __name__)
 		process_manager.end()
@@ -392,82 +419,100 @@ def process_video(start_time : float) -> ErrorCode:
 	trim_frame_start, trim_frame_end = restrict_trim_frame(state_manager.get_item('target_path'), state_manager.get_item('trim_frame_start'), state_manager.get_item('trim_frame_end'))
 	if analyse_video(state_manager.get_item('target_path'), trim_frame_start, trim_frame_end):
 		return 3
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# create temp
 	logger.debug(wording.get('creating_temp'), __name__)
 	create_temp_directory(state_manager.get_item('target_path'))
-	# extract frames
+
 	process_manager.start()
-	temp_video_resolution = pack_resolution(restrict_video_resolution(state_manager.get_item('target_path'), unpack_resolution(state_manager.get_item('output_video_resolution'))))
+	output_video_resolution = scale_resolution(detect_video_resolution(state_manager.get_item('target_path')), state_manager.get_item('output_video_scale'))
+	temp_video_resolution = restrict_video_resolution(state_manager.get_item('target_path'), output_video_resolution)
 	temp_video_fps = restrict_video_fps(state_manager.get_item('target_path'), state_manager.get_item('output_video_fps'))
-	logger.info(wording.get('extracting_frames').format(resolution = temp_video_resolution, fps = temp_video_fps), __name__)
+	logger.info(wording.get('extracting_frames').format(resolution = pack_resolution(temp_video_resolution), fps = temp_video_fps), __name__)
+
 	if extract_frames(state_manager.get_item('target_path'), temp_video_resolution, temp_video_fps, trim_frame_start, trim_frame_end):
-		logger.debug(wording.get('extracting_frames_succeed'), __name__)
+		logger.debug(wording.get('extracting_frames_succeeded'), __name__)
 	else:
 		if is_process_stopping():
-			process_manager.end()
 			return 4
 		logger.error(wording.get('extracting_frames_failed'), __name__)
 		process_manager.end()
 		return 1
-	# process frames
-	temp_frame_paths = get_temp_frame_paths(state_manager.get_item('target_path'))
+
+	temp_frame_paths = resolve_temp_frame_paths(state_manager.get_item('target_path'))
+
 	if temp_frame_paths:
+		with tqdm(total = len(temp_frame_paths), desc = wording.get('processing'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+			progress.set_postfix(execution_providers = state_manager.get_item('execution_providers'))
+
+			with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
+				futures = []
+
+				for frame_number, temp_frame_path in enumerate(temp_frame_paths):
+					future = executor.submit(process_temp_frame, temp_frame_path, frame_number)
+					futures.append(future)
+
+				for future in as_completed(futures):
+					if is_process_stopping():
+						for __future__ in futures:
+							__future__.cancel()
+
+					if not future.cancelled():
+						future.result()
+						progress.update()
+
 		for processor_module in get_processors_modules(state_manager.get_item('processors')):
-			logger.info(wording.get('processing'), processor_module.__name__)
-			processor_module.process_video(state_manager.get_item('source_paths'), temp_frame_paths)
 			processor_module.post_process()
+
 		if is_process_stopping():
 			return 4
 	else:
 		logger.error(wording.get('temp_frames_not_found'), __name__)
 		process_manager.end()
 		return 1
-	# merge video
-	logger.info(wording.get('merging_video').format(resolution = state_manager.get_item('output_video_resolution'), fps = state_manager.get_item('output_video_fps')), __name__)
-	if merge_video(state_manager.get_item('target_path'), state_manager.get_item('output_video_resolution'), state_manager.get_item('output_video_fps')):
-		logger.debug(wording.get('merging_video_succeed'), __name__)
+
+	logger.info(wording.get('merging_video').format(resolution = pack_resolution(output_video_resolution), fps = state_manager.get_item('output_video_fps')), __name__)
+	if merge_video(state_manager.get_item('target_path'), temp_video_fps, output_video_resolution, state_manager.get_item('output_video_fps'), trim_frame_start, trim_frame_end):
+		logger.debug(wording.get('merging_video_succeeded'), __name__)
 	else:
 		if is_process_stopping():
-			process_manager.end()
 			return 4
 		logger.error(wording.get('merging_video_failed'), __name__)
 		process_manager.end()
 		return 1
-	# handle audio
-	if state_manager.get_item('skip_audio'):
+
+	if state_manager.get_item('output_audio_volume') == 0:
 		logger.info(wording.get('skipping_audio'), __name__)
 		move_temp_file(state_manager.get_item('target_path'), state_manager.get_item('output_path'))
 	else:
 		source_audio_path = get_first(filter_audio_paths(state_manager.get_item('source_paths')))
 		if source_audio_path:
 			if replace_audio(state_manager.get_item('target_path'), source_audio_path, state_manager.get_item('output_path')):
-				logger.debug(wording.get('replacing_audio_succeed'), __name__)
+				video_manager.clear_video_pool()
+				logger.debug(wording.get('replacing_audio_succeeded'), __name__)
 			else:
+				video_manager.clear_video_pool()
 				if is_process_stopping():
-					process_manager.end()
 					return 4
 				logger.warn(wording.get('replacing_audio_skipped'), __name__)
 				move_temp_file(state_manager.get_item('target_path'), state_manager.get_item('output_path'))
 		else:
-			if restore_audio(state_manager.get_item('target_path'), state_manager.get_item('output_path'), state_manager.get_item('output_video_fps'), trim_frame_start, trim_frame_end):
-				logger.debug(wording.get('restoring_audio_succeed'), __name__)
+			if restore_audio(state_manager.get_item('target_path'), state_manager.get_item('output_path'), trim_frame_start, trim_frame_end):
+				video_manager.clear_video_pool()
+				logger.debug(wording.get('restoring_audio_succeeded'), __name__)
 			else:
+				video_manager.clear_video_pool()
 				if is_process_stopping():
-					process_manager.end()
 					return 4
 				logger.warn(wording.get('restoring_audio_skipped'), __name__)
 				move_temp_file(state_manager.get_item('target_path'), state_manager.get_item('output_path'))
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# validate video
+
 	if is_video(state_manager.get_item('output_path')):
-		seconds = '{:.2f}'.format((time() - start_time))
-		logger.info(wording.get('processing_video_succeed').format(seconds = seconds), __name__)
-		conditional_log_statistics()
+		logger.info(wording.get('processing_video_succeeded').format(seconds = calculate_end_time(start_time)), __name__)
 	else:
 		logger.error(wording.get('processing_video_failed'), __name__)
 		process_manager.end()
@@ -476,6 +521,36 @@ def process_video(start_time : float) -> ErrorCode:
 	return 0
 
 
+def process_temp_frame(temp_frame_path : str, frame_number : int) -> bool:
+	reference_vision_frame = read_static_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
+	source_vision_frames = read_static_images(state_manager.get_item('source_paths'))
+	source_audio_path = get_first(filter_audio_paths(state_manager.get_item('source_paths')))
+	temp_video_fps = restrict_video_fps(state_manager.get_item('target_path'), state_manager.get_item('output_video_fps'))
+	target_vision_frame = read_static_image(temp_frame_path)
+	temp_vision_frame = target_vision_frame.copy()
+
+	source_audio_frame = get_audio_frame(source_audio_path, temp_video_fps, frame_number)
+	source_voice_frame = get_voice_frame(source_audio_path, temp_video_fps, frame_number)
+
+	if not numpy.any(source_audio_frame):
+		source_audio_frame = create_empty_audio_frame()
+	if not numpy.any(source_voice_frame):
+		source_voice_frame = create_empty_audio_frame()
+
+	for processor_module in get_processors_modules(state_manager.get_item('processors')):
+		temp_vision_frame = processor_module.process_frame(
+		{
+			'reference_vision_frame': reference_vision_frame,
+			'source_vision_frames': source_vision_frames,
+			'source_audio_frame': source_audio_frame,
+			'source_voice_frame': source_voice_frame,
+			'target_vision_frame': target_vision_frame,
+			'temp_vision_frame': temp_vision_frame
+		})
+
+	return write_image(temp_frame_path, temp_vision_frame)
+
+
 def is_process_stopping() -> bool:
 	if process_manager.is_stopping():
 		process_manager.end()

facefusion/curl_builder.py

@@ -0,0 +1,27 @@
+import itertools
+import shutil
+
+from facefusion import metadata
+from facefusion.types import Commands
+
+
+def run(commands : Commands) -> Commands:
+	user_agent = metadata.get('name') + '/' + metadata.get('version')
+
+	return [ shutil.which('curl'), '--user-agent', user_agent, '--insecure', '--location', '--silent' ] + commands
+
+
+def chain(*commands : Commands) -> Commands:
+	return list(itertools.chain(*commands))
+
+
+def head(url : str) -> Commands:
+	return [ '-I', url ]
+
+
+def download(url : str, download_file_path : str) -> Commands:
+	return [ '--create-dirs', '--continue-at', '-', '--output', download_file_path, url ]
+
+
+def set_timeout(timeout : int) -> Commands:
+	return [ '--connect-timeout', str(timeout) ]

facefusion/download.py

@@ -1,5 +1,4 @@
 import os
-import shutil
 import subprocess
 from functools import lru_cache
 from typing import List, Optional, Tuple
@@ -8,15 +7,14 @@ from urllib.parse import urlparse
 from tqdm import tqdm
 
 import facefusion.choices
-from facefusion import logger, process_manager, state_manager, wording
-from facefusion.filesystem import get_file_size, is_file, remove_file
+from facefusion import curl_builder, logger, process_manager, state_manager, wording
+from facefusion.filesystem import get_file_name, get_file_size, is_file, remove_file
 from facefusion.hash_helper import validate_hash
-from facefusion.typing import DownloadProvider, DownloadSet
+from facefusion.types import Commands, DownloadProvider, DownloadSet
 
 
-def open_curl(args : List[str]) -> subprocess.Popen[bytes]:
-	commands = [ shutil.which('curl'), '--silent', '--insecure', '--location' ]
-	commands.extend(args)
+def open_curl(commands : Commands) -> subprocess.Popen[bytes]:
+	commands = curl_builder.run(commands)
 	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)
 
 
@@ -29,7 +27,10 @@ def conditional_download(download_directory_path : str, urls : List[str]) -> Non
 
 		if initial_size < download_size:
 			with tqdm(total = download_size, initial = initial_size, desc = wording.get('downloading'), unit = 'B', unit_scale = True, unit_divisor = 1024, ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
-				commands = [ '--create-dirs', '--continue-at', '-', '--output', download_file_path, url ]
+				commands = curl_builder.chain(
+					curl_builder.download(url, download_file_path),
+					curl_builder.set_timeout(5)
+				)
 				open_curl(commands)
 				current_size = initial_size
 				progress.set_postfix(download_providers = state_manager.get_item('download_providers'), file_name = download_file_name)
@@ -40,9 +41,12 @@ def conditional_download(download_directory_path : str, urls : List[str]) -> Non
 						progress.update(current_size - progress.n)
 
 
-@lru_cache(maxsize = None)
+@lru_cache(maxsize = 1024)
 def get_static_download_size(url : str) -> int:
-	commands = [ '-I', url ]
+	commands = curl_builder.chain(
+		curl_builder.head(url),
+		curl_builder.set_timeout(5)
+	)
 	process = open_curl(commands)
 	lines = reversed(process.stdout.readlines())
 
@@ -55,34 +59,37 @@ def get_static_download_size(url : str) -> int:
 	return 0
 
 
-@lru_cache(maxsize = None)
+@lru_cache(maxsize = 1024)
 def ping_static_url(url : str) -> bool:
-	commands = [ '-I', url ]
+	commands = curl_builder.chain(
+		curl_builder.head(url),
+		curl_builder.set_timeout(5)
+	)
 	process = open_curl(commands)
 	process.communicate()
 	return process.returncode == 0
 
 
-def conditional_download_hashes(hashes : DownloadSet) -> bool:
-	hash_paths = [ hashes.get(hash_key).get('path') for hash_key in hashes.keys() ]
+def conditional_download_hashes(hash_set : DownloadSet) -> bool:
+	hash_paths = [ hash_set.get(hash_key).get('path') for hash_key in hash_set.keys() ]
 
 	process_manager.check()
 	_, invalid_hash_paths = validate_hash_paths(hash_paths)
 	if invalid_hash_paths:
-		for index in hashes:
-			if hashes.get(index).get('path') in invalid_hash_paths:
-				invalid_hash_url = hashes.get(index).get('url')
+		for index in hash_set:
+			if hash_set.get(index).get('path') in invalid_hash_paths:
+				invalid_hash_url = hash_set.get(index).get('url')
 				if invalid_hash_url:
-					download_directory_path = os.path.dirname(hashes.get(index).get('path'))
+					download_directory_path = os.path.dirname(hash_set.get(index).get('path'))
 					conditional_download(download_directory_path, [ invalid_hash_url ])
 
 	valid_hash_paths, invalid_hash_paths = validate_hash_paths(hash_paths)
 
 	for valid_hash_path in valid_hash_paths:
-		valid_hash_file_name, _ = os.path.splitext(os.path.basename(valid_hash_path))
-		logger.debug(wording.get('validating_hash_succeed').format(hash_file_name = valid_hash_file_name), __name__)
+		valid_hash_file_name = get_file_name(valid_hash_path)
+		logger.debug(wording.get('validating_hash_succeeded').format(hash_file_name = valid_hash_file_name), __name__)
 	for invalid_hash_path in invalid_hash_paths:
-		invalid_hash_file_name, _ = os.path.splitext(os.path.basename(invalid_hash_path))
+		invalid_hash_file_name = get_file_name(invalid_hash_path)
 		logger.error(wording.get('validating_hash_failed').format(hash_file_name = invalid_hash_file_name), __name__)
 
 	if not invalid_hash_paths:
@@ -90,26 +97,26 @@ def conditional_download_hashes(hashes : DownloadSet) -> bool:
 	return not invalid_hash_paths
 
 
-def conditional_download_sources(sources : DownloadSet) -> bool:
-	source_paths = [ sources.get(source_key).get('path') for source_key in sources.keys() ]
+def conditional_download_sources(source_set : DownloadSet) -> bool:
+	source_paths = [ source_set.get(source_key).get('path') for source_key in source_set.keys() ]
 
 	process_manager.check()
 	_, invalid_source_paths = validate_source_paths(source_paths)
 	if invalid_source_paths:
-		for index in sources:
-			if sources.get(index).get('path') in invalid_source_paths:
-				invalid_source_url = sources.get(index).get('url')
+		for index in source_set:
+			if source_set.get(index).get('path') in invalid_source_paths:
+				invalid_source_url = source_set.get(index).get('url')
 				if invalid_source_url:
-					download_directory_path = os.path.dirname(sources.get(index).get('path'))
+					download_directory_path = os.path.dirname(source_set.get(index).get('path'))
 					conditional_download(download_directory_path, [ invalid_source_url ])
 
 	valid_source_paths, invalid_source_paths = validate_source_paths(source_paths)
 
 	for valid_source_path in valid_source_paths:
-		valid_source_file_name, _ = os.path.splitext(os.path.basename(valid_source_path))
-		logger.debug(wording.get('validating_source_succeed').format(source_file_name = valid_source_file_name), __name__)
+		valid_source_file_name = get_file_name(valid_source_path)
+		logger.debug(wording.get('validating_source_succeeded').format(source_file_name = valid_source_file_name), __name__)
 	for invalid_source_path in invalid_source_paths:
-		invalid_source_file_name, _ = os.path.splitext(os.path.basename(invalid_source_path))
+		invalid_source_file_name = get_file_name(invalid_source_path)
 		logger.error(wording.get('validating_source_failed').format(source_file_name = invalid_source_file_name), __name__)
 
 		if remove_file(invalid_source_path):
@@ -129,6 +136,7 @@ def validate_hash_paths(hash_paths : List[str]) -> Tuple[List[str], List[str]]:
 			valid_hash_paths.append(hash_path)
 		else:
 			invalid_hash_paths.append(hash_path)
+
 	return valid_hash_paths, invalid_hash_paths
 
 
@@ -141,6 +149,7 @@ def validate_source_paths(source_paths : List[str]) -> Tuple[List[str], List[str
 			valid_source_paths.append(source_path)
 		else:
 			invalid_source_paths.append(source_path)
+
 	return valid_source_paths, invalid_source_paths
 
 
@@ -148,16 +157,18 @@ def resolve_download_url(base_name : str, file_name : str) -> Optional[str]:
 	download_providers = state_manager.get_item('download_providers')
 
 	for download_provider in download_providers:
-		if ping_download_provider(download_provider):
-			return resolve_download_url_by_provider(download_provider, base_name, file_name)
+		download_url = resolve_download_url_by_provider(download_provider, base_name, file_name)
+		if download_url:
+			return download_url
+
 	return None
 
 
-def ping_download_provider(download_provider : DownloadProvider) -> bool:
-	download_provider_value = facefusion.choices.download_provider_set.get(download_provider)
-	return ping_static_url(download_provider_value.get('url'))
-
-
 def resolve_download_url_by_provider(download_provider : DownloadProvider, base_name : str, file_name : str) -> Optional[str]:
 	download_provider_value = facefusion.choices.download_provider_set.get(download_provider)
-	return download_provider_value.get('url') + download_provider_value.get('path').format(base_name = base_name, file_name = file_name)
+
+	for download_provider_url in download_provider_value.get('urls'):
+		if ping_static_url(download_provider_url):
+			return download_provider_url + download_provider_value.get('path').format(base_name = base_name, file_name = file_name)
+
+	return None

facefusion/execution.py

@@ -2,12 +2,12 @@ import shutil
 import subprocess
 import xml.etree.ElementTree as ElementTree
 from functools import lru_cache
-from typing import Any, List, Optional
+from typing import List, Optional
 
 from onnxruntime import get_available_providers, set_default_logger_severity
 
 import facefusion.choices
-from facefusion.typing import ExecutionDevice, ExecutionProvider, ValueAndUnit
+from facefusion.types import ExecutionDevice, ExecutionProvider, InferenceSessionProvider, ValueAndUnit
 
 set_default_logger_severity(3)
 
@@ -17,28 +17,29 @@ def has_execution_provider(execution_provider : ExecutionProvider) -> bool:
 
 
 def get_available_execution_providers() -> List[ExecutionProvider]:
-	inference_execution_providers = get_available_providers()
-	available_execution_providers = []
+	inference_session_providers = get_available_providers()
+	available_execution_providers : List[ExecutionProvider] = []
 
 	for execution_provider, execution_provider_value in facefusion.choices.execution_provider_set.items():
-		if execution_provider_value in inference_execution_providers:
-			available_execution_providers.append(execution_provider)
+		if execution_provider_value in inference_session_providers:
+			index = facefusion.choices.execution_providers.index(execution_provider)
+			available_execution_providers.insert(index, execution_provider)
 
 	return available_execution_providers
 
 
-def create_inference_execution_providers(execution_device_id : str, execution_providers : List[ExecutionProvider]) -> List[Any]:
-	inference_execution_providers : List[Any] = []
+def create_inference_session_providers(execution_device_id : str, execution_providers : List[ExecutionProvider]) -> List[InferenceSessionProvider]:
+	inference_session_providers : List[InferenceSessionProvider] = []
 
 	for execution_provider in execution_providers:
 		if execution_provider == 'cuda':
-			inference_execution_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id,
-				'cudnn_conv_algo_search': 'DEFAULT' if is_geforce_16_series() else 'EXHAUSTIVE'
+				'cudnn_conv_algo_search': resolve_cudnn_conv_algo_search()
 			}))
 		if execution_provider == 'tensorrt':
-			inference_execution_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id,
 				'trt_engine_cache_enable': True,
@@ -47,31 +48,51 @@ def create_inference_execution_providers(execution_device_id : str, execution_pr
 				'trt_timing_cache_path': '.caches',
 				'trt_builder_optimization_level': 5
 			}))
-		if execution_provider == 'openvino':
-			inference_execution_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
-			{
-				'device_type': 'GPU' if execution_device_id == '0' else 'GPU.' + execution_device_id,
-				'precision': 'FP32'
-			}))
 		if execution_provider in [ 'directml', 'rocm' ]:
-			inference_execution_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id
 			}))
+		if execution_provider == 'migraphx':
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			{
+				'device_id': execution_device_id,
+				'migraphx_model_cache_dir': '.caches'
+			}))
+		if execution_provider == 'openvino':
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			{
+				'device_type': resolve_openvino_device_type(execution_device_id),
+				'precision': 'FP32'
+			}))
 		if execution_provider == 'coreml':
-			inference_execution_providers.append(facefusion.choices.execution_provider_set.get(execution_provider))
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			{
+				'SpecializationStrategy': 'FastPrediction',
+				'ModelCacheDirectory': '.caches'
+			}))
 
 	if 'cpu' in execution_providers:
-		inference_execution_providers.append(facefusion.choices.execution_provider_set.get('cpu'))
+		inference_session_providers.append(facefusion.choices.execution_provider_set.get('cpu'))
 
-	return inference_execution_providers
+	return inference_session_providers
 
 
-def is_geforce_16_series() -> bool:
+def resolve_cudnn_conv_algo_search() -> str:
 	execution_devices = detect_static_execution_devices()
 	product_names = ('GeForce GTX 1630', 'GeForce GTX 1650', 'GeForce GTX 1660')
 
-	return any(execution_device.get('product').get('name').startswith(product_names) for execution_device in execution_devices)
+	for execution_device in execution_devices:
+		if execution_device.get('product').get('name').startswith(product_names):
+			return 'DEFAULT'
+
+	return 'EXHAUSTIVE'
+
+
+def resolve_openvino_device_type(execution_device_id : str) -> str:
+	if execution_device_id == '0':
+		return 'GPU'
+	return 'GPU.' + execution_device_id
 
 
 def run_nvidia_smi() -> subprocess.Popen[bytes]:
@@ -79,7 +100,7 @@ def run_nvidia_smi() -> subprocess.Popen[bytes]:
 	return subprocess.Popen(commands, stdout = subprocess.PIPE)
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def detect_static_execution_devices() -> List[ExecutionDevice]:
 	return detect_execution_devices()
 
@@ -129,7 +150,7 @@ def detect_execution_devices() -> List[ExecutionDevice]:
 
 def create_value_and_unit(text : str) -> Optional[ValueAndUnit]:
 	if ' ' in text:
-		value, unit = text.split(' ')
+		value, unit = text.split()
 
 		return\
 		{

facefusion/exit_helper.py

@@ -1,26 +1,34 @@
+import os
 import signal
 import sys
 from time import sleep
+from types import FrameType
 
 from facefusion import process_manager, state_manager
 from facefusion.temp_helper import clear_temp_directory
-from facefusion.typing import ErrorCode
+from facefusion.types import ErrorCode
+
+
+def fatal_exit(error_code : ErrorCode) -> None:
+	os._exit(error_code)
 
 
 def hard_exit(error_code : ErrorCode) -> None:
-	signal.signal(signal.SIGINT, signal.SIG_IGN)
 	sys.exit(error_code)
 
 
-def conditional_exit(error_code : ErrorCode) -> None:
-	if state_manager.get_item('command') == 'headless-run':
-		hard_exit(error_code)
+def signal_exit(signum : int, frame : FrameType) -> None:
+	graceful_exit(0)
 
 
 def graceful_exit(error_code : ErrorCode) -> None:
+	signal.signal(signal.SIGINT, signal.SIG_IGN)
 	process_manager.stop()
+
 	while process_manager.is_processing():
 		sleep(0.5)
+
 	if state_manager.get_item('target_path'):
 		clear_temp_directory(state_manager.get_item('target_path'))
+
 	hard_exit(error_code)

facefusion/face_analyser.py

@@ -5,12 +5,12 @@ import numpy
 from facefusion import state_manager
 from facefusion.common_helper import get_first
 from facefusion.face_classifier import classify_face
-from facefusion.face_detector import detect_faces, detect_rotated_faces
+from facefusion.face_detector import detect_faces, detect_faces_by_angle
 from facefusion.face_helper import apply_nms, convert_to_face_landmark_5, estimate_face_angle, get_nms_threshold
-from facefusion.face_landmarker import detect_face_landmarks, estimate_face_landmark_68_5
-from facefusion.face_recognizer import calc_embedding
+from facefusion.face_landmarker import detect_face_landmark, estimate_face_landmark_68_5
+from facefusion.face_recognizer import calculate_face_embedding
 from facefusion.face_store import get_static_faces, set_static_faces
-from facefusion.typing import BoundingBox, Face, FaceLandmark5, FaceLandmarkSet, FaceScoreSet, Score, VisionFrame
+from facefusion.types import BoundingBox, Face, FaceLandmark5, FaceLandmarkSet, FaceScoreSet, Score, VisionFrame
 
 
 def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox], face_scores : List[Score], face_landmarks_5 : List[FaceLandmark5]) -> List[Face]:
@@ -29,7 +29,7 @@ def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox],
 		face_angle = estimate_face_angle(face_landmark_68_5)
 
 		if state_manager.get_item('face_landmarker_score') > 0:
-			face_landmark_68, face_landmark_score_68 = detect_face_landmarks(vision_frame, bounding_box, face_angle)
+			face_landmark_68, face_landmark_score_68 = detect_face_landmark(vision_frame, bounding_box, face_angle)
 		if face_landmark_score_68 > state_manager.get_item('face_landmarker_score'):
 			face_landmark_5_68 = convert_to_face_landmark_5(face_landmark_68)
 
@@ -45,15 +45,15 @@ def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox],
 			'detector': face_score,
 			'landmarker': face_landmark_score_68
 		}
-		embedding, normed_embedding = calc_embedding(vision_frame, face_landmark_set.get('5/68'))
+		face_embedding, face_embedding_norm = calculate_face_embedding(vision_frame, face_landmark_set.get('5/68'))
 		gender, age, race = classify_face(vision_frame, face_landmark_set.get('5/68'))
 		faces.append(Face(
 			bounding_box = bounding_box,
 			score_set = face_score_set,
 			landmark_set = face_landmark_set,
 			angle = face_angle,
-			embedding = embedding,
-			normed_embedding = normed_embedding,
+			embedding = face_embedding,
+			embedding_norm = face_embedding_norm,
 			gender = gender,
 			age = age,
 			race = race
@@ -69,23 +69,23 @@ def get_one_face(faces : List[Face], position : int = 0) -> Optional[Face]:
 
 
 def get_average_face(faces : List[Face]) -> Optional[Face]:
-	embeddings = []
-	normed_embeddings = []
+	face_embeddings = []
+	face_embeddings_norm = []
 
 	if faces:
 		first_face = get_first(faces)
 
 		for face in faces:
-			embeddings.append(face.embedding)
-			normed_embeddings.append(face.normed_embedding)
+			face_embeddings.append(face.embedding)
+			face_embeddings_norm.append(face.embedding_norm)
 
 		return Face(
 			bounding_box = first_face.bounding_box,
 			score_set = first_face.score_set,
 			landmark_set = first_face.landmark_set,
 			angle = first_face.angle,
-			embedding = numpy.mean(embeddings, axis = 0),
-			normed_embedding = numpy.mean(normed_embeddings, axis = 0),
+			embedding = numpy.mean(face_embeddings, axis = 0),
+			embedding_norm = numpy.mean(face_embeddings_norm, axis = 0),
 			gender = first_face.gender,
 			age = first_face.age,
 			race = first_face.race
@@ -110,7 +110,7 @@ def get_many_faces(vision_frames : List[VisionFrame]) -> List[Face]:
 					if face_detector_angle == 0:
 						bounding_boxes, face_scores, face_landmarks_5 = detect_faces(vision_frame)
 					else:
-						bounding_boxes, face_scores, face_landmarks_5 = detect_rotated_faces(vision_frame, face_detector_angle)
+						bounding_boxes, face_scores, face_landmarks_5 = detect_faces_by_angle(vision_frame, face_detector_angle)
 					all_bounding_boxes.extend(bounding_boxes)
 					all_face_scores.extend(face_scores)
 					all_face_landmarks_5.extend(face_landmarks_5)
@@ -122,3 +122,28 @@ def get_many_faces(vision_frames : List[VisionFrame]) -> List[Face]:
 						many_faces.extend(faces)
 						set_static_faces(vision_frame, faces)
 	return many_faces
+
+
+def scale_face(target_face : Face, target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> Face:
+	scale_x = temp_vision_frame.shape[1] / target_vision_frame.shape[1]
+	scale_y = temp_vision_frame.shape[0] / target_vision_frame.shape[0]
+
+	bounding_box =\
+	[
+		target_face.bounding_box * scale_x,
+		target_face.bounding_box * scale_y,
+		target_face.bounding_box * scale_x,
+		target_face.bounding_box * scale_y
+	]
+	landmark_set =\
+	{
+		'5': target_face.landmark_set.get('5') * numpy.array([ scale_x, scale_y ]),
+		'5/68': target_face.landmark_set.get('5/68') * numpy.array([ scale_x, scale_y ]),
+		'68': target_face.landmark_set.get('68') * numpy.array([ scale_x, scale_y ]),
+		'68/5': target_face.landmark_set.get('68/5') * numpy.array([ scale_x, scale_y ])
+	}
+
+	return target_face._replace(
+		bounding_box = bounding_box,
+		landmark_set = landmark_set
+	)

facefusion/face_classifier.py

@@ -8,10 +8,10 @@ from facefusion.download import conditional_download_hashes, conditional_downloa
 from facefusion.face_helper import warp_face_by_face_landmark_5
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import Age, DownloadScope, FaceLandmark5, Gender, InferencePool, ModelOptions, ModelSet, Race, VisionFrame
+from facefusion.types import Age, DownloadScope, FaceLandmark5, Gender, InferencePool, ModelOptions, ModelSet, Race, VisionFrame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -42,12 +42,15 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ 'fairface' ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ 'fairface' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
@@ -55,10 +58,10 @@ def get_model_options() -> ModelOptions:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def classify_face(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5) -> Tuple[Gender, Age, Race]:
@@ -67,7 +70,7 @@ def classify_face(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmar
 	model_mean = get_model_options().get('mean')
 	model_standard_deviation = get_model_options().get('standard_deviation')
 	crop_vision_frame, _ = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_template, model_size)
-	crop_vision_frame = crop_vision_frame.astype(numpy.float32)[:, :, ::-1] / 255
+	crop_vision_frame = crop_vision_frame.astype(numpy.float32)[:, :, ::-1] / 255.0
 	crop_vision_frame -= model_mean
 	crop_vision_frame /= model_standard_deviation
 	crop_vision_frame = crop_vision_frame.transpose(2, 0, 1)

facefusion/face_detector.py

@@ -1,19 +1,19 @@
-from typing import List, Tuple
+from functools import lru_cache
+from typing import List, Sequence, Tuple
 
 import cv2
 import numpy
-from charset_normalizer.md import lru_cache
 
 from facefusion import inference_manager, state_manager
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_helper import create_rotated_matrix_and_size, create_static_anchors, distance_to_bounding_box, distance_to_face_landmark_5, normalize_bounding_box, transform_bounding_box, transform_points
+from facefusion.face_helper import create_rotation_matrix_and_size, create_static_anchors, distance_to_bounding_box, distance_to_face_landmark_5, normalize_bounding_box, transform_bounding_box, transform_points
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import Angle, BoundingBox, Detection, DownloadScope, DownloadSet, FaceLandmark5, InferencePool, ModelSet, Score, VisionFrame
-from facefusion.vision import resize_frame_resolution, unpack_resolution
+from facefusion.types import Angle, BoundingBox, Detection, DownloadScope, DownloadSet, FaceLandmark5, InferencePool, ModelSet, Score, VisionFrame
+from facefusion.vision import restrict_frame, unpack_resolution
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -55,11 +55,11 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				}
 			}
 		},
-		'yoloface':
+		'yolo_face':
 		{
 			'hashes':
 			{
-				'yoloface':
+				'yolo_face':
 				{
 					'url': resolve_download_url('models-3.0.0', 'yoloface_8n.hash'),
 					'path': resolve_relative_path('../.assets/models/yoloface_8n.hash')
@@ -67,49 +67,64 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			},
 			'sources':
 			{
-				'yoloface':
+				'yolo_face':
 				{
 					'url': resolve_download_url('models-3.0.0', 'yoloface_8n.onnx'),
 					'path': resolve_relative_path('../.assets/models/yoloface_8n.onnx')
 				}
 			}
+		},
+		'yunet':
+		{
+			'hashes':
+			{
+				'yunet':
+				{
+					'url': resolve_download_url('models-3.4.0', 'yunet_2023_mar.hash'),
+					'path': resolve_relative_path('../.assets/models/yunet_2023_mar.hash')
+				}
+			},
+			'sources':
+			{
+				'yunet':
+				{
+					'url': resolve_download_url('models-3.4.0', 'yunet_2023_mar.onnx'),
+					'path': resolve_relative_path('../.assets/models/yunet_2023_mar.onnx')
+				}
+			}
 		}
 	}
 
 
 def get_inference_pool() -> InferencePool:
-	_, model_sources = collect_model_downloads()
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('face_detector_model') ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('face_detector_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
-	model_hashes = {}
-	model_sources = {}
 	model_set = create_static_model_set('full')
+	model_hash_set = {}
+	model_source_set = {}
 
-	if state_manager.get_item('face_detector_model') in [ 'many', 'retinaface' ]:
-		model_hashes['retinaface'] = model_set.get('retinaface').get('hashes').get('retinaface')
-		model_sources['retinaface'] = model_set.get('retinaface').get('sources').get('retinaface')
+	for face_detector_model in [ 'retinaface', 'scrfd', 'yolo_face', 'yunet' ]:
+		if state_manager.get_item('face_detector_model') in [ 'many', face_detector_model ]:
+			model_hash_set[face_detector_model] = model_set.get(face_detector_model).get('hashes').get(face_detector_model)
+			model_source_set[face_detector_model] = model_set.get(face_detector_model).get('sources').get(face_detector_model)
 
-	if state_manager.get_item('face_detector_model') in [ 'many', 'scrfd' ]:
-		model_hashes['scrfd'] = model_set.get('scrfd').get('hashes').get('scrfd')
-		model_sources['scrfd'] = model_set.get('scrfd').get('sources').get('scrfd')
-
-	if state_manager.get_item('face_detector_model') in [ 'many', 'yoloface' ]:
-		model_hashes['yoloface'] = model_set.get('yoloface').get('hashes').get('yoloface')
-		model_sources['yoloface'] = model_set.get('yoloface').get('sources').get('yoloface')
-
-	return model_hashes, model_sources
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	model_hashes, model_sources = collect_model_downloads()
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def detect_faces(vision_frame : VisionFrame) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
@@ -129,8 +144,14 @@ def detect_faces(vision_frame : VisionFrame) -> Tuple[List[BoundingBox], List[Sc
 		all_face_scores.extend(face_scores)
 		all_face_landmarks_5.extend(face_landmarks_5)
 
-	if state_manager.get_item('face_detector_model') in [ 'many', 'yoloface' ]:
-		bounding_boxes, face_scores, face_landmarks_5 = detect_with_yoloface(vision_frame, state_manager.get_item('face_detector_size'))
+	if state_manager.get_item('face_detector_model') in [ 'many', 'yolo_face' ]:
+		bounding_boxes, face_scores, face_landmarks_5 = detect_with_yolo_face(vision_frame, state_manager.get_item('face_detector_size'))
+		all_bounding_boxes.extend(bounding_boxes)
+		all_face_scores.extend(face_scores)
+		all_face_landmarks_5.extend(face_landmarks_5)
+
+	if state_manager.get_item('face_detector_model') == 'yunet':
+		bounding_boxes, face_scores, face_landmarks_5 = detect_with_yunet(vision_frame, state_manager.get_item('face_detector_size'))
 		all_bounding_boxes.extend(bounding_boxes)
 		all_face_scores.extend(face_scores)
 		all_face_landmarks_5.extend(face_landmarks_5)
@@ -139,13 +160,13 @@ def detect_faces(vision_frame : VisionFrame) -> Tuple[List[BoundingBox], List[Sc
 	return all_bounding_boxes, all_face_scores, all_face_landmarks_5
 
 
-def detect_rotated_faces(vision_frame : VisionFrame, angle : Angle) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
-	rotated_matrix, rotated_size = create_rotated_matrix_and_size(angle, vision_frame.shape[:2][::-1])
-	rotated_vision_frame = cv2.warpAffine(vision_frame, rotated_matrix, rotated_size)
-	rotated_inverse_matrix = cv2.invertAffineTransform(rotated_matrix)
-	bounding_boxes, face_scores, face_landmarks_5 = detect_faces(rotated_vision_frame)
-	bounding_boxes = [ transform_bounding_box(bounding_box, rotated_inverse_matrix) for bounding_box in bounding_boxes ]
-	face_landmarks_5 = [ transform_points(face_landmark_5, rotated_inverse_matrix) for face_landmark_5 in face_landmarks_5 ]
+def detect_faces_by_angle(vision_frame : VisionFrame, face_angle : Angle) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
+	rotation_matrix, rotation_size = create_rotation_matrix_and_size(face_angle, vision_frame.shape[:2][::-1])
+	rotation_vision_frame = cv2.warpAffine(vision_frame, rotation_matrix, rotation_size)
+	rotation_inverse_matrix = cv2.invertAffineTransform(rotation_matrix)
+	bounding_boxes, face_scores, face_landmarks_5 = detect_faces(rotation_vision_frame)
+	bounding_boxes = [ transform_bounding_box(bounding_box, rotation_inverse_matrix) for bounding_box in bounding_boxes ]
+	face_landmarks_5 = [ transform_points(face_landmark_5, rotation_inverse_matrix) for face_landmark_5 in face_landmarks_5 ]
 	return bounding_boxes, face_scores, face_landmarks_5
 
 
@@ -156,37 +177,40 @@ def detect_with_retinaface(vision_frame : VisionFrame, face_detector_size : str)
 	feature_strides = [ 8, 16, 32 ]
 	feature_map_channel = 3
 	anchor_total = 2
+	face_detector_score = state_manager.get_item('face_detector_score')
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
-	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
 	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
 	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
 	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ -1, 1 ])
 	detection = forward_with_retinaface(detect_vision_frame)
 
 	for index, feature_stride in enumerate(feature_strides):
-		keep_indices = numpy.where(detection[index] >= state_manager.get_item('face_detector_score'))[0]
+		face_scores_raw = detection[index]
+		keep_indices = numpy.where(face_scores_raw >= face_detector_score)[0]
 
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
 			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
-			bounding_box_raw = detection[index + feature_map_channel] * feature_stride
-			face_landmark_5_raw = detection[index + feature_map_channel * 2] * feature_stride
+			bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride
+			face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride
 
-			for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]:
+			for bounding_box_raw in distance_to_bounding_box(anchors, bounding_boxes_raw)[keep_indices]:
 				bounding_boxes.append(numpy.array(
 				[
-					bounding_box[0] * ratio_width,
-					bounding_box[1] * ratio_height,
-					bounding_box[2] * ratio_width,
-					bounding_box[3] * ratio_height,
+					bounding_box_raw[0] * ratio_width,
+					bounding_box_raw[1] * ratio_height,
+					bounding_box_raw[2] * ratio_width,
+					bounding_box_raw[3] * ratio_height
 				]))
 
-			for score in detection[index][keep_indices]:
-				face_scores.append(score[0])
+			for face_score_raw in face_scores_raw[keep_indices]:
+				face_scores.append(face_score_raw[0])
 
-			for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]:
-				face_landmarks_5.append(face_landmark_5 * [ ratio_width, ratio_height ])
+			for face_landmark_raw_5 in distance_to_face_landmark_5(anchors, face_landmarks_5_raw)[keep_indices]:
+				face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ])
 
 	return bounding_boxes, face_scores, face_landmarks_5
 
@@ -198,73 +222,139 @@ def detect_with_scrfd(vision_frame : VisionFrame, face_detector_size : str) -> T
 	feature_strides = [ 8, 16, 32 ]
 	feature_map_channel = 3
 	anchor_total = 2
+	face_detector_score = state_manager.get_item('face_detector_score')
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
-	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
 	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
 	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
 	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ -1, 1 ])
 	detection = forward_with_scrfd(detect_vision_frame)
 
 	for index, feature_stride in enumerate(feature_strides):
-		keep_indices = numpy.where(detection[index] >= state_manager.get_item('face_detector_score'))[0]
+		face_scores_raw = detection[index]
+		keep_indices = numpy.where(face_scores_raw >= face_detector_score)[0]
 
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
 			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
-			bounding_box_raw = detection[index + feature_map_channel] * feature_stride
-			face_landmark_5_raw = detection[index + feature_map_channel * 2] * feature_stride
+			bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride
+			face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride
 
-			for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]:
+			for bounding_box_raw in distance_to_bounding_box(anchors, bounding_boxes_raw)[keep_indices]:
 				bounding_boxes.append(numpy.array(
 				[
-					bounding_box[0] * ratio_width,
-					bounding_box[1] * ratio_height,
-					bounding_box[2] * ratio_width,
-					bounding_box[3] * ratio_height,
+					bounding_box_raw[0] * ratio_width,
+					bounding_box_raw[1] * ratio_height,
+					bounding_box_raw[2] * ratio_width,
+					bounding_box_raw[3] * ratio_height
 				]))
 
-			for score in detection[index][keep_indices]:
-				face_scores.append(score[0])
+			for face_score_raw in face_scores_raw[keep_indices]:
+				face_scores.append(face_score_raw[0])
 
-			for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]:
-				face_landmarks_5.append(face_landmark_5 * [ ratio_width, ratio_height ])
+			for face_landmark_raw_5 in distance_to_face_landmark_5(anchors, face_landmarks_5_raw)[keep_indices]:
+				face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ])
 
 	return bounding_boxes, face_scores, face_landmarks_5
 
 
-def detect_with_yoloface(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
+def detect_with_yolo_face(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
 	bounding_boxes = []
 	face_scores = []
 	face_landmarks_5 = []
+	face_detector_score = state_manager.get_item('face_detector_score')
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
-	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
 	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
 	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
 	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
-	detection = forward_with_yoloface(detect_vision_frame)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ 0, 1 ])
+	detection = forward_with_yolo_face(detect_vision_frame)
 	detection = numpy.squeeze(detection).T
-	bounding_box_raw, score_raw, face_landmark_5_raw = numpy.split(detection, [ 4, 5 ], axis = 1)
-	keep_indices = numpy.where(score_raw > state_manager.get_item('face_detector_score'))[0]
+	bounding_boxes_raw, face_scores_raw, face_landmarks_5_raw = numpy.split(detection, [ 4, 5 ], axis = 1)
+	keep_indices = numpy.where(face_scores_raw > face_detector_score)[0]
 
 	if numpy.any(keep_indices):
-		bounding_box_raw, face_landmark_5_raw, score_raw = bounding_box_raw[keep_indices], face_landmark_5_raw[keep_indices], score_raw[keep_indices]
+		bounding_boxes_raw, face_scores_raw, face_landmarks_5_raw = bounding_boxes_raw[keep_indices], face_scores_raw[keep_indices], face_landmarks_5_raw[keep_indices]
 
-		for bounding_box in bounding_box_raw:
+		for bounding_box_raw in bounding_boxes_raw:
 			bounding_boxes.append(numpy.array(
 			[
-				(bounding_box[0] - bounding_box[2] / 2) * ratio_width,
-				(bounding_box[1] - bounding_box[3] / 2) * ratio_height,
-				(bounding_box[0] + bounding_box[2] / 2) * ratio_width,
-				(bounding_box[1] + bounding_box[3] / 2) * ratio_height,
+				(bounding_box_raw[0] - bounding_box_raw[2] / 2) * ratio_width,
+				(bounding_box_raw[1] - bounding_box_raw[3] / 2) * ratio_height,
+				(bounding_box_raw[0] + bounding_box_raw[2] / 2) * ratio_width,
+				(bounding_box_raw[1] + bounding_box_raw[3] / 2) * ratio_height
 			]))
 
-		face_scores = score_raw.ravel().tolist()
-		face_landmark_5_raw[:, 0::3] = (face_landmark_5_raw[:, 0::3]) * ratio_width
-		face_landmark_5_raw[:, 1::3] = (face_landmark_5_raw[:, 1::3]) * ratio_height
+		face_scores = face_scores_raw.ravel().tolist()
+		face_landmarks_5_raw[:, 0::3] = (face_landmarks_5_raw[:, 0::3]) * ratio_width
+		face_landmarks_5_raw[:, 1::3] = (face_landmarks_5_raw[:, 1::3]) * ratio_height
 
-		for face_landmark_5 in face_landmark_5_raw:
-			face_landmarks_5.append(numpy.array(face_landmark_5.reshape(-1, 3)[:, :2]))
+		for face_landmark_raw_5 in face_landmarks_5_raw:
+			face_landmarks_5.append(numpy.array(face_landmark_raw_5.reshape(-1, 3)[:, :2]))
+
+	return bounding_boxes, face_scores, face_landmarks_5
+
+
+def detect_with_yunet(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
+	bounding_boxes = []
+	face_scores = []
+	face_landmarks_5 = []
+	feature_strides = [ 8, 16, 32 ]
+	feature_map_channel = 3
+	anchor_total = 1
+	face_detector_score = state_manager.get_item('face_detector_score')
+	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
+	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
+	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
+	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ 0, 255 ])
+	detection = forward_with_yunet(detect_vision_frame)
+
+	for index, feature_stride in enumerate(feature_strides):
+		face_scores_raw = (detection[index] * detection[index + feature_map_channel]).reshape(-1)
+		keep_indices = numpy.where(face_scores_raw >= face_detector_score)[0]
+
+		if numpy.any(keep_indices):
+			stride_height = face_detector_height // feature_stride
+			stride_width = face_detector_width // feature_stride
+			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
+			bounding_boxes_center = detection[index + feature_map_channel * 2].squeeze(0)[:, :2] * feature_stride + anchors
+			bounding_boxes_size = numpy.exp(detection[index + feature_map_channel * 2].squeeze(0)[:, 2:4]) * feature_stride
+			face_landmarks_5_raw = detection[index + feature_map_channel * 3].squeeze(0)
+
+			bounding_boxes_raw = numpy.stack(
+			[
+				bounding_boxes_center[:, 0] - bounding_boxes_size[:, 0] / 2,
+				bounding_boxes_center[:, 1] - bounding_boxes_size[:, 1] / 2,
+				bounding_boxes_center[:, 0] + bounding_boxes_size[:, 0] / 2,
+				bounding_boxes_center[:, 1] + bounding_boxes_size[:, 1] / 2
+			], axis = -1)
+
+			for bounding_box_raw in bounding_boxes_raw[keep_indices]:
+				bounding_boxes.append(numpy.array(
+				[
+					bounding_box_raw[0] * ratio_width,
+					bounding_box_raw[1] * ratio_height,
+					bounding_box_raw[2] * ratio_width,
+					bounding_box_raw[3] * ratio_height
+				]))
+
+			face_scores.extend(face_scores_raw[keep_indices])
+			face_landmarks_5_raw = numpy.concatenate(
+			[
+				face_landmarks_5_raw[:, [0, 1]] * feature_stride + anchors,
+				face_landmarks_5_raw[:, [2, 3]] * feature_stride + anchors,
+				face_landmarks_5_raw[:, [4, 5]] * feature_stride + anchors,
+				face_landmarks_5_raw[:, [6, 7]] * feature_stride + anchors,
+				face_landmarks_5_raw[:, [8, 9]] * feature_stride + anchors
+			], axis = -1).reshape(-1, 5, 2)
+
+			for face_landmark_raw_5 in face_landmarks_5_raw[keep_indices]:
+				face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ])
 
 	return bounding_boxes, face_scores, face_landmarks_5
 
@@ -293,8 +383,20 @@ def forward_with_scrfd(detect_vision_frame : VisionFrame) -> Detection:
 	return detection
 
 
-def forward_with_yoloface(detect_vision_frame : VisionFrame) -> Detection:
-	face_detector = get_inference_pool().get('yoloface')
+def forward_with_yolo_face(detect_vision_frame : VisionFrame) -> Detection:
+	face_detector = get_inference_pool().get('yolo_face')
+
+	with thread_semaphore():
+		detection = face_detector.run(None,
+		{
+			'input': detect_vision_frame
+		})
+
+	return detection
+
+
+def forward_with_yunet(detect_vision_frame : VisionFrame) -> Detection:
+	face_detector = get_inference_pool().get('yunet')
 
 	with thread_semaphore():
 		detection = face_detector.run(None,
@@ -309,6 +411,13 @@ def prepare_detect_frame(temp_vision_frame : VisionFrame, face_detector_size : s
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
 	detect_vision_frame = numpy.zeros((face_detector_height, face_detector_width, 3))
 	detect_vision_frame[:temp_vision_frame.shape[0], :temp_vision_frame.shape[1], :] = temp_vision_frame
-	detect_vision_frame = (detect_vision_frame - 127.5) / 128.0
 	detect_vision_frame = numpy.expand_dims(detect_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
 	return detect_vision_frame
+
+
+def normalize_detect_frame(detect_vision_frame : VisionFrame, normalize_range : Sequence[int]) -> VisionFrame:
+	if normalize_range == [ -1, 1 ]:
+		return (detect_vision_frame - 127.5) / 128.0
+	if normalize_range == [ 0, 1 ]:
+		return detect_vision_frame / 255.0
+	return detect_vision_frame

facefusion/face_helper.py

@@ -5,9 +5,9 @@ import cv2
 import numpy
 from cv2.typing import Size
 
-from facefusion.typing import Anchors, Angle, BoundingBox, Distance, FaceDetectorModel, FaceLandmark5, FaceLandmark68, Mask, Matrix, Points, Scale, Score, Translation, VisionFrame, WarpTemplate, WarpTemplateSet
+from facefusion.types import Anchors, Angle, BoundingBox, Distance, FaceDetectorModel, FaceLandmark5, FaceLandmark68, Mask, Matrix, Points, Scale, Score, Translation, VisionFrame, WarpTemplate, WarpTemplateSet
 
-WARP_TEMPLATES : WarpTemplateSet =\
+WARP_TEMPLATE_SET : WarpTemplateSet =\
 {
 	'arcface_112_v1': numpy.array(
 	[
@@ -25,7 +25,7 @@ WARP_TEMPLATES : WarpTemplateSet =\
 		[ 0.37097589, 0.82469196 ],
 		[ 0.63151696, 0.82325089 ]
 	]),
-	'arcface_128_v2': numpy.array(
+	'arcface_128': numpy.array(
 	[
 		[ 0.36167656, 0.40387734 ],
 		[ 0.63696719, 0.40235469 ],
@@ -69,8 +69,8 @@ WARP_TEMPLATES : WarpTemplateSet =\
 
 
 def estimate_matrix_by_face_landmark_5(face_landmark_5 : FaceLandmark5, warp_template : WarpTemplate, crop_size : Size) -> Matrix:
-	normed_warp_template = WARP_TEMPLATES.get(warp_template) * crop_size
-	affine_matrix = cv2.estimateAffinePartial2D(face_landmark_5, normed_warp_template, method = cv2.RANSAC, ransacReprojThreshold = 100)[0]
+	warp_template_norm = WARP_TEMPLATE_SET.get(warp_template) * crop_size
+	affine_matrix = cv2.estimateAffinePartial2D(face_landmark_5, warp_template_norm, method = cv2.RANSAC, ransacReprojThreshold = 100)[0]
 	return affine_matrix
 
 
@@ -99,38 +99,58 @@ def warp_face_by_translation(temp_vision_frame : VisionFrame, translation : Tran
 
 
 def paste_back(temp_vision_frame : VisionFrame, crop_vision_frame : VisionFrame, crop_mask : Mask, affine_matrix : Matrix) -> VisionFrame:
+	paste_bounding_box, paste_matrix = calculate_paste_area(temp_vision_frame, crop_vision_frame, affine_matrix)
+	x1, y1, x2, y2 = paste_bounding_box
+	paste_width = x2 - x1
+	paste_height = y2 - y1
+	inverse_mask = cv2.warpAffine(crop_mask, paste_matrix, (paste_width, paste_height)).clip(0, 1)
+	inverse_mask = numpy.expand_dims(inverse_mask, axis = -1)
+	inverse_vision_frame = cv2.warpAffine(crop_vision_frame, paste_matrix, (paste_width, paste_height), borderMode = cv2.BORDER_REPLICATE)
+	temp_vision_frame = temp_vision_frame.copy()
+	paste_vision_frame = temp_vision_frame[y1:y2, x1:x2]
+	paste_vision_frame = paste_vision_frame * (1 - inverse_mask) + inverse_vision_frame * inverse_mask
+	temp_vision_frame[y1:y2, x1:x2] = paste_vision_frame.astype(temp_vision_frame.dtype)
+	return temp_vision_frame
+
+
+def calculate_paste_area(temp_vision_frame : VisionFrame, crop_vision_frame : VisionFrame, affine_matrix : Matrix) -> Tuple[BoundingBox, Matrix]:
+	temp_height, temp_width = temp_vision_frame.shape[:2]
+	crop_height, crop_width = crop_vision_frame.shape[:2]
 	inverse_matrix = cv2.invertAffineTransform(affine_matrix)
-	temp_size = temp_vision_frame.shape[:2][::-1]
-	inverse_mask = cv2.warpAffine(crop_mask, inverse_matrix, temp_size).clip(0, 1)
-	inverse_vision_frame = cv2.warpAffine(crop_vision_frame, inverse_matrix, temp_size, borderMode = cv2.BORDER_REPLICATE)
-	paste_vision_frame = temp_vision_frame.copy()
-	paste_vision_frame[:, :, 0] = inverse_mask * inverse_vision_frame[:, :, 0] + (1 - inverse_mask) * temp_vision_frame[:, :, 0]
-	paste_vision_frame[:, :, 1] = inverse_mask * inverse_vision_frame[:, :, 1] + (1 - inverse_mask) * temp_vision_frame[:, :, 1]
-	paste_vision_frame[:, :, 2] = inverse_mask * inverse_vision_frame[:, :, 2] + (1 - inverse_mask) * temp_vision_frame[:, :, 2]
-	return paste_vision_frame
+	crop_points = numpy.array([ [ 0, 0 ], [ crop_width, 0 ], [ crop_width, crop_height ], [ 0, crop_height ] ])
+	paste_region_points = transform_points(crop_points, inverse_matrix)
+	paste_region_point_min = numpy.floor(paste_region_points.min(axis = 0)).astype(int)
+	paste_region_point_max = numpy.ceil(paste_region_points.max(axis = 0)).astype(int)
+	x1, y1 = numpy.clip(paste_region_point_min, 0, [ temp_width, temp_height ])
+	x2, y2 = numpy.clip(paste_region_point_max, 0, [ temp_width, temp_height ])
+	paste_bounding_box = numpy.array([ x1, y1, x2, y2 ])
+	paste_matrix = inverse_matrix.copy()
+	paste_matrix[0, 2] -= x1
+	paste_matrix[1, 2] -= y1
+	return paste_bounding_box, paste_matrix
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_anchors(feature_stride : int, anchor_total : int, stride_height : int, stride_width : int) -> Anchors:
-	y, x = numpy.mgrid[:stride_height, :stride_width][::-1]
+	x, y = numpy.mgrid[:stride_width, :stride_height]
 	anchors = numpy.stack((y, x), axis = -1)
 	anchors = (anchors * feature_stride).reshape((-1, 2))
 	anchors = numpy.stack([ anchors ] * anchor_total, axis = 1).reshape((-1, 2))
 	return anchors
 
 
-def create_rotated_matrix_and_size(angle : Angle, size : Size) -> Tuple[Matrix, Size]:
-	rotated_matrix = cv2.getRotationMatrix2D((size[0] / 2, size[1] / 2), angle, 1)
-	rotated_size = numpy.dot(numpy.abs(rotated_matrix[:, :2]), size)
-	rotated_matrix[:, -1] += (rotated_size - size) * 0.5 #type:ignore[misc]
-	rotated_size = int(rotated_size[0]), int(rotated_size[1])
-	return rotated_matrix, rotated_size
+def create_rotation_matrix_and_size(angle : Angle, size : Size) -> Tuple[Matrix, Size]:
+	rotation_matrix = cv2.getRotationMatrix2D((size[0] / 2, size[1] / 2), angle, 1)
+	rotation_size = numpy.dot(numpy.abs(rotation_matrix[:, :2]), size)
+	rotation_matrix[:, -1] += (rotation_size - size) * 0.5 #type:ignore[misc]
+	rotation_size = int(rotation_size[0]), int(rotation_size[1])
+	return rotation_matrix, rotation_size
 
 
 def create_bounding_box(face_landmark_68 : FaceLandmark68) -> BoundingBox:
-	min_x, min_y = numpy.min(face_landmark_68, axis = 0)
-	max_x, max_y = numpy.max(face_landmark_68, axis = 0)
-	bounding_box = normalize_bounding_box(numpy.array([ min_x, min_y, max_x, max_y ]))
+	x1, y1 = numpy.min(face_landmark_68, axis = 0)
+	x2, y2 = numpy.max(face_landmark_68, axis = 0)
+	bounding_box = normalize_bounding_box(numpy.array([ x1, y1, x2, y2 ]))
 	return bounding_box
 
 
@@ -208,9 +228,9 @@ def estimate_face_angle(face_landmark_68 : FaceLandmark68) -> Angle:
 	return face_angle
 
 
-def apply_nms(bounding_boxes : List[BoundingBox], face_scores : List[Score], score_threshold : float, nms_threshold : float) -> Sequence[int]:
-	normed_bounding_boxes = [ (x1, y1, x2 - x1, y2 - y1) for (x1, y1, x2, y2) in bounding_boxes ]
-	keep_indices = cv2.dnn.NMSBoxes(normed_bounding_boxes, face_scores, score_threshold = score_threshold, nms_threshold = nms_threshold)
+def apply_nms(bounding_boxes : List[BoundingBox], scores : List[Score], score_threshold : float, nms_threshold : float) -> Sequence[int]:
+	bounding_boxes_norm = [ (x1, y1, x2 - x1, y2 - y1) for (x1, y1, x2, y2) in bounding_boxes ]
+	keep_indices = cv2.dnn.NMSBoxes(bounding_boxes_norm, scores, score_threshold = score_threshold, nms_threshold = nms_threshold)
 	return keep_indices
 
 
@@ -226,9 +246,11 @@ def get_nms_threshold(face_detector_model : FaceDetectorModel, face_detector_ang
 	return 0.4
 
 
-def merge_matrix(matrices : List[Matrix]) -> Matrix:
-	merged_matrix = numpy.vstack([ matrices[0], [ 0, 0, 1 ] ])
-	for matrix in matrices[1:]:
-		matrix = numpy.vstack([ matrix, [ 0, 0, 1 ] ])
-		merged_matrix = numpy.dot(merged_matrix, matrix)
-	return merged_matrix[:2, :]
+def merge_matrix(temp_matrices : List[Matrix]) -> Matrix:
+	matrix = numpy.vstack([temp_matrices[0], [0, 0, 1]])
+
+	for temp_matrix in temp_matrices[1:]:
+		temp_matrix = numpy.vstack([ temp_matrix, [ 0, 0, 1 ] ])
+		matrix = numpy.dot(temp_matrix, matrix)
+
+	return matrix[:2, :]

facefusion/face_landmarker.py

@@ -6,13 +6,13 @@ import numpy
 
 from facefusion import inference_manager, state_manager
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_helper import create_rotated_matrix_and_size, estimate_matrix_by_face_landmark_5, transform_points, warp_face_by_translation
+from facefusion.face_helper import create_rotation_matrix_and_size, estimate_matrix_by_face_landmark_5, transform_points, warp_face_by_translation
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import Angle, BoundingBox, DownloadScope, DownloadSet, FaceLandmark5, FaceLandmark68, InferencePool, ModelSet, Prediction, Score, VisionFrame
+from facefusion.types import Angle, BoundingBox, DownloadScope, DownloadSet, FaceLandmark5, FaceLandmark68, InferencePool, ModelSet, Prediction, Score, VisionFrame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -79,43 +79,43 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	_, model_sources = collect_model_downloads()
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('face_landmarker_model'), 'fan_68_5' ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('face_landmarker_model'), 'fan_68_5' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
 	model_set = create_static_model_set('full')
-	model_hashes =\
+	model_hash_set =\
 	{
 		'fan_68_5': model_set.get('fan_68_5').get('hashes').get('fan_68_5')
 	}
-	model_sources =\
+	model_source_set =\
 	{
 		'fan_68_5': model_set.get('fan_68_5').get('sources').get('fan_68_5')
 	}
 
-	if state_manager.get_item('face_landmarker_model') in [ 'many', '2dfan4' ]:
-		model_hashes['2dfan4'] = model_set.get('2dfan4').get('hashes').get('2dfan4')
-		model_sources['2dfan4'] = model_set.get('2dfan4').get('sources').get('2dfan4')
+	for face_landmarker_model in [ '2dfan4', 'peppa_wutz' ]:
+		if state_manager.get_item('face_landmarker_model') in [ 'many', face_landmarker_model ]:
+			model_hash_set[face_landmarker_model] = model_set.get(face_landmarker_model).get('hashes').get(face_landmarker_model)
+			model_source_set[face_landmarker_model] = model_set.get(face_landmarker_model).get('sources').get(face_landmarker_model)
 
-	if state_manager.get_item('face_landmarker_model') in [ 'many', 'peppa_wutz' ]:
-		model_hashes['peppa_wutz'] = model_set.get('peppa_wutz').get('hashes').get('peppa_wutz')
-		model_sources['peppa_wutz'] = model_set.get('peppa_wutz').get('sources').get('peppa_wutz')
-
-	return model_hashes, model_sources
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	model_hashes, model_sources = collect_model_downloads()
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
-def detect_face_landmarks(vision_frame : VisionFrame, bounding_box : BoundingBox, face_angle : Angle) -> Tuple[FaceLandmark68, Score]:
+def detect_face_landmark(vision_frame : VisionFrame, bounding_box : BoundingBox, face_angle : Angle) -> Tuple[FaceLandmark68, Score]:
 	face_landmark_2dfan4 = None
 	face_landmark_peppa_wutz = None
 	face_landmark_score_2dfan4 = 0.0
@@ -136,14 +136,14 @@ def detect_with_2dfan4(temp_vision_frame: VisionFrame, bounding_box: BoundingBox
 	model_size = create_static_model_set('full').get('2dfan4').get('size')
 	scale = 195 / numpy.subtract(bounding_box[2:], bounding_box[:2]).max().clip(1, None)
 	translation = (model_size[0] - numpy.add(bounding_box[2:], bounding_box[:2]) * scale) * 0.5
-	rotated_matrix, rotated_size = create_rotated_matrix_and_size(face_angle, model_size)
+	rotation_matrix, rotation_size = create_rotation_matrix_and_size(face_angle, model_size)
 	crop_vision_frame, affine_matrix = warp_face_by_translation(temp_vision_frame, translation, scale, model_size)
-	crop_vision_frame = cv2.warpAffine(crop_vision_frame, rotated_matrix, rotated_size)
+	crop_vision_frame = cv2.warpAffine(crop_vision_frame, rotation_matrix, rotation_size)
 	crop_vision_frame = conditional_optimize_contrast(crop_vision_frame)
 	crop_vision_frame = crop_vision_frame.transpose(2, 0, 1).astype(numpy.float32) / 255.0
 	face_landmark_68, face_heatmap = forward_with_2dfan4(crop_vision_frame)
 	face_landmark_68 = face_landmark_68[:, :, :2][0] / 64 * 256
-	face_landmark_68 = transform_points(face_landmark_68, cv2.invertAffineTransform(rotated_matrix))
+	face_landmark_68 = transform_points(face_landmark_68, cv2.invertAffineTransform(rotation_matrix))
 	face_landmark_68 = transform_points(face_landmark_68, cv2.invertAffineTransform(affine_matrix))
 	face_landmark_score_68 = numpy.amax(face_heatmap, axis = (2, 3))
 	face_landmark_score_68 = numpy.mean(face_landmark_score_68)
@@ -155,15 +155,15 @@ def detect_with_peppa_wutz(temp_vision_frame : VisionFrame, bounding_box : Bound
 	model_size = create_static_model_set('full').get('peppa_wutz').get('size')
 	scale = 195 / numpy.subtract(bounding_box[2:], bounding_box[:2]).max().clip(1, None)
 	translation = (model_size[0] - numpy.add(bounding_box[2:], bounding_box[:2]) * scale) * 0.5
-	rotated_matrix, rotated_size = create_rotated_matrix_and_size(face_angle, model_size)
+	rotation_matrix, rotation_size = create_rotation_matrix_and_size(face_angle, model_size)
 	crop_vision_frame, affine_matrix = warp_face_by_translation(temp_vision_frame, translation, scale, model_size)
-	crop_vision_frame = cv2.warpAffine(crop_vision_frame, rotated_matrix, rotated_size)
+	crop_vision_frame = cv2.warpAffine(crop_vision_frame, rotation_matrix, rotation_size)
 	crop_vision_frame = conditional_optimize_contrast(crop_vision_frame)
 	crop_vision_frame = crop_vision_frame.transpose(2, 0, 1).astype(numpy.float32) / 255.0
 	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
 	prediction = forward_with_peppa_wutz(crop_vision_frame)
 	face_landmark_68 = prediction.reshape(-1, 3)[:, :2] / 64 * model_size[0]
-	face_landmark_68 = transform_points(face_landmark_68, cv2.invertAffineTransform(rotated_matrix))
+	face_landmark_68 = transform_points(face_landmark_68, cv2.invertAffineTransform(rotation_matrix))
 	face_landmark_68 = transform_points(face_landmark_68, cv2.invertAffineTransform(affine_matrix))
 	face_landmark_score_68 = prediction.reshape(-1, 3)[:, 2].mean()
 	face_landmark_score_68 = numpy.interp(face_landmark_score_68, [ 0, 0.95 ], [ 0, 1 ])

facefusion/face_masker.py

@@ -3,17 +3,16 @@ from typing import List, Tuple
 
 import cv2
 import numpy
-from cv2.typing import Size
 
 import facefusion.choices
 from facefusion import inference_manager, state_manager
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import DownloadScope, DownloadSet, FaceLandmark68, FaceMaskRegion, InferencePool, Mask, ModelSet, Padding, VisionFrame
+from facefusion.types import DownloadScope, DownloadSet, FaceLandmark68, FaceMaskArea, FaceMaskRegion, InferencePool, Mask, ModelSet, Padding, VisionFrame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -57,6 +56,26 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			},
 			'size': (256, 256)
 		},
+		'xseg_3':
+		{
+			'hashes':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.2.0', 'xseg_3.hash'),
+					'path': resolve_relative_path('../.assets/models/xseg_3.hash')
+				}
+			},
+			'sources':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.2.0', 'xseg_3.onnx'),
+					'path': resolve_relative_path('../.assets/models/xseg_3.onnx')
+				}
+			},
+			'size': (256, 256)
+		},
 		'bisenet_resnet_18':
 		{
 			'hashes':
@@ -101,46 +120,43 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	_, model_sources = collect_model_downloads()
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('face_occluder_model'), state_manager.get_item('face_parser_model') ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('face_occluder_model'), state_manager.get_item('face_parser_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
-	model_hashes = {}
-	model_sources = {}
 	model_set = create_static_model_set('full')
+	model_hash_set = {}
+	model_source_set = {}
 
-	if state_manager.get_item('face_occluder_model') == 'xseg_1':
-		model_hashes['xseg_1'] = model_set.get('xseg_1').get('hashes').get('face_occluder')
-		model_sources['xseg_1'] = model_set.get('xseg_1').get('sources').get('face_occluder')
+	for face_occluder_model in [ 'xseg_1', 'xseg_2', 'xseg_3' ]:
+		if state_manager.get_item('face_occluder_model') in [ 'many', face_occluder_model ]:
+			model_hash_set[face_occluder_model] = model_set.get(face_occluder_model).get('hashes').get('face_occluder')
+			model_source_set[face_occluder_model] = model_set.get(face_occluder_model).get('sources').get('face_occluder')
 
-	if state_manager.get_item('face_occluder_model') == 'xseg_2':
-		model_hashes['xseg_2'] = model_set.get('xseg_2').get('hashes').get('face_occluder')
-		model_sources['xseg_2'] = model_set.get('xseg_2').get('sources').get('face_occluder')
+	for face_parser_model in [ 'bisenet_resnet_18', 'bisenet_resnet_34' ]:
+		if state_manager.get_item('face_parser_model') == face_parser_model:
+			model_hash_set[face_parser_model] = model_set.get(face_parser_model).get('hashes').get('face_parser')
+			model_source_set[face_parser_model] = model_set.get(face_parser_model).get('sources').get('face_parser')
 
-	if state_manager.get_item('face_parser_model') == 'bisenet_resnet_18':
-		model_hashes['bisenet_resnet_18'] = model_set.get('bisenet_resnet_18').get('hashes').get('face_parser')
-		model_sources['bisenet_resnet_18'] = model_set.get('bisenet_resnet_18').get('sources').get('face_parser')
-
-	if state_manager.get_item('face_parser_model') == 'bisenet_resnet_34':
-		model_hashes['bisenet_resnet_34'] = model_set.get('bisenet_resnet_34').get('hashes').get('face_parser')
-		model_sources['bisenet_resnet_34'] = model_set.get('bisenet_resnet_34').get('sources').get('face_parser')
-
-	return model_hashes, model_sources
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	model_hashes, model_sources = collect_model_downloads()
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
-@lru_cache(maxsize = None)
-def create_static_box_mask(crop_size : Size, face_mask_blur : float, face_mask_padding : Padding) -> Mask:
+def create_box_mask(crop_vision_frame : VisionFrame, face_mask_blur : float, face_mask_padding : Padding) -> Mask:
+	crop_size = crop_vision_frame.shape[:2][::-1]
 	blur_amount = int(crop_size[0] * 0.5 * face_mask_blur)
 	blur_area = max(blur_amount // 2, 1)
 	box_mask : Mask = numpy.ones(crop_size).astype(numpy.float32)
@@ -148,29 +164,55 @@ def create_static_box_mask(crop_size : Size, face_mask_blur : float, face_mask_p
 	box_mask[-max(blur_area, int(crop_size[1] * face_mask_padding[2] / 100)):, :] = 0
 	box_mask[:, :max(blur_area, int(crop_size[0] * face_mask_padding[3] / 100))] = 0
 	box_mask[:, -max(blur_area, int(crop_size[0] * face_mask_padding[1] / 100)):] = 0
+
 	if blur_amount > 0:
 		box_mask = cv2.GaussianBlur(box_mask, (0, 0), blur_amount * 0.25)
 	return box_mask
 
 
 def create_occlusion_mask(crop_vision_frame : VisionFrame) -> Mask:
-	face_occluder_model = state_manager.get_item('face_occluder_model')
-	model_size = create_static_model_set('full').get(face_occluder_model).get('size')
-	prepare_vision_frame = cv2.resize(crop_vision_frame, model_size)
-	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0).astype(numpy.float32) / 255
-	prepare_vision_frame = prepare_vision_frame.transpose(0, 1, 2, 3)
-	occlusion_mask = forward_occlude_face(prepare_vision_frame)
-	occlusion_mask = occlusion_mask.transpose(0, 1, 2).clip(0, 1).astype(numpy.float32)
-	occlusion_mask = cv2.resize(occlusion_mask, crop_vision_frame.shape[:2][::-1])
+	temp_masks = []
+
+	if state_manager.get_item('face_occluder_model') == 'many':
+		model_names = [ 'xseg_1', 'xseg_2', 'xseg_3' ]
+	else:
+		model_names = [ state_manager.get_item('face_occluder_model') ]
+
+	for model_name in model_names:
+		model_size = create_static_model_set('full').get(model_name).get('size')
+		prepare_vision_frame = cv2.resize(crop_vision_frame, model_size)
+		prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0).astype(numpy.float32) / 255.0
+		prepare_vision_frame = prepare_vision_frame.transpose(0, 1, 2, 3)
+		temp_mask = forward_occlude_face(prepare_vision_frame, model_name)
+		temp_mask = temp_mask.transpose(0, 1, 2).clip(0, 1).astype(numpy.float32)
+		temp_mask = cv2.resize(temp_mask, crop_vision_frame.shape[:2][::-1])
+		temp_masks.append(temp_mask)
+
+	occlusion_mask = numpy.minimum.reduce(temp_masks)
 	occlusion_mask = (cv2.GaussianBlur(occlusion_mask.clip(0, 1), (0, 0), 5).clip(0.5, 1) - 0.5) * 2
 	return occlusion_mask
 
 
+def create_area_mask(crop_vision_frame : VisionFrame, face_landmark_68 : FaceLandmark68, face_mask_areas : List[FaceMaskArea]) -> Mask:
+	crop_size = crop_vision_frame.shape[:2][::-1]
+	landmark_points = []
+
+	for face_mask_area in face_mask_areas:
+		if face_mask_area in facefusion.choices.face_mask_area_set:
+			landmark_points.extend(facefusion.choices.face_mask_area_set.get(face_mask_area))
+
+	convex_hull = cv2.convexHull(face_landmark_68[landmark_points].astype(numpy.int32))
+	area_mask = numpy.zeros(crop_size).astype(numpy.float32)
+	cv2.fillConvexPoly(area_mask, convex_hull, 1.0) # type: ignore[call-overload]
+	area_mask = (cv2.GaussianBlur(area_mask.clip(0, 1), (0, 0), 5).clip(0.5, 1) - 0.5) * 2
+	return area_mask
+
+
 def create_region_mask(crop_vision_frame : VisionFrame, face_mask_regions : List[FaceMaskRegion]) -> Mask:
-	face_parser_model = state_manager.get_item('face_parser_model')
-	model_size = create_static_model_set('full').get(face_parser_model).get('size')
+	model_name = state_manager.get_item('face_parser_model')
+	model_size = create_static_model_set('full').get(model_name).get('size')
 	prepare_vision_frame = cv2.resize(crop_vision_frame, model_size)
-	prepare_vision_frame = prepare_vision_frame[:, :, ::-1].astype(numpy.float32) / 255
+	prepare_vision_frame = prepare_vision_frame[:, :, ::-1].astype(numpy.float32) / 255.0
 	prepare_vision_frame = numpy.subtract(prepare_vision_frame, numpy.array([ 0.485, 0.456, 0.406 ]).astype(numpy.float32))
 	prepare_vision_frame = numpy.divide(prepare_vision_frame, numpy.array([ 0.229, 0.224, 0.225 ]).astype(numpy.float32))
 	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0)
@@ -182,18 +224,8 @@ def create_region_mask(crop_vision_frame : VisionFrame, face_mask_regions : List
 	return region_mask
 
 
-def create_mouth_mask(face_landmark_68 : FaceLandmark68) -> Mask:
-	convex_hull = cv2.convexHull(face_landmark_68[numpy.r_[3:14, 31:36]].astype(numpy.int32))
-	mouth_mask : Mask = numpy.zeros((512, 512)).astype(numpy.float32)
-	mouth_mask = cv2.fillConvexPoly(mouth_mask, convex_hull, 1.0) #type:ignore[call-overload]
-	mouth_mask = cv2.erode(mouth_mask.clip(0, 1), numpy.ones((21, 3)))
-	mouth_mask = cv2.GaussianBlur(mouth_mask, (0, 0), sigmaX = 1, sigmaY = 15)
-	return mouth_mask
-
-
-def forward_occlude_face(prepare_vision_frame : VisionFrame) -> Mask:
-	face_occluder_model = state_manager.get_item('face_occluder_model')
-	face_occluder = get_inference_pool().get(face_occluder_model)
+def forward_occlude_face(prepare_vision_frame : VisionFrame, model_name : str) -> Mask:
+	face_occluder = get_inference_pool().get(model_name)
 
 	with conditional_thread_semaphore():
 		occlusion_mask : Mask = face_occluder.run(None,
@@ -205,8 +237,8 @@ def forward_occlude_face(prepare_vision_frame : VisionFrame) -> Mask:
 
 
 def forward_parse_face(prepare_vision_frame : VisionFrame) -> Mask:
-	face_parser_model = state_manager.get_item('face_parser_model')
-	face_parser = get_inference_pool().get(face_parser_model)
+	model_name = state_manager.get_item('face_parser_model')
+	face_parser = get_inference_pool().get(model_name)
 
 	with conditional_thread_semaphore():
 		region_mask : Mask = face_parser.run(None,

facefusion/face_recognizer.py

@@ -8,10 +8,10 @@ from facefusion.download import conditional_download_hashes, conditional_downloa
 from facefusion.face_helper import warp_face_by_face_landmark_5
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import DownloadScope, Embedding, FaceLandmark5, InferencePool, ModelOptions, ModelSet, VisionFrame
+from facefusion.types import DownloadScope, Embedding, FaceLandmark5, InferencePool, ModelOptions, ModelSet, VisionFrame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -40,12 +40,15 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ 'arcface' ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ 'arcface' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
@@ -53,32 +56,32 @@ def get_model_options() -> ModelOptions:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
-def calc_embedding(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5) -> Tuple[Embedding, Embedding]:
+def calculate_face_embedding(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5) -> Tuple[Embedding, Embedding]:
 	model_template = get_model_options().get('template')
 	model_size = get_model_options().get('size')
 	crop_vision_frame, matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_template, model_size)
 	crop_vision_frame = crop_vision_frame / 127.5 - 1
 	crop_vision_frame = crop_vision_frame[:, :, ::-1].transpose(2, 0, 1).astype(numpy.float32)
 	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
-	embedding = forward(crop_vision_frame)
-	embedding = embedding.ravel()
-	normed_embedding = embedding / numpy.linalg.norm(embedding)
-	return embedding, normed_embedding
+	face_embedding = forward(crop_vision_frame)
+	face_embedding = face_embedding.ravel()
+	face_embedding_norm = face_embedding / numpy.linalg.norm(face_embedding)
+	return face_embedding, face_embedding_norm
 
 
 def forward(crop_vision_frame : VisionFrame) -> Embedding:
 	face_recognizer = get_inference_pool().get('face_recognizer')
 
 	with conditional_thread_semaphore():
-		embedding = face_recognizer.run(None,
+		face_embedding = face_recognizer.run(None,
 		{
 			'input': crop_vision_frame
 		})[0]
 
-	return embedding
+	return face_embedding

facefusion/face_selector.py

@@ -3,30 +3,53 @@ from typing import List
 import numpy
 
 from facefusion import state_manager
-from facefusion.typing import Face, FaceSelectorOrder, FaceSet, Gender, Race
+from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.types import Face, FaceSelectorOrder, Gender, Race, Score, VisionFrame
 
 
-def find_similar_faces(faces : List[Face], reference_faces : FaceSet, face_distance : float) -> List[Face]:
-	similar_faces : List[Face] = []
+def select_faces(reference_vision_frame : VisionFrame, target_vision_frame : VisionFrame) -> List[Face]:
+	target_faces = get_many_faces([ target_vision_frame ])
 
-	if faces and reference_faces:
-		for reference_set in reference_faces:
-			if not similar_faces:
-				for reference_face in reference_faces[reference_set]:
-					for face in faces:
-						if compare_faces(face, reference_face, face_distance):
-							similar_faces.append(face)
-	return similar_faces
+	if state_manager.get_item('face_selector_mode') == 'many':
+		return sort_and_filter_faces(target_faces)
+
+	if state_manager.get_item('face_selector_mode') == 'one':
+		target_face = get_one_face(sort_and_filter_faces(target_faces))
+		if target_face:
+			return [ target_face ]
+
+	if state_manager.get_item('face_selector_mode') == 'reference':
+		reference_faces = get_many_faces([ reference_vision_frame ])
+		reference_faces = sort_and_filter_faces(reference_faces)
+		reference_face = get_one_face(reference_faces, state_manager.get_item('reference_face_position'))
+		if reference_face:
+			match_faces = find_match_faces([ reference_face ], target_faces, state_manager.get_item('reference_face_distance'))
+			return match_faces
+
+	return []
+
+
+def find_match_faces(reference_faces : List[Face], target_faces : List[Face], face_distance : float) -> List[Face]:
+	match_faces : List[Face] = []
+
+	for reference_face in reference_faces:
+		if reference_face:
+			for index, target_face in enumerate(target_faces):
+				if compare_faces(target_face, reference_face, face_distance):
+					match_faces.append(target_faces[index])
+
+	return match_faces
 
 
 def compare_faces(face : Face, reference_face : Face, face_distance : float) -> bool:
-	current_face_distance = calc_face_distance(face, reference_face)
+	current_face_distance = calculate_face_distance(face, reference_face)
+	current_face_distance = float(numpy.interp(current_face_distance, [ 0, 2 ], [ 0, 1 ]))
 	return current_face_distance < face_distance
 
 
-def calc_face_distance(face : Face, reference_face : Face) -> float:
-	if hasattr(face, 'normed_embedding') and hasattr(reference_face, 'normed_embedding'):
-		return 1 - numpy.dot(face.normed_embedding, reference_face.normed_embedding)
+def calculate_face_distance(face : Face, reference_face : Face) -> float:
+	if hasattr(face, 'embedding_norm') and hasattr(reference_face, 'embedding_norm'):
+		return 1 - numpy.dot(face.embedding_norm, reference_face.embedding_norm)
 	return 0
 
 
@@ -45,24 +68,40 @@ def sort_and_filter_faces(faces : List[Face]) -> List[Face]:
 
 def sort_faces_by_order(faces : List[Face], order : FaceSelectorOrder) -> List[Face]:
 	if order == 'left-right':
-		return sorted(faces, key = lambda face: face.bounding_box[0])
+		return sorted(faces, key = get_bounding_box_left)
 	if order == 'right-left':
-		return sorted(faces, key = lambda face: face.bounding_box[0], reverse = True)
+		return sorted(faces, key = get_bounding_box_left, reverse = True)
 	if order == 'top-bottom':
-		return sorted(faces, key = lambda face: face.bounding_box[1])
+		return sorted(faces, key = get_bounding_box_top)
 	if order == 'bottom-top':
-		return sorted(faces, key = lambda face: face.bounding_box[1], reverse = True)
+		return sorted(faces, key = get_bounding_box_top, reverse = True)
 	if order == 'small-large':
-		return sorted(faces, key = lambda face: (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1]))
+		return sorted(faces, key = get_bounding_box_area)
 	if order == 'large-small':
-		return sorted(faces, key = lambda face: (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1]), reverse = True)
+		return sorted(faces, key = get_bounding_box_area, reverse = True)
 	if order == 'best-worst':
-		return sorted(faces, key = lambda face: face.score_set.get('detector'), reverse = True)
+		return sorted(faces, key = get_face_detector_score, reverse = True)
 	if order == 'worst-best':
-		return sorted(faces, key = lambda face: face.score_set.get('detector'))
+		return sorted(faces, key = get_face_detector_score)
 	return faces
 
 
+def get_bounding_box_left(face : Face) -> float:
+	return face.bounding_box[0]
+
+
+def get_bounding_box_top(face : Face) -> float:
+	return face.bounding_box[1]
+
+
+def get_bounding_box_area(face : Face) -> float:
+	return (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1])
+
+
+def get_face_detector_score(face : Face) -> Score:
+	return face.score_set.get('detector')
+
+
 def filter_faces_by_gender(faces : List[Face], gender : Gender) -> List[Face]:
 	filter_faces = []
 

facefusion/face_store.py

@@ -1,14 +1,11 @@
-import hashlib
 from typing import List, Optional
 
-import numpy
-
-from facefusion.typing import Face, FaceSet, FaceStore, VisionFrame
+from facefusion.hash_helper import create_hash
+from facefusion.types import Face, FaceStore, VisionFrame
 
 FACE_STORE : FaceStore =\
 {
-	'static_faces': {},
-	'reference_faces': {}
+	'static_faces': {}
 }
 
 
@@ -17,37 +14,15 @@ def get_face_store() -> FaceStore:
 
 
 def get_static_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
-	frame_hash = create_frame_hash(vision_frame)
-	if frame_hash in FACE_STORE['static_faces']:
-		return FACE_STORE['static_faces'][frame_hash]
-	return None
+	vision_hash = create_hash(vision_frame.tobytes())
+	return FACE_STORE.get('static_faces').get(vision_hash)
 
 
 def set_static_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
-	frame_hash = create_frame_hash(vision_frame)
-	if frame_hash:
-		FACE_STORE['static_faces'][frame_hash] = faces
+	vision_hash = create_hash(vision_frame.tobytes())
+	if vision_hash:
+		FACE_STORE['static_faces'][vision_hash] = faces
 
 
 def clear_static_faces() -> None:
-	FACE_STORE['static_faces'] = {}
-
-
-def create_frame_hash(vision_frame : VisionFrame) -> Optional[str]:
-	return hashlib.sha1(vision_frame.tobytes()).hexdigest() if numpy.any(vision_frame) else None
-
-
-def get_reference_faces() -> Optional[FaceSet]:
-	if FACE_STORE['reference_faces']:
-		return FACE_STORE['reference_faces']
-	return None
-
-
-def append_reference_face(name : str, face : Face) -> None:
-	if name not in FACE_STORE['reference_faces']:
-		FACE_STORE['reference_faces'][name] = []
-	FACE_STORE['reference_faces'][name].append(face)
-
-
-def clear_reference_faces() -> None:
-	FACE_STORE['reference_faces'] = {}
+	FACE_STORE['static_faces'].clear()

facefusion/ffmpeg.py

@@ -1,29 +1,32 @@
 import os
-import shutil
 import subprocess
 import tempfile
-from typing import List, Optional
+from functools import partial
+from typing import List, Optional, cast
 
-import filetype
 from tqdm import tqdm
 
-from facefusion import logger, process_manager, state_manager, wording
-from facefusion.filesystem import remove_file
-from facefusion.temp_helper import get_temp_file_path, get_temp_frame_paths, get_temp_frames_pattern
-from facefusion.typing import AudioBuffer, Fps, OutputVideoPreset, UpdateProgress
-from facefusion.vision import count_trim_frame_total, detect_video_duration, restrict_video_fps
+import facefusion.choices
+from facefusion import ffmpeg_builder, logger, process_manager, state_manager, wording
+from facefusion.filesystem import get_file_format, remove_file
+from facefusion.temp_helper import get_temp_file_path, get_temp_frames_pattern
+from facefusion.types import AudioBuffer, AudioEncoder, Commands, EncoderSet, Fps, Resolution, UpdateProgress, VideoEncoder, VideoFormat
+from facefusion.vision import detect_video_duration, detect_video_fps, pack_resolution, predict_video_frame_total
 
 
-def run_ffmpeg_with_progress(args: List[str], update_progress : UpdateProgress) -> subprocess.Popen[bytes]:
+def run_ffmpeg_with_progress(commands : Commands, update_progress : UpdateProgress) -> subprocess.Popen[bytes]:
 	log_level = state_manager.get_item('log_level')
-	commands = [ shutil.which('ffmpeg'), '-hide_banner', '-nostats', '-loglevel', 'error', '-progress', '-' ]
-	commands.extend(args)
+	commands.extend(ffmpeg_builder.set_progress())
+	commands.extend(ffmpeg_builder.cast_stream())
+	commands = ffmpeg_builder.run(commands)
 	process = subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
 
 	while process_manager.is_processing():
 		try:
-
 			while __line__ := process.stdout.readline().decode().lower():
+				if process_manager.is_stopping():
+					process.terminate()
+
 				if 'frame=' in __line__:
 					_, frame_number = __line__.split('frame=')
 					update_progress(int(frame_number))
@@ -35,15 +38,16 @@ def run_ffmpeg_with_progress(args: List[str], update_progress : UpdateProgress)
 			continue
 		return process
 
-	if process_manager.is_stopping():
-		process.terminate()
 	return process
 
 
-def run_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
+def update_progress(progress : tqdm, frame_number : int) -> None:
+	progress.update(frame_number - progress.n)
+
+
+def run_ffmpeg(commands : Commands) -> subprocess.Popen[bytes]:
 	log_level = state_manager.get_item('log_level')
-	commands = [ shutil.which('ffmpeg'), '-hide_banner', '-nostats', '-loglevel', 'error' ]
-	commands.extend(args)
+	commands = ffmpeg_builder.run(commands)
 	process = subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
 
 	while process_manager.is_processing():
@@ -57,12 +61,12 @@ def run_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
 
 	if process_manager.is_stopping():
 		process.terminate()
+
 	return process
 
 
-def open_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
-	commands = [ shutil.which('ffmpeg'), '-loglevel', 'quiet' ]
-	commands.extend(args)
+def open_ffmpeg(commands : Commands) -> subprocess.Popen[bytes]:
+	commands = ffmpeg_builder.run(commands)
 	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)
 
 
@@ -75,100 +79,84 @@ def log_debug(process : subprocess.Popen[bytes]) -> None:
 			logger.debug(error.strip(), __name__)
 
 
-def extract_frames(target_path : str, temp_video_resolution : str, temp_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
-	extract_frame_total = count_trim_frame_total(target_path, trim_frame_start, trim_frame_end)
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
-	commands = [ '-i', target_path, '-s', str(temp_video_resolution), '-q:v', '0' ]
+def get_available_encoder_set() -> EncoderSet:
+	available_encoder_set : EncoderSet =\
+	{
+		'audio': [],
+		'video': []
+	}
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.get_encoders()
+	)
+	process = run_ffmpeg(commands)
 
-	if isinstance(trim_frame_start, int) and isinstance(trim_frame_end, int):
-		commands.extend([ '-vf', 'trim=start_frame=' + str(trim_frame_start) + ':end_frame=' + str(trim_frame_end) + ',fps=' + str(temp_video_fps) ])
-	elif isinstance(trim_frame_start, int):
-		commands.extend([ '-vf', 'trim=start_frame=' + str(trim_frame_start) + ',fps=' + str(temp_video_fps) ])
-	elif isinstance(trim_frame_end, int):
-		commands.extend([ '-vf', 'trim=end_frame=' + str(trim_frame_end) + ',fps=' + str(temp_video_fps) ])
-	else:
-		commands.extend([ '-vf', 'fps=' + str(temp_video_fps) ])
-	commands.extend([ '-vsync', '0', temp_frames_pattern ])
+	while line := process.stdout.readline().decode().lower():
+		if line.startswith(' a'):
+			audio_encoder = line.split()[1]
+
+			if audio_encoder in facefusion.choices.output_audio_encoders:
+				index = facefusion.choices.output_audio_encoders.index(audio_encoder) #type:ignore[arg-type]
+				available_encoder_set['audio'].insert(index, audio_encoder) #type:ignore[arg-type]
+		if line.startswith(' v'):
+			video_encoder = line.split()[1]
+
+			if video_encoder in facefusion.choices.output_video_encoders:
+				index = facefusion.choices.output_video_encoders.index(video_encoder) #type:ignore[arg-type]
+				available_encoder_set['video'].insert(index, video_encoder) #type:ignore[arg-type]
+
+	return available_encoder_set
+
+
+def extract_frames(target_path : str, temp_video_resolution : Resolution, temp_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+	extract_frame_total = predict_video_frame_total(target_path, temp_video_fps, trim_frame_start, trim_frame_end)
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.set_media_resolution(pack_resolution(temp_video_resolution)),
+		ffmpeg_builder.set_frame_quality(0),
+		ffmpeg_builder.select_frame_range(trim_frame_start, trim_frame_end, temp_video_fps),
+		ffmpeg_builder.prevent_frame_drop(),
+		ffmpeg_builder.set_output(temp_frames_pattern)
+	)
 
 	with tqdm(total = extract_frame_total, desc = wording.get('extracting'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
-		process = run_ffmpeg_with_progress(commands, lambda frame_number: progress.update(frame_number - progress.n))
+		process = run_ffmpeg_with_progress(commands, partial(update_progress, progress))
 		return process.returncode == 0
 
 
-def merge_video(target_path : str, output_video_resolution : str, output_video_fps: Fps) -> bool:
-	output_video_encoder = state_manager.get_item('output_video_encoder')
-	output_video_quality = state_manager.get_item('output_video_quality')
-	output_video_preset = state_manager.get_item('output_video_preset')
-	merge_frame_total = len(get_temp_frame_paths(target_path))
-	temp_video_fps = restrict_video_fps(target_path, output_video_fps)
-	temp_file_path = get_temp_file_path(target_path)
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
-	is_webm = filetype.guess_mime(target_path) == 'video/webm'
-
-	if is_webm:
-		output_video_encoder = 'libvpx-vp9'
-	commands = [ '-r', str(temp_video_fps), '-i', temp_frames_pattern, '-s', str(output_video_resolution), '-c:v', output_video_encoder ]
-	if output_video_encoder in [ 'libx264', 'libx265' ]:
-		output_video_compression = round(51 - (output_video_quality * 0.51))
-		commands.extend([ '-crf', str(output_video_compression), '-preset', output_video_preset ])
-	if output_video_encoder in [ 'libvpx-vp9' ]:
-		output_video_compression = round(63 - (output_video_quality * 0.63))
-		commands.extend([ '-crf', str(output_video_compression) ])
-	if output_video_encoder in [ 'h264_nvenc', 'hevc_nvenc' ]:
-		output_video_compression = round(51 - (output_video_quality * 0.51))
-		commands.extend([ '-cq', str(output_video_compression), '-preset', map_nvenc_preset(output_video_preset) ])
-	if output_video_encoder in [ 'h264_amf', 'hevc_amf' ]:
-		output_video_compression = round(51 - (output_video_quality * 0.51))
-		commands.extend([ '-qp_i', str(output_video_compression), '-qp_p', str(output_video_compression), '-quality', map_amf_preset(output_video_preset) ])
-	if output_video_encoder in [ 'h264_videotoolbox', 'hevc_videotoolbox' ]:
-		commands.extend([ '-q:v', str(output_video_quality) ])
-	commands.extend([ '-vf', 'framerate=fps=' + str(output_video_fps), '-pix_fmt', 'yuv420p', '-colorspace', 'bt709', '-y', temp_file_path ])
-
-	with tqdm(total = merge_frame_total, desc = wording.get('merging'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
-		process = run_ffmpeg_with_progress(commands, lambda frame_number: progress.update(frame_number - progress.n))
-		return process.returncode == 0
-
-
-def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
-	output_audio_encoder = state_manager.get_item('output_audio_encoder')
-	concat_video_path = tempfile.mktemp()
-
-	with open(concat_video_path, 'w') as concat_video_file:
-		for temp_output_path in temp_output_paths:
-			concat_video_file.write('file \'' + os.path.abspath(temp_output_path) + '\'' + os.linesep)
-		concat_video_file.flush()
-		concat_video_file.close()
-	commands = [ '-f', 'concat', '-safe', '0', '-i', concat_video_file.name, '-c:v', 'copy', '-c:a', output_audio_encoder, '-y', os.path.abspath(output_path) ]
-	process = run_ffmpeg(commands)
-	process.communicate()
-	remove_file(concat_video_path)
-	return process.returncode == 0
-
-
-def copy_image(target_path : str, temp_image_resolution : str) -> bool:
-	temp_file_path = get_temp_file_path(target_path)
-	temp_image_compression = calc_image_compression(target_path, 100)
-	commands = [ '-i', target_path, '-s', str(temp_image_resolution), '-q:v', str(temp_image_compression), '-y', temp_file_path ]
+def copy_image(target_path : str, temp_image_resolution : Resolution) -> bool:
+	temp_image_path = get_temp_file_path(target_path)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.set_media_resolution(pack_resolution(temp_image_resolution)),
+		ffmpeg_builder.set_image_quality(target_path, 100),
+		ffmpeg_builder.force_output(temp_image_path)
+	)
 	return run_ffmpeg(commands).returncode == 0
 
 
-def finalize_image(target_path : str, output_path : str, output_image_resolution : str) -> bool:
+def finalize_image(target_path : str, output_path : str, output_image_resolution : Resolution) -> bool:
 	output_image_quality = state_manager.get_item('output_image_quality')
-	temp_file_path = get_temp_file_path(target_path)
-	output_image_compression = calc_image_compression(target_path, output_image_quality)
-	commands = [ '-i', temp_file_path, '-s', str(output_image_resolution), '-q:v', str(output_image_compression), '-y', output_path ]
+	temp_image_path = get_temp_file_path(target_path)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(temp_image_path),
+		ffmpeg_builder.set_media_resolution(pack_resolution(output_image_resolution)),
+		ffmpeg_builder.set_image_quality(target_path, output_image_quality),
+		ffmpeg_builder.force_output(output_path)
+	)
 	return run_ffmpeg(commands).returncode == 0
 
 
-def calc_image_compression(image_path : str, image_quality : int) -> int:
-	is_webp = filetype.guess_mime(image_path) == 'image/webp'
-	if is_webp:
-		image_quality = 100 - image_quality
-	return round(31 - (image_quality * 0.31))
+def read_audio_buffer(target_path : str, audio_sample_rate : int, audio_sample_size : int, audio_channel_total : int) -> Optional[AudioBuffer]:
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.ignore_video_stream(),
+		ffmpeg_builder.set_audio_sample_rate(audio_sample_rate),
+		ffmpeg_builder.set_audio_sample_size(audio_sample_size),
+		ffmpeg_builder.set_audio_channel_total(audio_channel_total),
+		ffmpeg_builder.cast_stream()
+	)
 
-
-def read_audio_buffer(target_path : str, sample_rate : int, channel_total : int) -> Optional[AudioBuffer]:
-	commands = [ '-i', target_path, '-vn', '-f', 's16le', '-acodec', 'pcm_s16le', '-ar', str(sample_rate), '-ac', str(channel_total), '-' ]
 	process = open_ffmpeg(commands)
 	audio_buffer, _ = process.communicate()
 	if process.returncode == 0:
@@ -176,55 +164,123 @@ def read_audio_buffer(target_path : str, sample_rate : int, channel_total : int)
 	return None
 
 
-def restore_audio(target_path : str, output_path : str, output_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+def restore_audio(target_path : str, output_path : str, trim_frame_start : int, trim_frame_end : int) -> bool:
 	output_audio_encoder = state_manager.get_item('output_audio_encoder')
-	temp_file_path = get_temp_file_path(target_path)
-	temp_video_duration = detect_video_duration(temp_file_path)
-	commands = [ '-i', temp_file_path ]
+	output_audio_quality = state_manager.get_item('output_audio_quality')
+	output_audio_volume = state_manager.get_item('output_audio_volume')
+	target_video_fps = detect_video_fps(target_path)
+	temp_video_path = get_temp_file_path(target_path)
+	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_video_duration = detect_video_duration(temp_video_path)
 
-	if isinstance(trim_frame_start, int):
-		start_time = trim_frame_start / output_video_fps
-		commands.extend([ '-ss', str(start_time) ])
-	if isinstance(trim_frame_end, int):
-		end_time = trim_frame_end / output_video_fps
-		commands.extend([ '-to', str(end_time) ])
-	commands.extend([ '-i', target_path, '-c:v', 'copy', '-c:a', output_audio_encoder, '-map', '0:v:0', '-map', '1:a:0', '-t', str(temp_video_duration), '-y', output_path ])
+	output_audio_encoder = fix_audio_encoder(temp_video_format, output_audio_encoder)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(temp_video_path),
+		ffmpeg_builder.select_media_range(trim_frame_start, trim_frame_end, target_video_fps),
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.set_audio_encoder(output_audio_encoder),
+		ffmpeg_builder.set_audio_quality(output_audio_encoder, output_audio_quality),
+		ffmpeg_builder.set_audio_volume(output_audio_volume),
+		ffmpeg_builder.select_media_stream('0:v:0'),
+		ffmpeg_builder.select_media_stream('1:a:0'),
+		ffmpeg_builder.set_video_duration(temp_video_duration),
+		ffmpeg_builder.force_output(output_path)
+	)
 	return run_ffmpeg(commands).returncode == 0
 
 
 def replace_audio(target_path : str, audio_path : str, output_path : str) -> bool:
 	output_audio_encoder = state_manager.get_item('output_audio_encoder')
-	temp_file_path = get_temp_file_path(target_path)
-	temp_video_duration = detect_video_duration(temp_file_path)
-	commands = [ '-i', temp_file_path, '-i', audio_path, '-c:v', 'copy', '-c:a', output_audio_encoder, '-t', str(temp_video_duration), '-y', output_path ]
+	output_audio_quality = state_manager.get_item('output_audio_quality')
+	output_audio_volume = state_manager.get_item('output_audio_volume')
+	temp_video_path = get_temp_file_path(target_path)
+	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_video_duration = detect_video_duration(temp_video_path)
+
+	output_audio_encoder = fix_audio_encoder(temp_video_format, output_audio_encoder)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(temp_video_path),
+		ffmpeg_builder.set_input(audio_path),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.set_audio_encoder(output_audio_encoder),
+		ffmpeg_builder.set_audio_quality(output_audio_encoder, output_audio_quality),
+		ffmpeg_builder.set_audio_volume(output_audio_volume),
+		ffmpeg_builder.set_video_duration(temp_video_duration),
+		ffmpeg_builder.force_output(output_path)
+	)
 	return run_ffmpeg(commands).returncode == 0
 
 
-def map_nvenc_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
-	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast' ]:
-		return 'fast'
-	if output_video_preset == 'medium':
-		return 'medium'
-	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
-		return 'slow'
-	return None
+def merge_video(target_path : str, temp_video_fps : Fps, output_video_resolution : Resolution, output_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+	output_video_encoder = state_manager.get_item('output_video_encoder')
+	output_video_quality = state_manager.get_item('output_video_quality')
+	output_video_preset = state_manager.get_item('output_video_preset')
+	merge_frame_total = predict_video_frame_total(target_path, output_video_fps, trim_frame_start, trim_frame_end)
+	temp_video_path = get_temp_file_path(target_path)
+	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
+
+	output_video_encoder = fix_video_encoder(temp_video_format, output_video_encoder)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input_fps(temp_video_fps),
+		ffmpeg_builder.set_input(temp_frames_pattern),
+		ffmpeg_builder.set_media_resolution(pack_resolution(output_video_resolution)),
+		ffmpeg_builder.set_video_encoder(output_video_encoder),
+		ffmpeg_builder.set_video_quality(output_video_encoder, output_video_quality),
+		ffmpeg_builder.set_video_preset(output_video_encoder, output_video_preset),
+		ffmpeg_builder.set_video_fps(output_video_fps),
+		ffmpeg_builder.set_pixel_format(output_video_encoder),
+		ffmpeg_builder.force_output(temp_video_path)
+	)
+
+	with tqdm(total = merge_frame_total, desc = wording.get('merging'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+		process = run_ffmpeg_with_progress(commands, partial(update_progress, progress))
+		return process.returncode == 0
 
 
-def map_amf_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
-	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
-		return 'speed'
-	if output_video_preset in [ 'faster', 'fast', 'medium' ]:
-		return 'balanced'
-	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
-		return 'quality'
-	return None
+def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
+	concat_video_path = tempfile.mktemp()
+
+	with open(concat_video_path, 'w') as concat_video_file:
+		for temp_output_path in temp_output_paths:
+			concat_video_file.write('file \'' + os.path.abspath(temp_output_path) + '\'' + os.linesep)
+		concat_video_file.flush()
+		concat_video_file.close()
+
+	output_path = os.path.abspath(output_path)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.unsafe_concat(),
+		ffmpeg_builder.set_input(concat_video_file.name),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.copy_audio_encoder(),
+		ffmpeg_builder.force_output(output_path)
+	)
+	process = run_ffmpeg(commands)
+	process.communicate()
+	remove_file(concat_video_path)
+	return process.returncode == 0
 
 
-def map_qsv_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
-	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast' ]:
-		return 'fast'
-	if output_video_preset == 'medium':
-		return 'medium'
-	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
-		return 'slow'
-	return None
+def fix_audio_encoder(video_format : VideoFormat, audio_encoder : AudioEncoder) -> AudioEncoder:
+	if video_format == 'avi' and audio_encoder == 'libopus':
+		return 'aac'
+	if video_format in [ 'm4v', 'wmv' ]:
+		return 'aac'
+	if video_format == 'mov' and audio_encoder in [ 'flac', 'libopus' ]:
+		return 'aac'
+	if video_format == 'webm':
+		return 'libopus'
+	return audio_encoder
+
+
+def fix_video_encoder(video_format : VideoFormat, video_encoder : VideoEncoder) -> VideoEncoder:
+	if video_format in [ 'm4v', 'wmv' ]:
+		return 'libx264'
+	if video_format in [ 'mkv', 'mp4' ] and video_encoder == 'rawvideo':
+		return 'libx264'
+	if video_format == 'mov' and video_encoder == 'libvpx-vp9':
+		return 'libx264'
+	if video_format == 'webm':
+		return 'libvpx-vp9'
+	return video_encoder

facefusion/ffmpeg_builder.py

@@ -0,0 +1,244 @@
+import itertools
+import shutil
+from typing import Optional
+
+import numpy
+
+from facefusion.filesystem import get_file_format
+from facefusion.types import AudioEncoder, Commands, Duration, Fps, StreamMode, VideoEncoder, VideoPreset
+
+
+def run(commands : Commands) -> Commands:
+	return [ shutil.which('ffmpeg'), '-loglevel', 'error' ] + commands
+
+
+def chain(*commands : Commands) -> Commands:
+	return list(itertools.chain(*commands))
+
+
+def get_encoders() -> Commands:
+	return [ '-encoders' ]
+
+
+def set_hardware_accelerator(value : str) -> Commands:
+	return [ '-hwaccel', value ]
+
+
+def set_progress() -> Commands:
+	return [ '-progress' ]
+
+
+def set_input(input_path : str) -> Commands:
+	return [ '-i', input_path ]
+
+
+def set_input_fps(input_fps : Fps) -> Commands:
+	return [ '-r', str(input_fps)]
+
+
+def set_output(output_path : str) -> Commands:
+	return [ output_path ]
+
+
+def force_output(output_path : str) -> Commands:
+	return [ '-y', output_path ]
+
+
+def cast_stream() -> Commands:
+	return [ '-' ]
+
+
+def set_stream_mode(stream_mode : StreamMode) -> Commands:
+	if stream_mode == 'udp':
+		return [ '-f', 'mpegts' ]
+	if stream_mode == 'v4l2':
+		return [ '-f', 'v4l2' ]
+	return []
+
+
+def set_stream_quality(stream_quality : int) -> Commands:
+	return [ '-b:v', str(stream_quality) + 'k' ]
+
+
+def unsafe_concat() -> Commands:
+	return [ '-f', 'concat', '-safe', '0' ]
+
+
+def set_pixel_format(video_encoder : VideoEncoder) -> Commands:
+	if video_encoder == 'rawvideo':
+		return [ '-pix_fmt', 'rgb24' ]
+	return [ '-pix_fmt', 'yuv420p' ]
+
+
+def set_frame_quality(frame_quality : int) -> Commands:
+	return [ '-q:v', str(frame_quality) ]
+
+
+def select_frame_range(frame_start : int, frame_end : int, video_fps : Fps) -> Commands:
+	if isinstance(frame_start, int) and isinstance(frame_end, int):
+		return [ '-vf', 'trim=start_frame=' + str(frame_start) + ':end_frame=' + str(frame_end) + ',fps=' + str(video_fps) ]
+	if isinstance(frame_start, int):
+		return [ '-vf', 'trim=start_frame=' + str(frame_start) + ',fps=' + str(video_fps) ]
+	if isinstance(frame_end, int):
+		return [ '-vf', 'trim=end_frame=' + str(frame_end) + ',fps=' + str(video_fps) ]
+	return [ '-vf', 'fps=' + str(video_fps) ]
+
+
+def prevent_frame_drop() -> Commands:
+	return [ '-vsync', '0' ]
+
+
+def select_media_range(frame_start : int, frame_end : int, media_fps : Fps) -> Commands:
+	commands = []
+
+	if isinstance(frame_start, int):
+		commands.extend([ '-ss', str(frame_start / media_fps) ])
+	if isinstance(frame_end, int):
+		commands.extend([ '-to', str(frame_end / media_fps) ])
+	return commands
+
+
+def select_media_stream(media_stream : str) -> Commands:
+	return [ '-map', media_stream ]
+
+
+def set_media_resolution(video_resolution : str) -> Commands:
+	return [ '-s', video_resolution ]
+
+
+def set_image_quality(image_path : str, image_quality : int) -> Commands:
+	if get_file_format(image_path) == 'webp':
+		return [ '-q:v', str(image_quality) ]
+
+	image_compression = round(31 - (image_quality * 0.31))
+	return [ '-q:v', str(image_compression) ]
+
+
+def set_audio_encoder(audio_codec : str) -> Commands:
+	return [ '-c:a', audio_codec ]
+
+
+def copy_audio_encoder() -> Commands:
+	return set_audio_encoder('copy')
+
+
+def set_audio_sample_rate(audio_sample_rate : int) -> Commands:
+	return [ '-ar', str(audio_sample_rate) ]
+
+
+def set_audio_sample_size(audio_sample_size : int) -> Commands:
+	if audio_sample_size == 16:
+		return [ '-f', 's16le' ]
+	if audio_sample_size == 32:
+		return [ '-f', 's32le' ]
+	return []
+
+
+def set_audio_channel_total(audio_channel_total : int) -> Commands:
+	return [ '-ac', str(audio_channel_total) ]
+
+
+def set_audio_quality(audio_encoder : AudioEncoder, audio_quality : int) -> Commands:
+	if audio_encoder == 'aac':
+		audio_compression = numpy.round(numpy.interp(audio_quality, [ 0, 100 ], [ 0.1, 2.0 ]), 1).astype(float).item()
+		return [ '-q:a', str(audio_compression) ]
+	if audio_encoder == 'libmp3lame':
+		audio_compression = numpy.round(numpy.interp(audio_quality, [ 0, 100 ], [ 9, 0 ])).astype(int).item()
+		return [ '-q:a', str(audio_compression) ]
+	if audio_encoder == 'libopus':
+		audio_bit_rate = numpy.round(numpy.interp(audio_quality, [ 0, 100 ], [ 64, 256 ])).astype(int).item()
+		return [ '-b:a', str(audio_bit_rate) + 'k' ]
+	if audio_encoder == 'libvorbis':
+		audio_compression = numpy.round(numpy.interp(audio_quality, [ 0, 100 ], [ -1, 10 ]), 1).astype(float).item()
+		return [ '-q:a', str(audio_compression) ]
+	return []
+
+
+def set_audio_volume(audio_volume : int) -> Commands:
+	return [ '-filter:a', 'volume=' + str(audio_volume / 100) ]
+
+
+def set_video_encoder(video_encoder : str) -> Commands:
+	return [ '-c:v', video_encoder ]
+
+
+def copy_video_encoder() -> Commands:
+	return set_video_encoder('copy')
+
+
+def set_video_quality(video_encoder : VideoEncoder, video_quality : int) -> Commands:
+	if video_encoder in [ 'libx264', 'libx264rgb', 'libx265' ]:
+		video_compression = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ])).astype(int).item()
+		return [ '-crf', str(video_compression) ]
+	if video_encoder == 'libvpx-vp9':
+		video_compression = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 63, 0 ])).astype(int).item()
+		return [ '-crf', str(video_compression) ]
+	if video_encoder in [ 'h264_nvenc', 'hevc_nvenc' ]:
+		video_compression = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ])).astype(int).item()
+		return [ '-cq', str(video_compression) ]
+	if video_encoder in [ 'h264_amf', 'hevc_amf' ]:
+		video_compression = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ])).astype(int).item()
+		return [ '-qp_i', str(video_compression), '-qp_p', str(video_compression), '-qp_b', str(video_compression) ]
+	if video_encoder in [ 'h264_qsv', 'hevc_qsv' ]:
+		video_compression = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ])).astype(int).item()
+		return [ '-qp', str(video_compression) ]
+	if video_encoder in [ 'h264_videotoolbox', 'hevc_videotoolbox' ]:
+		video_bit_rate = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 1024, 50512 ])).astype(int).item()
+		return [ '-b:v', str(video_bit_rate) + 'k' ]
+	return []
+
+
+def set_video_preset(video_encoder : VideoEncoder, video_preset : VideoPreset) -> Commands:
+	if video_encoder in [ 'libx264', 'libx264rgb', 'libx265' ]:
+		return [ '-preset', video_preset ]
+	if video_encoder in [ 'h264_nvenc', 'hevc_nvenc' ]:
+		return [ '-preset', map_nvenc_preset(video_preset) ]
+	if video_encoder in [ 'h264_amf', 'hevc_amf' ]:
+		return [ '-quality', map_amf_preset(video_preset) ]
+	if video_encoder in [ 'h264_qsv', 'hevc_qsv' ]:
+		return [ '-preset', map_qsv_preset(video_preset) ]
+	return []
+
+
+def set_video_fps(video_fps : Fps) -> Commands:
+	return [ '-vf', 'framerate=fps=' + str(video_fps) ]
+
+
+def set_video_duration(video_duration : Duration) -> Commands:
+	return [ '-t', str(video_duration) ]
+
+
+def capture_video() -> Commands:
+	return [ '-f', 'rawvideo', '-pix_fmt', 'rgb24' ]
+
+
+def ignore_video_stream() -> Commands:
+	return [ '-vn' ]
+
+
+def map_nvenc_preset(video_preset : VideoPreset) -> Optional[str]:
+	if video_preset in [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast' ]:
+		return 'fast'
+	if video_preset == 'medium':
+		return 'medium'
+	if video_preset in [ 'slow', 'slower', 'veryslow' ]:
+		return 'slow'
+	return None
+
+
+def map_amf_preset(video_preset : VideoPreset) -> Optional[str]:
+	if video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
+		return 'speed'
+	if video_preset in [ 'faster', 'fast', 'medium' ]:
+		return 'balanced'
+	if video_preset in [ 'slow', 'slower', 'veryslow' ]:
+		return 'quality'
+	return None
+
+
+def map_qsv_preset(video_preset : VideoPreset) -> Optional[str]:
+	if video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
+		return 'veryfast'
+	if video_preset in [ 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]:
+		return video_preset
+	return None

facefusion/filesystem.py

@@ -1,16 +1,9 @@
 import glob
 import os
 import shutil
-from pathlib import Path
 from typing import List, Optional
 
-import filetype
-
-from facefusion.common_helper import is_windows
-from facefusion.typing import File
-
-if is_windows():
-	import ctypes
+import facefusion.choices
 
 
 def get_file_size(file_path : str) -> int:
@@ -19,54 +12,95 @@ def get_file_size(file_path : str) -> int:
 	return 0
 
 
-def same_file_extension(file_paths : List[str]) -> bool:
-	file_extensions : List[str] = []
+def get_file_name(file_path : str) -> Optional[str]:
+	file_name, _ = os.path.splitext(os.path.basename(file_path))
 
-	for file_path in file_paths:
-		_, file_extension = os.path.splitext(file_path.lower())
+	if file_name:
+		return file_name
+	return None
 
-		if file_extensions and file_extension not in file_extensions:
-			return False
-		file_extensions.append(file_extension)
-	return True
+
+def get_file_extension(file_path : str) -> Optional[str]:
+	_, file_extension = os.path.splitext(file_path)
+
+	if file_extension:
+		return file_extension.lower()
+	return None
+
+
+def get_file_format(file_path : str) -> Optional[str]:
+	file_extension = get_file_extension(file_path)
+
+	if file_extension:
+		if file_extension == '.jpg':
+			return 'jpeg'
+		if file_extension == '.tif':
+			return 'tiff'
+		return file_extension.lstrip('.')
+	return None
+
+
+def same_file_extension(first_file_path : str, second_file_path : str) -> bool:
+	first_file_extension = get_file_extension(first_file_path)
+	second_file_extension = get_file_extension(second_file_path)
+
+	if first_file_extension and second_file_extension:
+		return get_file_extension(first_file_path) == get_file_extension(second_file_path)
+	return False
 
 
 def is_file(file_path : str) -> bool:
-	return bool(file_path and os.path.isfile(file_path))
-
-
-def is_directory(directory_path : str) -> bool:
-	return bool(directory_path and os.path.isdir(directory_path))
-
-
-def in_directory(file_path : str) -> bool:
-	if file_path and not is_directory(file_path):
-		return is_directory(os.path.dirname(file_path))
+	if file_path:
+		return os.path.isfile(file_path)
 	return False
 
 
 def is_audio(audio_path : str) -> bool:
-	return is_file(audio_path) and filetype.helpers.is_audio(audio_path)
+	return is_file(audio_path) and get_file_format(audio_path) in facefusion.choices.audio_formats
 
 
 def has_audio(audio_paths : List[str]) -> bool:
 	if audio_paths:
-		return any(is_audio(audio_path) for audio_path in audio_paths)
+		return any(map(is_audio, audio_paths))
+	return False
+
+
+def are_audios(audio_paths : List[str]) -> bool:
+	if audio_paths:
+		return all(map(is_audio, audio_paths))
 	return False
 
 
 def is_image(image_path : str) -> bool:
-	return is_file(image_path) and filetype.helpers.is_image(image_path)
+	return is_file(image_path) and get_file_format(image_path) in facefusion.choices.image_formats
 
 
-def has_image(image_paths: List[str]) -> bool:
+def has_image(image_paths : List[str]) -> bool:
 	if image_paths:
 		return any(is_image(image_path) for image_path in image_paths)
 	return False
 
 
+def are_images(image_paths : List[str]) -> bool:
+	if image_paths:
+		return all(map(is_image, image_paths))
+	return False
+
+
 def is_video(video_path : str) -> bool:
-	return is_file(video_path) and filetype.helpers.is_video(video_path)
+	return is_file(video_path) and get_file_format(video_path) in facefusion.choices.video_formats
+
+
+def has_video(video_paths : List[str]) -> bool:
+	if video_paths:
+		return any(map(is_video, video_paths))
+	return False
+
+
+def are_videos(video_paths : List[str]) -> bool:
+	if video_paths:
+		return any(map(is_video, video_paths))
+	return False
 
 
 def filter_audio_paths(paths : List[str]) -> List[str]:
@@ -81,24 +115,6 @@ def filter_image_paths(paths : List[str]) -> List[str]:
 	return []
 
 
-def resolve_relative_path(path : str) -> str:
-	return os.path.abspath(os.path.join(os.path.dirname(__file__), path))
-
-
-def sanitize_path_for_windows(full_path : str) -> Optional[str]:
-	buffer_size = 0
-
-	while True:
-		unicode_buffer = ctypes.create_unicode_buffer(buffer_size)
-		buffer_limit = ctypes.windll.kernel32.GetShortPathNameW(full_path, unicode_buffer, buffer_size) #type:ignore[attr-defined]
-
-		if buffer_size > buffer_limit:
-			return unicode_buffer.value
-		if buffer_limit == 0:
-			return None
-		buffer_size = buffer_limit
-
-
 def copy_file(file_path : str, move_path : str) -> bool:
 	if is_file(file_path):
 		shutil.copy(file_path, move_path)
@@ -120,31 +136,18 @@ def remove_file(file_path : str) -> bool:
 	return False
 
 
-def create_directory(directory_path : str) -> bool:
-	if directory_path and not is_file(directory_path):
-		Path(directory_path).mkdir(parents = True, exist_ok = True)
-		return is_directory(directory_path)
-	return False
+def resolve_file_paths(directory_path : str) -> List[str]:
+	file_paths : List[str] = []
 
-
-def list_directory(directory_path : str) -> Optional[List[File]]:
 	if is_directory(directory_path):
-		file_paths = sorted(os.listdir(directory_path))
-		files: List[File] = []
+		file_names_and_extensions = sorted(os.listdir(directory_path))
 
-		for file_path in file_paths:
-			file_name, file_extension = os.path.splitext(file_path)
+		for file_name_and_extension in file_names_and_extensions:
+			if not file_name_and_extension.startswith(('.', '__')):
+				file_path = os.path.join(directory_path, file_name_and_extension)
+				file_paths.append(file_path)
 
-			if not file_name.startswith(('.', '__')):
-				files.append(
-				{
-					'name': file_name,
-					'extension': file_extension,
-					'path': os.path.join(directory_path, file_path)
-				})
-
-		return files
-	return None
+	return file_paths
 
 
 def resolve_file_pattern(file_pattern : str) -> List[str]:
@@ -153,8 +156,33 @@ def resolve_file_pattern(file_pattern : str) -> List[str]:
 	return []
 
 
+def is_directory(directory_path : str) -> bool:
+	if directory_path:
+		return os.path.isdir(directory_path)
+	return False
+
+
+def in_directory(file_path : str) -> bool:
+	if file_path:
+		directory_path = os.path.dirname(file_path)
+		if directory_path:
+			return not is_directory(file_path) and is_directory(directory_path)
+	return False
+
+
+def create_directory(directory_path : str) -> bool:
+	if directory_path and not is_file(directory_path):
+		os.makedirs(directory_path, exist_ok = True)
+		return is_directory(directory_path)
+	return False
+
+
 def remove_directory(directory_path : str) -> bool:
 	if is_directory(directory_path):
 		shutil.rmtree(directory_path, ignore_errors = True)
 		return not is_directory(directory_path)
 	return False
+
+
+def resolve_relative_path(path : str) -> str:
+	return os.path.abspath(os.path.join(os.path.dirname(__file__), path))

facefusion/hash_helper.py

@@ -2,7 +2,7 @@ import os
 import zlib
 from typing import Optional
 
-from facefusion.filesystem import is_file
+from facefusion.filesystem import get_file_name, is_file
 
 
 def create_hash(content : bytes) -> str:
@@ -13,8 +13,8 @@ def validate_hash(validate_path : str) -> bool:
 	hash_path = get_hash_path(validate_path)
 
 	if is_file(hash_path):
-		with open(hash_path, 'r') as hash_file:
-			hash_content = hash_file.read().strip()
+		with open(hash_path) as hash_file:
+			hash_content = hash_file.read()
 
 		with open(validate_path, 'rb') as validate_file:
 			validate_content = validate_file.read()
@@ -25,8 +25,8 @@ def validate_hash(validate_path : str) -> bool:
 
 def get_hash_path(validate_path : str) -> Optional[str]:
 	if is_file(validate_path):
-		validate_directory_path, _ = os.path.split(validate_path)
-		validate_file_name, _ = os.path.splitext(_)
+		validate_directory_path, file_name_and_extension = os.path.split(validate_path)
+		validate_file_name = get_file_name(file_name_and_extension)
 
 		return os.path.join(validate_directory_path, validate_file_name + '.hash')
 	return None

facefusion/inference_manager.py

@@ -1,63 +1,92 @@
-from time import sleep
+import importlib
+import random
+from time import sleep, time
 from typing import List
 
 from onnxruntime import InferenceSession
 
-from facefusion import process_manager, state_manager
+from facefusion import logger, process_manager, state_manager, wording
 from facefusion.app_context import detect_app_context
-from facefusion.execution import create_inference_execution_providers
-from facefusion.thread_helper import thread_lock
-from facefusion.typing import DownloadSet, ExecutionProvider, InferencePool, InferencePoolSet
+from facefusion.execution import create_inference_session_providers
+from facefusion.exit_helper import fatal_exit
+from facefusion.filesystem import get_file_name, is_file
+from facefusion.time_helper import calculate_end_time
+from facefusion.types import DownloadSet, ExecutionProvider, InferencePool, InferencePoolSet
 
-INFERENCE_POOLS : InferencePoolSet =\
+INFERENCE_POOL_SET : InferencePoolSet =\
 {
-	'cli': {}, #type:ignore[typeddict-item]
-	'ui': {} #type:ignore[typeddict-item]
+	'cli': {},
+	'ui': {}
 }
 
 
-def get_inference_pool(model_context : str, model_sources : DownloadSet) -> InferencePool:
-	global INFERENCE_POOLS
+def get_inference_pool(module_name : str, model_names : List[str], model_source_set : DownloadSet) -> InferencePool:
+	while process_manager.is_checking():
+		sleep(0.5)
+	execution_device_ids = state_manager.get_item('execution_device_ids')
+	execution_providers = resolve_execution_providers(module_name)
+	app_context = detect_app_context()
 
-	with thread_lock():
-		while process_manager.is_checking():
-			sleep(0.5)
-		app_context = detect_app_context()
-		inference_context = get_inference_context(model_context)
+	for execution_device_id in execution_device_ids:
+		inference_context = get_inference_context(module_name, model_names, execution_device_id, execution_providers)
 
-		if app_context == 'cli' and INFERENCE_POOLS.get('ui').get(inference_context):
-			INFERENCE_POOLS['cli'][inference_context] = INFERENCE_POOLS.get('ui').get(inference_context)
-		if app_context == 'ui' and INFERENCE_POOLS.get('cli').get(inference_context):
-			INFERENCE_POOLS['ui'][inference_context] = INFERENCE_POOLS.get('cli').get(inference_context)
-		if not INFERENCE_POOLS.get(app_context).get(inference_context):
-			INFERENCE_POOLS[app_context][inference_context] = create_inference_pool(model_sources, state_manager.get_item('execution_device_id'), state_manager.get_item('execution_providers'))
+		if app_context == 'cli' and INFERENCE_POOL_SET.get('ui').get(inference_context):
+			INFERENCE_POOL_SET['cli'][inference_context] = INFERENCE_POOL_SET.get('ui').get(inference_context)
+		if app_context == 'ui' and INFERENCE_POOL_SET.get('cli').get(inference_context):
+			INFERENCE_POOL_SET['ui'][inference_context] = INFERENCE_POOL_SET.get('cli').get(inference_context)
+		if not INFERENCE_POOL_SET.get(app_context).get(inference_context):
+			INFERENCE_POOL_SET[app_context][inference_context] = create_inference_pool(model_source_set, execution_device_id, execution_providers)
 
-		return INFERENCE_POOLS.get(app_context).get(inference_context)
+	current_inference_context = get_inference_context(module_name, model_names, random.choice(execution_device_ids), execution_providers)
+	return INFERENCE_POOL_SET.get(app_context).get(current_inference_context)
 
 
-def create_inference_pool(model_sources : DownloadSet, execution_device_id : str, execution_providers : List[ExecutionProvider]) -> InferencePool:
+def create_inference_pool(model_source_set : DownloadSet, execution_device_id : str, execution_providers : List[ExecutionProvider]) -> InferencePool:
 	inference_pool : InferencePool = {}
 
-	for model_name in model_sources.keys():
-		inference_pool[model_name] = create_inference_session(model_sources.get(model_name).get('path'), execution_device_id, execution_providers)
+	for model_name in model_source_set.keys():
+		model_path = model_source_set.get(model_name).get('path')
+		if is_file(model_path):
+			inference_pool[model_name] = create_inference_session(model_path, execution_device_id, execution_providers)
+
 	return inference_pool
 
 
-def clear_inference_pool(model_context : str) -> None:
-	global INFERENCE_POOLS
-
+def clear_inference_pool(module_name : str, model_names : List[str]) -> None:
+	execution_device_ids = state_manager.get_item('execution_device_ids')
+	execution_providers = resolve_execution_providers(module_name)
 	app_context = detect_app_context()
-	inference_context = get_inference_context(model_context)
 
-	if INFERENCE_POOLS.get(app_context).get(inference_context):
-		del INFERENCE_POOLS[app_context][inference_context]
+	for execution_device_id in execution_device_ids:
+		inference_context = get_inference_context(module_name, model_names, execution_device_id, execution_providers)
+
+		if INFERENCE_POOL_SET.get(app_context).get(inference_context):
+			del INFERENCE_POOL_SET[app_context][inference_context]
 
 
 def create_inference_session(model_path : str, execution_device_id : str, execution_providers : List[ExecutionProvider]) -> InferenceSession:
-	inference_execution_providers = create_inference_execution_providers(execution_device_id, execution_providers)
-	return InferenceSession(model_path, providers = inference_execution_providers)
+	model_file_name = get_file_name(model_path)
+	start_time = time()
+
+	try:
+		inference_session_providers = create_inference_session_providers(execution_device_id, execution_providers)
+		inference_session = InferenceSession(model_path, providers = inference_session_providers)
+		logger.debug(wording.get('loading_model_succeeded').format(model_name = model_file_name, seconds = calculate_end_time(start_time)), __name__)
+		return inference_session
+
+	except Exception:
+		logger.error(wording.get('loading_model_failed').format(model_name = model_file_name), __name__)
+		fatal_exit(1)
 
 
-def get_inference_context(model_context : str) -> str:
-	inference_context = model_context + '.' + '_'.join(state_manager.get_item('execution_providers'))
+def get_inference_context(module_name : str, model_names : List[str], execution_device_id : str, execution_providers : List[ExecutionProvider]) -> str:
+	inference_context = '.'.join([ module_name ] + model_names + [ execution_device_id ] + list(execution_providers))
 	return inference_context
+
+
+def resolve_execution_providers(module_name : str) -> List[ExecutionProvider]:
+	module = importlib.import_module(module_name)
+
+	if hasattr(module, 'resolve_execution_providers'):
+		return getattr(module, 'resolve_execution_providers')()
+	return state_manager.get_item('execution_providers')

facefusion/installer.py

@@ -3,60 +3,63 @@ import shutil
 import signal
 import subprocess
 import sys
-import tempfile
 from argparse import ArgumentParser, HelpFormatter
-from typing import Dict, Tuple
+from functools import partial
+from types import FrameType
 
 from facefusion import metadata, wording
-from facefusion.common_helper import is_linux, is_macos, is_windows
+from facefusion.common_helper import is_linux, is_windows
 
-ONNXRUNTIMES : Dict[str, Tuple[str, str]] = {}
-
-if is_macos():
-	ONNXRUNTIMES['default'] = ('onnxruntime', '1.20.1')
-else:
-	ONNXRUNTIMES['default'] = ('onnxruntime', '1.20.1')
-	ONNXRUNTIMES['cuda'] = ('onnxruntime-gpu', '1.20.1')
-	ONNXRUNTIMES['openvino'] = ('onnxruntime-openvino', '1.20.0')
-if is_linux():
-	ONNXRUNTIMES['rocm'] = ('onnxruntime-rocm', '1.19.0')
+ONNXRUNTIME_SET =\
+{
+	'default': ('onnxruntime', '1.22.1')
+}
+if is_windows() or is_linux():
+	ONNXRUNTIME_SET['cuda'] = ('onnxruntime-gpu', '1.22.0')
+	ONNXRUNTIME_SET['openvino'] = ('onnxruntime-openvino', '1.22.0')
 if is_windows():
-	ONNXRUNTIMES['directml'] = ('onnxruntime-directml', '1.17.3')
+	ONNXRUNTIME_SET['directml'] = ('onnxruntime-directml', '1.17.3')
+if is_linux():
+	ONNXRUNTIME_SET['rocm'] = ('onnxruntime-rocm', '1.21.0')
 
 
 def cli() -> None:
-	signal.signal(signal.SIGINT, lambda signal_number, frame: sys.exit(0))
-	program = ArgumentParser(formatter_class = lambda prog: HelpFormatter(prog, max_help_position = 50))
-	program.add_argument('--onnxruntime', help = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIMES.keys(), required = True)
+	signal.signal(signal.SIGINT, signal_exit)
+	program = ArgumentParser(formatter_class = partial(HelpFormatter, max_help_position = 50))
+	program.add_argument('--onnxruntime', help = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIME_SET.keys(), required = True)
 	program.add_argument('--skip-conda', help = wording.get('help.skip_conda'), action = 'store_true')
 	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
 	run(program)
 
 
+def signal_exit(signum : int, frame : FrameType) -> None:
+	sys.exit(0)
+
+
 def run(program : ArgumentParser) -> None:
 	args = program.parse_args()
 	has_conda = 'CONDA_PREFIX' in os.environ
-	onnxruntime_name, onnxruntime_version = ONNXRUNTIMES.get(args.onnxruntime)
+	onnxruntime_name, onnxruntime_version = ONNXRUNTIME_SET.get(args.onnxruntime)
 
 	if not args.skip_conda and not has_conda:
 		sys.stdout.write(wording.get('conda_not_activated') + os.linesep)
 		sys.exit(1)
 
-	subprocess.call([ shutil.which('pip'), 'install', '-r', 'requirements.txt', '--force-reinstall' ])
+	with open('requirements.txt') as file:
+
+		for line in file.readlines():
+			__line__ = line.strip()
+			if not __line__.startswith('onnxruntime'):
+				subprocess.call([ shutil.which('pip'), 'install', line, '--force-reinstall' ])
 
 	if args.onnxruntime == 'rocm':
 		python_id = 'cp' + str(sys.version_info.major) + str(sys.version_info.minor)
 
 		if python_id in [ 'cp310', 'cp312' ]:
 			wheel_name = 'onnxruntime_rocm-' + onnxruntime_version + '-' + python_id + '-' + python_id + '-linux_x86_64.whl'
-			wheel_path = os.path.join(tempfile.gettempdir(), wheel_name)
-			wheel_url = 'https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3.1/' + wheel_name
-			subprocess.call([ shutil.which('curl'), '--silent', '--location', '--continue-at', '-', '--output', wheel_path, wheel_url ])
-			subprocess.call([ shutil.which('pip'), 'uninstall', 'onnxruntime', wheel_path, '-y', '-q' ])
-			subprocess.call([ shutil.which('pip'), 'install', wheel_path, '--force-reinstall' ])
-			os.remove(wheel_path)
+			wheel_url = 'https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/' + wheel_name
+			subprocess.call([ shutil.which('pip'), 'install', wheel_url, '--force-reinstall' ])
 	else:
-		subprocess.call([ shutil.which('pip'), 'uninstall', 'onnxruntime', onnxruntime_name, '-y', '-q' ])
 		subprocess.call([ shutil.which('pip'), 'install', onnxruntime_name + '==' + onnxruntime_version, '--force-reinstall' ])
 
 	if args.onnxruntime == 'cuda' and has_conda:
@@ -89,5 +92,5 @@ def run(program : ArgumentParser) -> None:
 
 			subprocess.call([ shutil.which('conda'), 'env', 'config', 'vars', 'set', 'PATH=' + os.pathsep.join(library_paths) ])
 
-	if args.onnxruntime in [ 'directml', 'rocm' ]:
+	if args.onnxruntime == 'directml':
 		subprocess.call([ shutil.which('pip'), 'install', 'numpy==1.26.4', '--force-reinstall' ])

facefusion/jobs/job_helper.py

@@ -2,12 +2,17 @@ import os
 from datetime import datetime
 from typing import Optional
 
+from facefusion.filesystem import get_file_extension, get_file_name
+
 
 def get_step_output_path(job_id : str, step_index : int, output_path : str) -> Optional[str]:
 	if output_path:
-		output_directory_path, _ = os.path.split(output_path)
-		output_file_name, output_file_extension = os.path.splitext(_)
-		return os.path.join(output_directory_path, output_file_name + '-' + job_id + '-' + str(step_index) + output_file_extension)
+		output_directory_path, output_file_path = os.path.split(output_path)
+		output_file_name = get_file_name(output_file_path)
+		output_file_extension = get_file_extension(output_file_path)
+
+		if output_file_name and output_file_extension:
+			return os.path.join(output_directory_path, output_file_name + '-' + job_id + '-' + str(step_index) + output_file_extension)
 	return None
 
 

facefusion/jobs/job_list.py

@@ -1,9 +1,9 @@
 from datetime import datetime
 from typing import Optional, Tuple
 
-from facefusion.date_helper import describe_time_ago
 from facefusion.jobs import job_manager
-from facefusion.typing import JobStatus, TableContents, TableHeaders
+from facefusion.time_helper import describe_time_ago
+from facefusion.types import JobStatus, TableContents, TableHeaders
 
 
 def compose_job_list(job_status : JobStatus) -> Tuple[TableHeaders, TableContents]:

facefusion/jobs/job_manager.py

@@ -3,11 +3,11 @@ from copy import copy
 from typing import List, Optional
 
 import facefusion.choices
-from facefusion.date_helper import get_current_date_time
-from facefusion.filesystem import create_directory, is_directory, is_file, move_file, remove_directory, remove_file, resolve_file_pattern
+from facefusion.filesystem import create_directory, get_file_name, is_directory, is_file, move_file, remove_directory, remove_file, resolve_file_pattern
 from facefusion.jobs.job_helper import get_step_output_path
 from facefusion.json import read_json, write_json
-from facefusion.typing import Args, Job, JobSet, JobStatus, JobStep, JobStepStatus
+from facefusion.time_helper import get_current_date_time
+from facefusion.types import Args, Job, JobSet, JobStatus, JobStep, JobStepStatus
 
 JOBS_PATH : Optional[str] = None
 
@@ -48,14 +48,17 @@ def submit_job(job_id : str) -> bool:
 	return False
 
 
-def submit_jobs() -> bool:
+def submit_jobs(halt_on_error : bool) -> bool:
 	drafted_job_ids = find_job_ids('drafted')
+	has_error = False
 
 	if drafted_job_ids:
 		for job_id in drafted_job_ids:
 			if not submit_job(job_id):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
@@ -63,24 +66,27 @@ def delete_job(job_id : str) -> bool:
 	return delete_job_file(job_id)
 
 
-def delete_jobs() -> bool:
+def delete_jobs(halt_on_error : bool) -> bool:
 	job_ids = find_job_ids('drafted') + find_job_ids('queued') + find_job_ids('failed') + find_job_ids('completed')
+	has_error = False
 
 	if job_ids:
 		for job_id in job_ids:
 			if not delete_job(job_id):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
 def find_jobs(job_status : JobStatus) -> JobSet:
 	job_ids = find_job_ids(job_status)
-	jobs : JobSet = {}
+	job_set : JobSet = {}
 
 	for job_id in job_ids:
-		jobs[job_id] = read_job_file(job_id)
-	return jobs
+		job_set[job_id] = read_job_file(job_id)
+	return job_set
 
 
 def find_job_ids(job_status : JobStatus) -> List[str]:
@@ -90,7 +96,7 @@ def find_job_ids(job_status : JobStatus) -> List[str]:
 	job_ids = []
 
 	for job_path in job_paths:
-		job_id, _ = os.path.splitext(os.path.basename(job_path))
+		job_id = get_file_name(job_path)
 		job_ids.append(job_id)
 	return job_ids
 
@@ -182,7 +188,6 @@ def set_step_status(job_id : str, step_index : int, step_status : JobStepStatus)
 
 	if job:
 		steps = job.get('steps')
-
 		if has_step(job_id, step_index):
 			steps[step_index]['status'] = step_status
 			return update_job_file(job_id, job)

facefusion/jobs/job_runner.py

@@ -1,7 +1,7 @@
 from facefusion.ffmpeg import concat_video
-from facefusion.filesystem import is_image, is_video, move_file, remove_file
+from facefusion.filesystem import are_images, are_videos, move_file, remove_file
 from facefusion.jobs import job_helper, job_manager
-from facefusion.typing import JobOutputSet, JobStep, ProcessStep
+from facefusion.types import JobOutputSet, JobStep, ProcessStep
 
 
 def run_job(job_id : str, process_step : ProcessStep) -> bool:
@@ -16,14 +16,17 @@ def run_job(job_id : str, process_step : ProcessStep) -> bool:
 	return False
 
 
-def run_jobs(process_step : ProcessStep) -> bool:
+def run_jobs(process_step : ProcessStep, halt_on_error : bool) -> bool:
 	queued_job_ids = job_manager.find_job_ids('queued')
+	has_error = False
 
 	if queued_job_ids:
 		for job_id in queued_job_ids:
 			if not run_job(job_id, process_step):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
@@ -35,14 +38,17 @@ def retry_job(job_id : str, process_step : ProcessStep) -> bool:
 	return False
 
 
-def retry_jobs(process_step : ProcessStep) -> bool:
+def retry_jobs(process_step : ProcessStep, halt_on_error : bool) -> bool:
 	failed_job_ids = job_manager.find_job_ids('failed')
+	has_error = False
 
 	if failed_job_ids:
 		for job_id in failed_job_ids:
 			if not retry_job(job_id, process_step):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
@@ -73,10 +79,10 @@ def finalize_steps(job_id : str) -> bool:
 	output_set = collect_output_set(job_id)
 
 	for output_path, temp_output_paths in output_set.items():
-		if all(map(is_video, temp_output_paths)):
+		if are_videos(temp_output_paths):
 			if not concat_video(output_path, temp_output_paths):
 				return False
-		if any(map(is_image, temp_output_paths)):
+		if are_images(temp_output_paths):
 			for temp_output_path in temp_output_paths:
 				if not move_file(temp_output_path, output_path):
 					return False
@@ -95,12 +101,12 @@ def clean_steps(job_id: str) -> bool:
 
 def collect_output_set(job_id : str) -> JobOutputSet:
 	steps = job_manager.get_steps(job_id)
-	output_set : JobOutputSet = {}
+	job_output_set : JobOutputSet = {}
 
 	for index, step in enumerate(steps):
 		output_path = step.get('args').get('output_path')
 
 		if output_path:
 			step_output_path = job_manager.get_step_output_path(job_id, index, output_path)
-			output_set.setdefault(output_path, []).append(step_output_path)
-	return output_set
+			job_output_set.setdefault(output_path, []).append(step_output_path)
+	return job_output_set

facefusion/jobs/job_store.py

@@ -1,6 +1,6 @@
 from typing import List
 
-from facefusion.typing import JobStore
+from facefusion.types import JobStore
 
 JOB_STORE : JobStore =\
 {

facefusion/json.py

@@ -3,13 +3,13 @@ from json import JSONDecodeError
 from typing import Optional
 
 from facefusion.filesystem import is_file
-from facefusion.typing import Content
+from facefusion.types import Content
 
 
 def read_json(json_path : str) -> Optional[Content]:
 	if is_file(json_path):
 		try:
-			with open(json_path, 'r') as json_file:
+			with open(json_path) as json_file:
 				return json.load(json_file)
 		except JSONDecodeError:
 			pass

facefusion/logger.py

@@ -1,9 +1,8 @@
 from logging import Logger, basicConfig, getLogger
-from typing import Tuple
 
 import facefusion.choices
 from facefusion.common_helper import get_first, get_last
-from facefusion.typing import LogLevel, TableContents, TableHeaders
+from facefusion.types import LogLevel
 
 
 def init(log_level : LogLevel) -> None:
@@ -32,46 +31,15 @@ def error(message : str, module_name : str) -> None:
 
 
 def create_message(message : str, module_name : str) -> str:
-	scopes = module_name.split('.')
-	first_scope = get_first(scopes)
-	last_scope = get_last(scopes)
+	module_names = module_name.split('.')
+	first_module_name = get_first(module_names)
+	last_module_name = get_last(module_names)
 
-	if first_scope and last_scope:
-		return '[' + first_scope.upper() + '.' + last_scope.upper() + '] ' + message
+	if first_module_name and last_module_name:
+		return '[' + first_module_name.upper() + '.' + last_module_name.upper() + '] ' + message
 	return message
 
 
-def table(headers : TableHeaders, contents : TableContents) -> None:
-	package_logger = get_package_logger()
-	table_column, table_separator = create_table_parts(headers, contents)
-
-	package_logger.info(table_separator)
-	package_logger.info(table_column.format(*headers))
-	package_logger.info(table_separator)
-
-	for content in contents:
-		content = [ value if value else '' for value in content ]
-		package_logger.info(table_column.format(*content))
-
-	package_logger.info(table_separator)
-
-
-def create_table_parts(headers : TableHeaders, contents : TableContents) -> Tuple[str, str]:
-	column_parts = []
-	separator_parts = []
-	widths = [ len(header) for header in headers ]
-
-	for content in contents:
-		for index, value in enumerate(content):
-			widths[index] = max(widths[index], len(str(value)))
-
-	for width in widths:
-		column_parts.append('{:<' + str(width) + '}')
-		separator_parts.append('-' * width)
-
-	return '| ' + ' | '.join(column_parts) + ' |', '+-' + '-+-'.join(separator_parts) + '-+'
-
-
 def enable() -> None:
 	get_package_logger().disabled = False
 

facefusion/metadata.py

@@ -4,8 +4,8 @@ METADATA =\
 {
 	'name': 'FaceFusion',
 	'description': 'Industry leading face manipulation platform',
-	'version': '3.1.1',
-	'license': 'MIT',
+	'version': '3.4.1',
+	'license': 'OpenRAIL-AS',
 	'author': 'Henry Ruhs',
 	'url': 'https://facefusion.io'
 }

facefusion/model_helper.py

@@ -2,10 +2,10 @@ from functools import lru_cache
 
 import onnx
 
-from facefusion.typing import ModelInitializer
+from facefusion.types import ModelInitializer
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def get_static_model_initializer(model_path : str) -> ModelInitializer:
 	model = onnx.load(model_path)
 	return onnx.numpy_helper.to_array(model.graph.initializer[-1])

facefusion/normalizer.py

@@ -1,6 +1,6 @@
 from typing import List, Optional
 
-from facefusion.typing import Fps, Padding
+from facefusion.types import Fps, Padding
 
 
 def normalize_padding(padding : Optional[List[int]]) -> Optional[Padding]:

facefusion/process_manager.py

@@ -1,6 +1,4 @@
-from typing import Generator, List
-
-from facefusion.typing import ProcessState, QueuePayload
+from facefusion.types import ProcessState
 
 PROCESS_STATE : ProcessState = 'pending'
 
@@ -45,9 +43,3 @@ def stop() -> None:
 
 def end() -> None:
 	set_process_state('pending')
-
-
-def manage(queue_payloads : List[QueuePayload]) -> Generator[QueuePayload, None, None]:
-	for query_payload in queue_payloads:
-		if is_processing():
-			yield query_payload

facefusion/processors/choices.py

@@ -1,12 +1,13 @@
 from typing import List, Sequence
 
 from facefusion.common_helper import create_float_range, create_int_range
-from facefusion.filesystem import list_directory, resolve_relative_path
-from facefusion.processors.typing import AgeModifierModel, DeepSwapperModel, ExpressionRestorerModel, FaceDebuggerItem, FaceEditorModel, FaceEnhancerModel, FaceSwapperModel, FaceSwapperSet, FrameColorizerModel, FrameEnhancerModel, LipSyncerModel
+from facefusion.filesystem import get_file_name, resolve_file_paths, resolve_relative_path
+from facefusion.processors.types import AgeModifierModel, DeepSwapperModel, ExpressionRestorerArea, ExpressionRestorerModel, FaceDebuggerItem, FaceEditorModel, FaceEnhancerModel, FaceSwapperModel, FaceSwapperSet, FaceSwapperWeight, FrameColorizerModel, FrameEnhancerModel, LipSyncerModel
 
 age_modifier_models : List[AgeModifierModel] = [ 'styleganex_age' ]
 deep_swapper_models : List[DeepSwapperModel] =\
 [
+	'druuzil/adam_levine_320',
 	'druuzil/adrianne_palicki_384',
 	'druuzil/agnetha_falskog_224',
 	'druuzil/alan_ritchson_320',
@@ -14,6 +15,7 @@ deep_swapper_models : List[DeepSwapperModel] =\
 	'druuzil/amber_midthunder_320',
 	'druuzil/andras_arato_384',
 	'druuzil/andrew_tate_320',
+	'druuzil/angelina_jolie_384',
 	'druuzil/anne_hathaway_320',
 	'druuzil/anya_chalotra_320',
 	'druuzil/arnold_schwarzenegger_320',
@@ -21,6 +23,7 @@ deep_swapper_models : List[DeepSwapperModel] =\
 	'druuzil/benjamin_stiller_384',
 	'druuzil/bradley_pitt_224',
 	'druuzil/brie_larson_384',
+	'druuzil/bruce_campbell_384',
 	'druuzil/bryan_cranston_320',
 	'druuzil/catherine_blanchett_352',
 	'druuzil/christian_bale_320',
@@ -50,6 +53,7 @@ deep_swapper_models : List[DeepSwapperModel] =\
 	'druuzil/hugh_jackman_384',
 	'druuzil/idris_elba_320',
 	'druuzil/jack_nicholson_320',
+	'druuzil/james_carrey_384',
 	'druuzil/james_mcavoy_320',
 	'druuzil/james_varney_320',
 	'druuzil/jason_momoa_320',
@@ -61,6 +65,7 @@ deep_swapper_models : List[DeepSwapperModel] =\
 	'druuzil/kate_beckinsale_384',
 	'druuzil/laurence_fishburne_384',
 	'druuzil/lili_reinhart_320',
+	'druuzil/luke_evans_384',
 	'druuzil/mads_mikkelsen_384',
 	'druuzil/mary_winstead_320',
 	'druuzil/margaret_qualley_384',
@@ -69,12 +74,16 @@ deep_swapper_models : List[DeepSwapperModel] =\
 	'druuzil/michael_fox_320',
 	'druuzil/millie_bobby_brown_320',
 	'druuzil/morgan_freeman_320',
-	'druuzil/patrick_stewart_320',
+	'druuzil/patrick_stewart_224',
+	'druuzil/rachel_weisz_384',
 	'druuzil/rebecca_ferguson_320',
 	'druuzil/scarlett_johansson_320',
+	'druuzil/shannen_doherty_384',
 	'druuzil/seth_macfarlane_384',
 	'druuzil/thomas_cruise_320',
 	'druuzil/thomas_hanks_384',
+	'druuzil/william_murray_384',
+	'druuzil/zoe_saldana_384',
 	'edel/emma_roberts_224',
 	'edel/ivanka_trump_224',
 	'edel/lize_dzjabrailova_224',
@@ -157,16 +166,17 @@ deep_swapper_models : List[DeepSwapperModel] =\
 	'rumateus/taylor_swift_224'
 ]
 
-custom_model_files = list_directory(resolve_relative_path('../.assets/models/custom'))
+custom_model_file_paths = resolve_file_paths(resolve_relative_path('../.assets/models/custom'))
 
-if custom_model_files:
+if custom_model_file_paths:
 
-	for model_file in custom_model_files:
-		model_id = '/'.join([ 'custom', model_file.get('name') ])
+	for model_file_path in custom_model_file_paths:
+		model_id = '/'.join([ 'custom', get_file_name(model_file_path) ])
 		deep_swapper_models.append(model_id)
 
 expression_restorer_models : List[ExpressionRestorerModel] = [ 'live_portrait' ]
-face_debugger_items : List[FaceDebuggerItem] = [ 'bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask', 'face-detector-score', 'face-landmarker-score', 'age', 'gender', 'race' ]
+expression_restorer_areas : List[ExpressionRestorerArea] = [ 'upper-face', 'lower-face' ]
+face_debugger_items : List[FaceDebuggerItem] = [ 'bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask' ]
 face_editor_models : List[FaceEditorModel] = [ 'live_portrait' ]
 face_enhancer_models : List[FaceEnhancerModel] = [ 'codeformer', 'gfpgan_1.2', 'gfpgan_1.3', 'gfpgan_1.4', 'gpen_bfr_256', 'gpen_bfr_512', 'gpen_bfr_1024', 'gpen_bfr_2048', 'restoreformer_plus_plus' ]
 face_swapper_set : FaceSwapperSet =\
@@ -176,6 +186,9 @@ face_swapper_set : FaceSwapperSet =\
 	'ghost_2_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'ghost_3_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'hififace_unofficial_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hyperswap_1a_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hyperswap_1b_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hyperswap_1c_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'inswapper_128': [ '128x128', '256x256', '384x384', '512x512', '768x768', '1024x1024' ],
 	'inswapper_128_fp16': [ '128x128', '256x256', '384x384', '512x512', '768x768', '1024x1024' ],
 	'simswap_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
@@ -185,8 +198,8 @@ face_swapper_set : FaceSwapperSet =\
 face_swapper_models : List[FaceSwapperModel] = list(face_swapper_set.keys())
 frame_colorizer_models : List[FrameColorizerModel] = [ 'ddcolor', 'ddcolor_artistic', 'deoldify', 'deoldify_artistic', 'deoldify_stable' ]
 frame_colorizer_sizes : List[str] = [ '192x192', '256x256', '384x384', '512x512' ]
-frame_enhancer_models : List[FrameEnhancerModel] = [ 'clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'ultra_sharp_x4' ]
-lip_syncer_models : List[LipSyncerModel] = [ 'wav2lip_96', 'wav2lip_gan_96' ]
+frame_enhancer_models : List[FrameEnhancerModel] = [ 'clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'ultra_sharp_x4', 'ultra_sharp_2_x4' ]
+lip_syncer_models : List[LipSyncerModel] = [ 'edtalk_256', 'wav2lip_96', 'wav2lip_gan_96' ]
 
 age_modifier_direction_range : Sequence[int] = create_int_range(-100, 100, 1)
 deep_swapper_morph_range : Sequence[int] = create_int_range(0, 100, 1)
@@ -207,5 +220,7 @@ face_editor_head_yaw_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.0
 face_editor_head_roll_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
 face_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
 face_enhancer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
+face_swapper_weight_range : Sequence[FaceSwapperWeight] = create_float_range(0.0, 1.0, 0.05)
 frame_colorizer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
 frame_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
+lip_syncer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)

facefusion/processors/core.py

@@ -1,15 +1,9 @@
 import importlib
-import os
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from queue import Queue
 from types import ModuleType
 from typing import Any, List
 
-from tqdm import tqdm
-
-from facefusion import logger, state_manager, wording
+from facefusion import logger, wording
 from facefusion.exit_helper import hard_exit
-from facefusion.typing import ProcessFrames, QueuePayload
 
 PROCESSORS_METHODS =\
 [
@@ -20,11 +14,7 @@ PROCESSORS_METHODS =\
 	'pre_check',
 	'pre_process',
 	'post_process',
-	'get_reference_frame',
-	'process_frame',
-	'process_frames',
-	'process_image',
-	'process_video'
+	'process_frame'
 ]
 
 
@@ -51,49 +41,3 @@ def get_processors_modules(processors : List[str]) -> List[ModuleType]:
 		processor_module = load_processor_module(processor)
 		processor_modules.append(processor_module)
 	return processor_modules
-
-
-def multi_process_frames(source_paths : List[str], temp_frame_paths : List[str], process_frames : ProcessFrames) -> None:
-	queue_payloads = create_queue_payloads(temp_frame_paths)
-	with tqdm(total = len(queue_payloads), desc = wording.get('processing'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
-		progress.set_postfix(execution_providers = state_manager.get_item('execution_providers'))
-		with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
-			futures = []
-			queue : Queue[QueuePayload] = create_queue(queue_payloads)
-			queue_per_future = max(len(queue_payloads) // state_manager.get_item('execution_thread_count') * state_manager.get_item('execution_queue_count'), 1)
-
-			while not queue.empty():
-				future = executor.submit(process_frames, source_paths, pick_queue(queue, queue_per_future), progress.update)
-				futures.append(future)
-
-			for future_done in as_completed(futures):
-				future_done.result()
-
-
-def create_queue(queue_payloads : List[QueuePayload]) -> Queue[QueuePayload]:
-	queue : Queue[QueuePayload] = Queue()
-	for queue_payload in queue_payloads:
-		queue.put(queue_payload)
-	return queue
-
-
-def pick_queue(queue : Queue[QueuePayload], queue_per_future : int) -> List[QueuePayload]:
-	queues = []
-	for _ in range(queue_per_future):
-		if not queue.empty():
-			queues.append(queue.get())
-	return queues
-
-
-def create_queue_payloads(temp_frame_paths : List[str]) -> List[QueuePayload]:
-	queue_payloads = []
-	temp_frame_paths = sorted(temp_frame_paths, key = os.path.basename)
-
-	for frame_number, frame_path in enumerate(temp_frame_paths):
-		frame_payload : QueuePayload =\
-		{
-			'frame_number': frame_number,
-			'frame_path': frame_path
-		}
-		queue_payloads.append(frame_payload)
-	return queue_payloads

facefusion/processors/live_portrait.py

@@ -3,7 +3,7 @@ from typing import Tuple
 import numpy
 import scipy
 
-from facefusion.processors.typing import LivePortraitExpression, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitYaw
+from facefusion.processors.types import LivePortraitExpression, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitYaw
 
 EXPRESSION_MIN = numpy.array(
 [
@@ -63,15 +63,15 @@ def limit_expression(expression : LivePortraitExpression) -> LivePortraitExpress
 	return numpy.clip(expression, EXPRESSION_MIN, EXPRESSION_MAX)
 
 
-def limit_euler_angles(target_pitch : LivePortraitPitch, target_yaw : LivePortraitYaw, target_roll : LivePortraitRoll, output_pitch : LivePortraitPitch, output_yaw : LivePortraitYaw, output_roll : LivePortraitRoll) -> Tuple[LivePortraitPitch, LivePortraitYaw, LivePortraitRoll]:
-	pitch_min, pitch_max, yaw_min, yaw_max, roll_min, roll_max = calc_euler_limits(target_pitch, target_yaw, target_roll)
+def limit_angle(target_pitch : LivePortraitPitch, target_yaw : LivePortraitYaw, target_roll : LivePortraitRoll, output_pitch : LivePortraitPitch, output_yaw : LivePortraitYaw, output_roll : LivePortraitRoll) -> Tuple[LivePortraitPitch, LivePortraitYaw, LivePortraitRoll]:
+	pitch_min, pitch_max, yaw_min, yaw_max, roll_min, roll_max = calculate_euler_limits(target_pitch, target_yaw, target_roll)
 	output_pitch = numpy.clip(output_pitch, pitch_min, pitch_max)
 	output_yaw = numpy.clip(output_yaw, yaw_min, yaw_max)
 	output_roll = numpy.clip(output_roll, roll_min, roll_max)
 	return output_pitch, output_yaw, output_roll
 
 
-def calc_euler_limits(pitch : LivePortraitPitch, yaw : LivePortraitYaw, roll : LivePortraitRoll) -> Tuple[float, float, float, float, float, float]:
+def calculate_euler_limits(pitch : LivePortraitPitch, yaw : LivePortraitYaw, roll : LivePortraitRoll) -> Tuple[float, float, float, float, float, float]:
 	pitch_min = -30.0
 	pitch_max = 30.0
 	yaw_min = -60.0

facefusion/processors/modules/age_modifier.py

@@ -1,6 +1,5 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List
 
 import cv2
 import numpy
@@ -8,26 +7,24 @@ import numpy
 import facefusion.choices
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
-from facefusion.common_helper import create_int_metavar
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, wording
+from facefusion.common_helper import create_int_metavar, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import merge_matrix, paste_back, scale_face_landmark_5, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
+from facefusion.face_masker import create_box_mask, create_occlusion_mask
+from facefusion.face_selector import select_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import AgeModifierDirection, AgeModifierInputs
+from facefusion.processors.types import AgeModifierDirection, AgeModifierInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import match_frame_color, read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import match_frame_color, read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -64,24 +61,27 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('age_modifier_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('age_modifier_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	age_modifier_model = state_manager.get_item('age_modifier_model')
-	return create_static_model_set('full').get(age_modifier_model)
+	model_name = state_manager.get_item('age_modifier_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--age-modifier-model', help = wording.get('help.age_modifier_model'), default = config.get_str_value('processors.age_modifier_model', 'styleganex_age'), choices = processors_choices.age_modifier_models)
-		group_processors.add_argument('--age-modifier-direction', help = wording.get('help.age_modifier_direction'), type = int, default = config.get_int_value('processors.age_modifier_direction', '0'), choices = processors_choices.age_modifier_direction_range, metavar = create_int_metavar(processors_choices.age_modifier_direction_range))
+		group_processors.add_argument('--age-modifier-model', help = wording.get('help.age_modifier_model'), default = config.get_str_value('processors', 'age_modifier_model', 'styleganex_age'), choices = processors_choices.age_modifier_models)
+		group_processors.add_argument('--age-modifier-direction', help = wording.get('help.age_modifier_direction'), type = int, default = config.get_int_value('processors', 'age_modifier_direction', '0'), choices = processors_choices.age_modifier_direction_range, metavar = create_int_metavar(processors_choices.age_modifier_direction_range))
 		facefusion.jobs.job_store.register_step_keys([ 'age_modifier_model', 'age_modifier_direction' ])
 
 
@@ -91,10 +91,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -104,7 +104,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -112,6 +112,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -131,7 +133,7 @@ def modify_age(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFra
 	extend_face_landmark_5 = scale_face_landmark_5(face_landmark_5, 0.875)
 	extend_vision_frame, extend_affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, extend_face_landmark_5, model_templates.get('target_with_background'), model_sizes.get('target_with_background'))
 	extend_vision_frame_raw = extend_vision_frame.copy()
-	box_mask = create_static_box_mask(model_sizes.get('target_with_background'), state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(extend_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_masks =\
 	[
 		box_mask
@@ -139,13 +141,13 @@ def modify_age(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFra
 
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
 		occlusion_mask = create_occlusion_mask(crop_vision_frame)
-		combined_matrix = merge_matrix([ extend_affine_matrix, cv2.invertAffineTransform(affine_matrix) ])
-		occlusion_mask = cv2.warpAffine(occlusion_mask, combined_matrix, model_sizes.get('target_with_background'))
+		temp_matrix = merge_matrix([ extend_affine_matrix, cv2.invertAffineTransform(affine_matrix) ])
+		occlusion_mask = cv2.warpAffine(occlusion_mask, temp_matrix, model_sizes.get('target_with_background'))
 		crop_masks.append(occlusion_mask)
 
 	crop_vision_frame = prepare_vision_frame(crop_vision_frame)
 	extend_vision_frame = prepare_vision_frame(extend_vision_frame)
-	age_modifier_direction = numpy.array(numpy.interp(state_manager.get_item('age_modifier_direction'), [-100, 100], [2.5, -2.5])).astype(numpy.float32)
+	age_modifier_direction = numpy.array(numpy.interp(state_manager.get_item('age_modifier_direction'), [ -100, 100 ], [ 2.5, -2.5 ])).astype(numpy.float32)
 	extend_vision_frame = forward(crop_vision_frame, extend_vision_frame, age_modifier_direction)
 	extend_vision_frame = normalize_extend_frame(extend_vision_frame)
 	extend_vision_frame = match_frame_color(extend_vision_frame_raw, extend_vision_frame)
@@ -160,7 +162,7 @@ def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame,
 	age_modifier = get_inference_pool().get('age_modifier')
 	age_modifier_inputs = {}
 
-	if has_execution_provider('coreml'):
+	if is_macos() and has_execution_provider('coreml'):
 		age_modifier.set_providers([ facefusion.choices.execution_provider_set.get('cpu') ])
 
 	for age_modifier_input in age_modifier.get_inputs():
@@ -195,56 +197,15 @@ def normalize_extend_frame(extend_vision_frame : VisionFrame) -> VisionFrame:
 	return extend_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	return modify_age(target_face, temp_vision_frame)
-
-
 def process_frame(inputs : AgeModifierInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
+	reference_vision_frame = inputs.get('reference_vision_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = modify_age(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = modify_age(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = modify_age(similar_face, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = modify_age(target_face, temp_vision_frame)
 
-
-def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_path : str, target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)
+	return temp_vision_frame

facefusion/processors/modules/deep_swapper.py

@@ -1,6 +1,6 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List, Tuple
+from typing import Tuple
 
 import cv2
 import numpy
@@ -8,31 +8,30 @@ from cv2.typing import Size
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, wording
 from facefusion.common_helper import create_int_metavar
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_region_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
-from facefusion.filesystem import in_directory, is_image, is_video, list_directory, resolve_relative_path, same_file_extension
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
+from facefusion.face_selector import select_faces
+from facefusion.filesystem import get_file_name, in_directory, is_image, is_video, resolve_file_paths, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import DeepSwapperInputs, DeepSwapperMorph
+from facefusion.processors.types import DeepSwapperInputs, DeepSwapperMorph
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import conditional_match_frame_color, read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import conditional_match_frame_color, read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	model_config = []
 
 	if download_scope == 'full':
 		model_config.extend(
 		[
+			('druuzil', 'adam_levine_320'),
 			('druuzil', 'adrianne_palicki_384'),
 			('druuzil', 'agnetha_falskog_224'),
 			('druuzil', 'alan_ritchson_320'),
@@ -40,6 +39,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			('druuzil', 'amber_midthunder_320'),
 			('druuzil', 'andras_arato_384'),
 			('druuzil', 'andrew_tate_320'),
+			('druuzil', 'angelina_jolie_384'),
 			('druuzil', 'anne_hathaway_320'),
 			('druuzil', 'anya_chalotra_320'),
 			('druuzil', 'arnold_schwarzenegger_320'),
@@ -47,6 +47,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			('druuzil', 'benjamin_stiller_384'),
 			('druuzil', 'bradley_pitt_224'),
 			('druuzil', 'brie_larson_384'),
+			('druuzil', 'bruce_campbell_384'),
 			('druuzil', 'bryan_cranston_320'),
 			('druuzil', 'catherine_blanchett_352'),
 			('druuzil', 'christian_bale_320'),
@@ -76,6 +77,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			('druuzil', 'hugh_jackman_384'),
 			('druuzil', 'idris_elba_320'),
 			('druuzil', 'jack_nicholson_320'),
+			('druuzil', 'james_carrey_384'),
 			('druuzil', 'james_mcavoy_320'),
 			('druuzil', 'james_varney_320'),
 			('druuzil', 'jason_momoa_320'),
@@ -87,6 +89,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			('druuzil', 'kate_beckinsale_384'),
 			('druuzil', 'laurence_fishburne_384'),
 			('druuzil', 'lili_reinhart_320'),
+			('druuzil', 'luke_evans_384'),
 			('druuzil', 'mads_mikkelsen_384'),
 			('druuzil', 'mary_winstead_320'),
 			('druuzil', 'margaret_qualley_384'),
@@ -95,12 +98,16 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			('druuzil', 'michael_fox_320'),
 			('druuzil', 'millie_bobby_brown_320'),
 			('druuzil', 'morgan_freeman_320'),
-			('druuzil', 'patrick_stewart_320'),
+			('druuzil', 'patrick_stewart_224'),
+			('druuzil', 'rachel_weisz_384'),
 			('druuzil', 'rebecca_ferguson_320'),
 			('druuzil', 'scarlett_johansson_320'),
+			('druuzil', 'shannen_doherty_384'),
 			('druuzil', 'seth_macfarlane_384'),
 			('druuzil', 'thomas_cruise_320'),
 			('druuzil', 'thomas_hanks_384'),
+			('druuzil', 'william_murray_384'),
+			('druuzil', 'zoe_saldana_384'),
 			('edel', 'emma_roberts_224'),
 			('edel', 'ivanka_trump_224'),
 			('edel', 'lize_dzjabrailova_224'),
@@ -216,12 +223,12 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			'template': 'dfl_whole_face'
 		}
 
-	custom_model_files = list_directory(resolve_relative_path('../.assets/models/custom'))
+	custom_model_file_paths = resolve_file_paths(resolve_relative_path('../.assets/models/custom'))
 
-	if custom_model_files:
+	if custom_model_file_paths:
 
-		for model_file in custom_model_files:
-			model_id = '/'.join([ 'custom', model_file.get('name') ])
+		for model_file_path in custom_model_file_paths:
+			model_id = '/'.join([ 'custom', get_file_name(model_file_path) ])
 
 			model_set[model_id] =\
 			{
@@ -229,7 +236,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				{
 					'deep_swapper':
 					{
-						'path': resolve_relative_path(model_file.get('path'))
+						'path': resolve_relative_path(model_file_path)
 					}
 				},
 				'template': 'dfl_whole_face'
@@ -239,33 +246,37 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('deep_swapper_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('deep_swapper_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	deep_swapper_model = state_manager.get_item('deep_swapper_model')
-	return create_static_model_set('full').get(deep_swapper_model)
+	model_name = state_manager.get_item('deep_swapper_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def get_model_size() -> Size:
 	deep_swapper = get_inference_pool().get('deep_swapper')
-	deep_swapper_outputs = deep_swapper.get_outputs()
 
-	for deep_swapper_output in deep_swapper_outputs:
-		return deep_swapper_output.shape[1:3]
+	for deep_swapper_input in deep_swapper.get_inputs():
+		if deep_swapper_input.name == 'in_face:0':
+			return deep_swapper_input.shape[1:3]
+
 	return 0, 0
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--deep-swapper-model', help = wording.get('help.deep_swapper_model'), default = config.get_str_value('processors.deep_swapper_model', 'iperov/elon_musk_224'), choices = processors_choices.deep_swapper_models)
-		group_processors.add_argument('--deep-swapper-morph', help = wording.get('help.deep_swapper_morph'), type = int, default = config.get_int_value('processors.deep_swapper_morph', '80'), choices = processors_choices.deep_swapper_morph_range, metavar = create_int_metavar(processors_choices.deep_swapper_morph_range))
+		group_processors.add_argument('--deep-swapper-model', help = wording.get('help.deep_swapper_model'), default = config.get_str_value('processors', 'deep_swapper_model', 'iperov/elon_musk_224'), choices = processors_choices.deep_swapper_models)
+		group_processors.add_argument('--deep-swapper-morph', help = wording.get('help.deep_swapper_morph'), type = int, default = config.get_int_value('processors', 'deep_swapper_morph', '100'), choices = processors_choices.deep_swapper_morph_range, metavar = create_int_metavar(processors_choices.deep_swapper_morph_range))
 		facefusion.jobs.job_store.register_step_keys([ 'deep_swapper_model', 'deep_swapper_morph' ])
 
 
@@ -275,11 +286,11 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	if model_hashes and model_sources:
-		return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	if model_hash_set and model_source_set:
+		return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 	return True
 
 
@@ -290,7 +301,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -298,6 +309,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -314,7 +327,7 @@ def swap_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFram
 	model_size = get_model_size()
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
 	crop_vision_frame_raw = crop_vision_frame.copy()
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
+	box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
 	crop_masks =\
 	[
 		box_mask
@@ -331,6 +344,11 @@ def swap_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFram
 	crop_vision_frame = conditional_match_frame_color(crop_vision_frame_raw, crop_vision_frame)
 	crop_masks.append(prepare_crop_mask(crop_source_mask, crop_target_mask))
 
+	if 'area' in state_manager.get_item('face_mask_types'):
+		face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, state_manager.get_item('face_mask_areas'))
+		crop_masks.append(area_mask)
+
 	if 'region' in state_manager.get_item('face_mask_types'):
 		region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
 		crop_masks.append(region_mask)
@@ -362,6 +380,7 @@ def has_morph_input() -> bool:
 	for deep_swapper_input in deep_swapper.get_inputs():
 		if deep_swapper_input.name == 'morph_value:0':
 			return True
+
 	return False
 
 
@@ -389,56 +408,17 @@ def prepare_crop_mask(crop_source_mask : Mask, crop_target_mask : Mask) -> Mask:
 	return crop_mask
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	return swap_face(target_face, temp_vision_frame)
-
-
 def process_frame(inputs : DeepSwapperInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
+	reference_vision_frame = inputs.get('reference_vision_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = swap_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = swap_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = swap_face(similar_face, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = swap_face(target_face, temp_vision_frame)
+
+	return temp_vision_frame
 
 
-def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_path : str, target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)

facefusion/processors/modules/expression_restorer.py

@@ -1,33 +1,30 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List, Tuple
+from typing import Tuple
 
 import cv2
 import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, wording
 from facefusion.common_helper import create_int_metavar
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
+from facefusion.face_masker import create_box_mask, create_occlusion_mask
+from facefusion.face_selector import select_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.live_portrait import create_rotation, limit_expression
-from facefusion.processors.typing import ExpressionRestorerInputs
-from facefusion.processors.typing import LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
+from facefusion.processors.types import ExpressionRestorerInputs, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore, thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import get_video_frame, read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -69,44 +66,49 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/live_portrait_generator.onnx')
 				}
 			},
-			'template': 'arcface_128_v2',
+			'template': 'arcface_128',
 			'size': (512, 512)
 		}
 	}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('expression_restorer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('expression_restorer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	expression_restorer_model = state_manager.get_item('expression_restorer_model')
-	return create_static_model_set('full').get(expression_restorer_model)
+	model_name = state_manager.get_item('expression_restorer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--expression-restorer-model', help = wording.get('help.expression_restorer_model'), default = config.get_str_value('processors.expression_restorer_model', 'live_portrait'), choices = processors_choices.expression_restorer_models)
-		group_processors.add_argument('--expression-restorer-factor', help = wording.get('help.expression_restorer_factor'), type = int, default = config.get_int_value('processors.expression_restorer_factor', '80'), choices = processors_choices.expression_restorer_factor_range, metavar = create_int_metavar(processors_choices.expression_restorer_factor_range))
-		facefusion.jobs.job_store.register_step_keys([ 'expression_restorer_model','expression_restorer_factor' ])
+		group_processors.add_argument('--expression-restorer-model', help = wording.get('help.expression_restorer_model'), default = config.get_str_value('processors', 'expression_restorer_model', 'live_portrait'), choices = processors_choices.expression_restorer_models)
+		group_processors.add_argument('--expression-restorer-factor', help = wording.get('help.expression_restorer_factor'), type = int, default = config.get_int_value('processors', 'expression_restorer_factor', '80'), choices = processors_choices.expression_restorer_factor_range, metavar = create_int_metavar(processors_choices.expression_restorer_factor_range))
+		group_processors.add_argument('--expression-restorer-areas', help = wording.get('help.expression_restorer_areas').format(choices = ', '.join(processors_choices.expression_restorer_areas)), default = config.get_str_list('processors', 'expression_restorer_areas', ' '.join(processors_choices.expression_restorer_areas)), choices = processors_choices.expression_restorer_areas, nargs = '+', metavar = 'EXPRESSION_RESTORER_AREAS')
+		facefusion.jobs.job_store.register_step_keys([ 'expression_restorer_model', 'expression_restorer_factor', 'expression_restorer_areas' ])
 
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('expression_restorer_model', args.get('expression_restorer_model'))
 	apply_state_item('expression_restorer_factor', args.get('expression_restorer_factor'))
+	apply_state_item('expression_restorer_areas', args.get('expression_restorer_areas'))
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -119,7 +121,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -127,6 +129,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -138,46 +142,58 @@ def post_process() -> None:
 		face_recognizer.clear_inference_pool()
 
 
-def restore_expression(source_vision_frame : VisionFrame, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+def restore_expression(target_face : Face, target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
 	model_template = get_model_options().get('template')
 	model_size = get_model_options().get('size')
 	expression_restorer_factor = float(numpy.interp(float(state_manager.get_item('expression_restorer_factor')), [ 0, 100 ], [ 0, 1.2 ]))
-	source_vision_frame = cv2.resize(source_vision_frame, temp_vision_frame.shape[:2][::-1])
-	source_crop_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
-	target_crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
-	box_mask = create_static_box_mask(target_crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	target_crop_vision_frame, _ = warp_face_by_face_landmark_5(target_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
+	temp_crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
+	box_mask = create_box_mask(temp_crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_masks =\
 	[
 		box_mask
 	]
 
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
-		occlusion_mask = create_occlusion_mask(target_crop_vision_frame)
+		occlusion_mask = create_occlusion_mask(temp_crop_vision_frame)
 		crop_masks.append(occlusion_mask)
 
-	source_crop_vision_frame = prepare_crop_frame(source_crop_vision_frame)
 	target_crop_vision_frame = prepare_crop_frame(target_crop_vision_frame)
-	target_crop_vision_frame = apply_restore(source_crop_vision_frame, target_crop_vision_frame, expression_restorer_factor)
-	target_crop_vision_frame = normalize_crop_frame(target_crop_vision_frame)
+	temp_crop_vision_frame = prepare_crop_frame(temp_crop_vision_frame)
+	temp_crop_vision_frame = apply_restore(target_crop_vision_frame, temp_crop_vision_frame, expression_restorer_factor)
+	temp_crop_vision_frame = normalize_crop_frame(temp_crop_vision_frame)
 	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
-	temp_vision_frame = paste_back(temp_vision_frame, target_crop_vision_frame, crop_mask, affine_matrix)
-	return temp_vision_frame
+	paste_vision_frame = paste_back(temp_vision_frame, temp_crop_vision_frame, crop_mask, affine_matrix)
+	return paste_vision_frame
 
 
-def apply_restore(source_crop_vision_frame : VisionFrame, target_crop_vision_frame : VisionFrame, expression_restorer_factor : float) -> VisionFrame:
-	feature_volume = forward_extract_feature(target_crop_vision_frame)
-	source_expression = forward_extract_motion(source_crop_vision_frame)[5]
-	pitch, yaw, roll, scale, translation, target_expression, motion_points = forward_extract_motion(target_crop_vision_frame)
+def apply_restore(target_crop_vision_frame : VisionFrame, temp_crop_vision_frame : VisionFrame, expression_restorer_factor : float) -> VisionFrame:
+	feature_volume = forward_extract_feature(temp_crop_vision_frame)
+	target_expression = forward_extract_motion(target_crop_vision_frame)[5]
+	pitch, yaw, roll, scale, translation, temp_expression, motion_points = forward_extract_motion(temp_crop_vision_frame)
 	rotation = create_rotation(pitch, yaw, roll)
-	source_expression[:, [ 0, 4, 5, 8, 9 ]] = target_expression[:, [ 0, 4, 5, 8, 9 ]]
-	source_expression = source_expression * expression_restorer_factor + target_expression * (1 - expression_restorer_factor)
-	source_expression = limit_expression(source_expression)
-	source_motion_points = scale * (motion_points @ rotation.T + source_expression) + translation
+	target_expression = restrict_expression_areas(temp_expression, target_expression)
+	target_expression = target_expression * expression_restorer_factor + temp_expression * (1 - expression_restorer_factor)
+	target_expression = limit_expression(target_expression)
 	target_motion_points = scale * (motion_points @ rotation.T + target_expression) + translation
-	crop_vision_frame = forward_generate_frame(feature_volume, source_motion_points, target_motion_points)
+	temp_motion_points = scale * (motion_points @ rotation.T + temp_expression) + translation
+	crop_vision_frame = forward_generate_frame(feature_volume, target_motion_points, temp_motion_points)
 	return crop_vision_frame
 
 
+def restrict_expression_areas(temp_expression : LivePortraitExpression, target_expression : LivePortraitExpression) -> LivePortraitExpression:
+	expression_restorer_areas = state_manager.get_item('expression_restorer_areas')
+
+	if 'upper-face' not in expression_restorer_areas:
+		target_expression[:, [1, 2, 6, 10, 11, 12, 13, 15, 16]] = temp_expression[:, [1, 2, 6, 10, 11, 12, 13, 15, 16]]
+
+	if 'lower-face' not in expression_restorer_areas:
+		target_expression[:, [3, 7, 14, 17, 18, 19, 20]] = temp_expression[:, [3, 7, 14, 17, 18, 19, 20]]
+
+	target_expression[:, [0, 4, 5, 8, 9]] = temp_expression[:, [0, 4, 5, 8, 9]]
+	return target_expression
+
+
 def forward_extract_feature(crop_vision_frame : VisionFrame) -> LivePortraitFeatureVolume:
 	feature_extractor = get_inference_pool().get('feature_extractor')
 
@@ -202,15 +218,15 @@ def forward_extract_motion(crop_vision_frame : VisionFrame) -> Tuple[LivePortrai
 	return pitch, yaw, roll, scale, translation, expression, motion_points
 
 
-def forward_generate_frame(feature_volume : LivePortraitFeatureVolume, source_motion_points : LivePortraitMotionPoints, target_motion_points : LivePortraitMotionPoints) -> VisionFrame:
+def forward_generate_frame(feature_volume : LivePortraitFeatureVolume, target_motion_points : LivePortraitMotionPoints, temp_motion_points : LivePortraitMotionPoints) -> VisionFrame:
 	generator = get_inference_pool().get('generator')
 
 	with thread_semaphore():
 		crop_vision_frame = generator.run(None,
 		{
 			'feature_volume': feature_volume,
-			'source': source_motion_points,
-			'target': target_motion_points
+			'source': target_motion_points,
+			'target': temp_motion_points
 		})[0][0]
 
 	return crop_vision_frame
@@ -232,64 +248,15 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	return crop_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	pass
-
-
 def process_frame(inputs : ExpressionRestorerInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
-	source_vision_frame = inputs.get('source_vision_frame')
+	reference_vision_frame = inputs.get('reference_vision_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = restore_expression(source_vision_frame, target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = restore_expression(source_vision_frame, target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = restore_expression(source_vision_frame, similar_face, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = restore_expression(target_face, target_vision_frame, temp_vision_frame)
 
-
-def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		frame_number = queue_payload.get('frame_number')
-		if state_manager.get_item('trim_frame_start'):
-			frame_number += state_manager.get_item('trim_frame_start')
-		source_vision_frame = get_video_frame(state_manager.get_item('target_path'), frame_number)
-		target_vision_path = queue_payload.get('frame_path')
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'source_vision_frame': source_vision_frame,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_path : str, target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	source_vision_frame = read_static_image(state_manager.get_item('target_path'))
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'source_vision_frame': source_vision_frame,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)
+	return temp_vision_frame

facefusion/processors/modules/face_debugger.py

@@ -1,24 +1,21 @@
 from argparse import ArgumentParser
-from typing import List
 
 import cv2
 import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, process_manager, state_manager, wording
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, state_manager, video_manager, wording
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_region_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
-from facefusion.filesystem import in_directory, same_file_extension
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
+from facefusion.face_selector import select_faces
+from facefusion.filesystem import in_directory, is_image, is_video, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FaceDebuggerInputs
+from facefusion.processors.types import FaceDebuggerInputs
 from facefusion.program_helper import find_argument_group
-from facefusion.typing import ApplyStateItem, Args, Face, InferencePool, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, Face, InferencePool, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_frame
 
 
 def get_inference_pool() -> InferencePool:
@@ -32,7 +29,7 @@ def clear_inference_pool() -> None:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-debugger-items', help = wording.get('help.face_debugger_items').format(choices = ', '.join(processors_choices.face_debugger_items)), default = config.get_str_list('processors.face_debugger_items', 'face-landmark-5/68 face-mask'), choices = processors_choices.face_debugger_items, nargs = '+', metavar = 'FACE_DEBUGGER_ITEMS')
+		group_processors.add_argument('--face-debugger-items', help = wording.get('help.face_debugger_items').format(choices = ', '.join(processors_choices.face_debugger_items)), default = config.get_str_list('processors', 'face_debugger_items', 'face-landmark-5/68 face-mask'), choices = processors_choices.face_debugger_items, nargs = '+', metavar = 'FACE_DEBUGGER_ITEMS')
 		facefusion.jobs.job_store.register_step_keys([ 'face_debugger_items' ])
 
 
@@ -45,10 +42,13 @@ def pre_check() -> bool:
 
 
 def pre_process(mode : ProcessMode) -> bool:
+	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
+		logger.error(wording.get('choose_image_or_video_target') + wording.get('exclamation_mark'), __name__)
+		return False
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -56,6 +56,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
 		content_analyser.clear_inference_pool()
 		face_classifier.clear_inference_pool()
@@ -66,157 +68,160 @@ def post_process() -> None:
 
 
 def debug_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	primary_color = (0, 0, 255)
-	primary_light_color = (100, 100, 255)
-	secondary_color = (0, 255, 0)
-	tertiary_color = (255, 255, 0)
-	bounding_box = target_face.bounding_box.astype(numpy.int32)
-	temp_vision_frame = temp_vision_frame.copy()
-	has_face_landmark_5_fallback = numpy.array_equal(target_face.landmark_set.get('5'), target_face.landmark_set.get('5/68'))
-	has_face_landmark_68_fallback = numpy.array_equal(target_face.landmark_set.get('68'), target_face.landmark_set.get('68/5'))
 	face_debugger_items = state_manager.get_item('face_debugger_items')
 
 	if 'bounding-box' in face_debugger_items:
-		x1, y1, x2, y2 = bounding_box
-		cv2.rectangle(temp_vision_frame, (x1, y1), (x2, y2), primary_color, 2)
-
-		if target_face.angle == 0:
-			cv2.line(temp_vision_frame, (x1, y1), (x2, y1), primary_light_color, 3)
-		elif target_face.angle == 180:
-			cv2.line(temp_vision_frame, (x1, y2), (x2, y2), primary_light_color, 3)
-		elif target_face.angle == 90:
-			cv2.line(temp_vision_frame, (x2, y1), (x2, y2), primary_light_color, 3)
-		elif target_face.angle == 270:
-			cv2.line(temp_vision_frame, (x1, y1), (x1, y2), primary_light_color, 3)
+		temp_vision_frame = draw_bounding_box(target_face, temp_vision_frame)
 
 	if 'face-mask' in face_debugger_items:
-		crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), 'arcface_128_v2', (512, 512))
-		inverse_matrix = cv2.invertAffineTransform(affine_matrix)
-		temp_size = temp_vision_frame.shape[:2][::-1]
-		crop_masks = []
+		temp_vision_frame = draw_face_mask(target_face, temp_vision_frame)
 
-		if 'box' in state_manager.get_item('face_mask_types'):
-			box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], 0, state_manager.get_item('face_mask_padding'))
-			crop_masks.append(box_mask)
+	if 'face-landmark-5' in face_debugger_items:
+		temp_vision_frame = draw_face_landmark_5(target_face, temp_vision_frame)
 
-		if 'occlusion' in state_manager.get_item('face_mask_types'):
-			occlusion_mask = create_occlusion_mask(crop_vision_frame)
-			crop_masks.append(occlusion_mask)
+	if 'face-landmark-5/68' in face_debugger_items:
+		temp_vision_frame = draw_face_landmark_5_68(target_face, temp_vision_frame)
 
-		if 'region' in state_manager.get_item('face_mask_types'):
-			region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
-			crop_masks.append(region_mask)
+	if 'face-landmark-68' in face_debugger_items:
+		temp_vision_frame = draw_face_landmark_68(target_face, temp_vision_frame)
 
-		crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
-		crop_mask = (crop_mask * 255).astype(numpy.uint8)
-		inverse_vision_frame = cv2.warpAffine(crop_mask, inverse_matrix, temp_size)
-		inverse_vision_frame = cv2.threshold(inverse_vision_frame, 100, 255, cv2.THRESH_BINARY)[1]
-		inverse_vision_frame[inverse_vision_frame > 0] = 255 #type:ignore[operator]
-		inverse_contours = cv2.findContours(inverse_vision_frame, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)[0]
-		cv2.drawContours(temp_vision_frame, inverse_contours, -1, tertiary_color if has_face_landmark_5_fallback else secondary_color, 2)
-
-	if 'face-landmark-5' in face_debugger_items and numpy.any(target_face.landmark_set.get('5')):
-		face_landmark_5 = target_face.landmark_set.get('5').astype(numpy.int32)
-		for index in range(face_landmark_5.shape[0]):
-			cv2.circle(temp_vision_frame, (face_landmark_5[index][0], face_landmark_5[index][1]), 3, primary_color, -1)
-
-	if 'face-landmark-5/68' in face_debugger_items and numpy.any(target_face.landmark_set.get('5/68')):
-		face_landmark_5_68 = target_face.landmark_set.get('5/68').astype(numpy.int32)
-		for index in range(face_landmark_5_68.shape[0]):
-			cv2.circle(temp_vision_frame, (face_landmark_5_68[index][0], face_landmark_5_68[index][1]), 3, tertiary_color if has_face_landmark_5_fallback else secondary_color, -1)
-
-	if 'face-landmark-68' in face_debugger_items and numpy.any(target_face.landmark_set.get('68')):
-		face_landmark_68 = target_face.landmark_set.get('68').astype(numpy.int32)
-		for index in range(face_landmark_68.shape[0]):
-			cv2.circle(temp_vision_frame, (face_landmark_68[index][0], face_landmark_68[index][1]), 3, tertiary_color if has_face_landmark_68_fallback else secondary_color, -1)
-
-	if 'face-landmark-68/5' in face_debugger_items and numpy.any(target_face.landmark_set.get('68')):
-		face_landmark_68 = target_face.landmark_set.get('68/5').astype(numpy.int32)
-		for index in range(face_landmark_68.shape[0]):
-			cv2.circle(temp_vision_frame, (face_landmark_68[index][0], face_landmark_68[index][1]), 3, tertiary_color, -1)
-
-	if bounding_box[3] - bounding_box[1] > 50 and bounding_box[2] - bounding_box[0] > 50:
-		top = bounding_box[1]
-		left = bounding_box[0] - 20
-
-		if 'face-detector-score' in face_debugger_items:
-			face_score_text = str(round(target_face.score_set.get('detector'), 2))
-			top = top + 20
-			cv2.putText(temp_vision_frame, face_score_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
-
-		if 'face-landmarker-score' in face_debugger_items:
-			face_score_text = str(round(target_face.score_set.get('landmarker'), 2))
-			top = top + 20
-			cv2.putText(temp_vision_frame, face_score_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, tertiary_color if has_face_landmark_5_fallback else secondary_color, 2)
-
-		if 'age' in face_debugger_items:
-			face_age_text = str(target_face.age.start) + '-' + str(target_face.age.stop)
-			top = top + 20
-			cv2.putText(temp_vision_frame, face_age_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
-
-		if 'gender' in face_debugger_items:
-			face_gender_text = target_face.gender
-			top = top + 20
-			cv2.putText(temp_vision_frame, face_gender_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
-
-		if 'race' in face_debugger_items:
-			face_race_text = target_face.race
-			top = top + 20
-			cv2.putText(temp_vision_frame, face_race_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
+	if 'face-landmark-68/5' in face_debugger_items:
+		temp_vision_frame = draw_face_landmark_68_5(target_face, temp_vision_frame)
 
 	return temp_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	pass
+def draw_bounding_box(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	box_color = 0, 0, 255
+	border_color = 100, 100, 255
+	bounding_box = target_face.bounding_box.astype(numpy.int32)
+	x1, y1, x2, y2 = bounding_box
+
+	cv2.rectangle(temp_vision_frame, (x1, y1), (x2, y2), box_color, 2)
+
+	if target_face.angle == 0:
+		cv2.line(temp_vision_frame, (x1, y1), (x2, y1), border_color, 3)
+	if target_face.angle == 180:
+		cv2.line(temp_vision_frame, (x1, y2), (x2, y2), border_color, 3)
+	if target_face.angle == 90:
+		cv2.line(temp_vision_frame, (x2, y1), (x2, y2), border_color, 3)
+	if target_face.angle == 270:
+		cv2.line(temp_vision_frame, (x1, y1), (x1, y2), border_color, 3)
+
+	return temp_vision_frame
+
+
+def draw_face_mask(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	crop_masks = []
+	face_landmark_5 = target_face.landmark_set.get('5')
+	face_landmark_68 = target_face.landmark_set.get('68')
+	face_landmark_5_68 = target_face.landmark_set.get('5/68')
+	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5_68, 'arcface_128', (512, 512))
+	inverse_matrix = cv2.invertAffineTransform(affine_matrix)
+	temp_size = temp_vision_frame.shape[:2][::-1]
+	mask_color = 0, 255, 0
+
+	if numpy.array_equal(face_landmark_5, face_landmark_5_68):
+		mask_color = 255, 255, 0
+
+	if 'box' in state_manager.get_item('face_mask_types'):
+		box_mask = create_box_mask(crop_vision_frame, 0, state_manager.get_item('face_mask_padding'))
+		crop_masks.append(box_mask)
+
+	if 'occlusion' in state_manager.get_item('face_mask_types'):
+		occlusion_mask = create_occlusion_mask(crop_vision_frame)
+		crop_masks.append(occlusion_mask)
+
+	if 'area' in state_manager.get_item('face_mask_types'):
+		face_landmark_68 = cv2.transform(face_landmark_68.reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, state_manager.get_item('face_mask_areas'))
+		crop_masks.append(area_mask)
+
+	if 'region' in state_manager.get_item('face_mask_types'):
+		region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
+		crop_masks.append(region_mask)
+
+	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
+	crop_mask = (crop_mask * 255).astype(numpy.uint8)
+	inverse_vision_frame = cv2.warpAffine(crop_mask, inverse_matrix, temp_size)
+	inverse_vision_frame = cv2.threshold(inverse_vision_frame, 100, 255, cv2.THRESH_BINARY)[1]
+	inverse_contours, _ = cv2.findContours(inverse_vision_frame, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+	cv2.drawContours(temp_vision_frame, inverse_contours, -1, mask_color, 2)
+
+	return temp_vision_frame
+
+
+def draw_face_landmark_5(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	face_landmark_5 = target_face.landmark_set.get('5')
+	point_color = 0, 0, 255
+
+	if numpy.any(face_landmark_5):
+		face_landmark_5 = face_landmark_5.astype(numpy.int32)
+
+		for point in face_landmark_5:
+			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+
+	return temp_vision_frame
+
+
+def draw_face_landmark_5_68(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	face_landmark_5 = target_face.landmark_set.get('5')
+	face_landmark_5_68 = target_face.landmark_set.get('5/68')
+	point_color = 0, 255, 0
+
+	if numpy.array_equal(face_landmark_5, face_landmark_5_68):
+		point_color = 255, 255, 0
+
+	if numpy.any(face_landmark_5_68):
+		face_landmark_5_68 = face_landmark_5_68.astype(numpy.int32)
+
+		for point in face_landmark_5_68:
+			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+
+	return temp_vision_frame
+
+
+def draw_face_landmark_68(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	face_landmark_68 = target_face.landmark_set.get('68')
+	face_landmark_68_5 = target_face.landmark_set.get('68/5')
+	point_color = 0, 255, 0
+
+	if numpy.array_equal(face_landmark_68, face_landmark_68_5):
+		point_color = 255, 255, 0
+
+	if numpy.any(face_landmark_68):
+		face_landmark_68 = face_landmark_68.astype(numpy.int32)
+
+		for point in face_landmark_68:
+			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+
+	return temp_vision_frame
+
+
+def draw_face_landmark_68_5(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	face_landmark_68_5 = target_face.landmark_set.get('68/5')
+	point_color = 255, 255, 0
+
+	if numpy.any(face_landmark_68_5):
+		face_landmark_68_5 = face_landmark_68_5.astype(numpy.int32)
+
+		for point in face_landmark_68_5:
+			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+
+	return temp_vision_frame
 
 
 def process_frame(inputs : FaceDebuggerInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
+	reference_vision_frame = inputs.get('reference_vision_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = debug_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = debug_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = debug_face(similar_face, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = debug_face(target_face, temp_vision_frame)
+
+	return temp_vision_frame
 
 
-def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(source_paths, temp_frame_paths, process_frames)

facefusion/processors/modules/face_editor.py

@@ -1,32 +1,30 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List, Tuple
+from typing import Tuple
 
 import cv2
 import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, wording
 from facefusion.common_helper import create_float_metavar
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import paste_back, scale_face_landmark_5, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
+from facefusion.face_masker import create_box_mask
+from facefusion.face_selector import select_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.live_portrait import create_rotation, limit_euler_angles, limit_expression
-from facefusion.processors.typing import FaceEditorInputs, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
+from facefusion.processors.live_portrait import create_rotation, limit_angle, limit_expression
+from facefusion.processors.types import FaceEditorInputs, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore, thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, FaceLandmark68, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, FaceLandmark68, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -105,37 +103,40 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('face_editor_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('face_editor_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	face_editor_model = state_manager.get_item('face_editor_model')
-	return create_static_model_set('full').get(face_editor_model)
+	model_name = state_manager.get_item('face_editor_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-editor-model', help = wording.get('help.face_editor_model'), default = config.get_str_value('processors.face_editor_model', 'live_portrait'), choices = processors_choices.face_editor_models)
-		group_processors.add_argument('--face-editor-eyebrow-direction', help = wording.get('help.face_editor_eyebrow_direction'), type = float, default = config.get_float_value('processors.face_editor_eyebrow_direction', '0'), choices = processors_choices.face_editor_eyebrow_direction_range, metavar = create_float_metavar(processors_choices.face_editor_eyebrow_direction_range))
-		group_processors.add_argument('--face-editor-eye-gaze-horizontal', help = wording.get('help.face_editor_eye_gaze_horizontal'), type = float, default = config.get_float_value('processors.face_editor_eye_gaze_horizontal', '0'), choices = processors_choices.face_editor_eye_gaze_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_horizontal_range))
-		group_processors.add_argument('--face-editor-eye-gaze-vertical', help = wording.get('help.face_editor_eye_gaze_vertical'), type = float, default = config.get_float_value('processors.face_editor_eye_gaze_vertical', '0'), choices = processors_choices.face_editor_eye_gaze_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_vertical_range))
-		group_processors.add_argument('--face-editor-eye-open-ratio', help = wording.get('help.face_editor_eye_open_ratio'), type = float, default = config.get_float_value('processors.face_editor_eye_open_ratio', '0'), choices = processors_choices.face_editor_eye_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_eye_open_ratio_range))
-		group_processors.add_argument('--face-editor-lip-open-ratio', help = wording.get('help.face_editor_lip_open_ratio'), type = float, default = config.get_float_value('processors.face_editor_lip_open_ratio', '0'), choices = processors_choices.face_editor_lip_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_lip_open_ratio_range))
-		group_processors.add_argument('--face-editor-mouth-grim', help = wording.get('help.face_editor_mouth_grim'), type = float, default = config.get_float_value('processors.face_editor_mouth_grim', '0'), choices = processors_choices.face_editor_mouth_grim_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_grim_range))
-		group_processors.add_argument('--face-editor-mouth-pout', help = wording.get('help.face_editor_mouth_pout'), type = float, default = config.get_float_value('processors.face_editor_mouth_pout', '0'), choices = processors_choices.face_editor_mouth_pout_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_pout_range))
-		group_processors.add_argument('--face-editor-mouth-purse', help = wording.get('help.face_editor_mouth_purse'), type = float, default = config.get_float_value('processors.face_editor_mouth_purse', '0'), choices = processors_choices.face_editor_mouth_purse_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_purse_range))
-		group_processors.add_argument('--face-editor-mouth-smile', help = wording.get('help.face_editor_mouth_smile'), type = float, default = config.get_float_value('processors.face_editor_mouth_smile', '0'), choices = processors_choices.face_editor_mouth_smile_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_smile_range))
-		group_processors.add_argument('--face-editor-mouth-position-horizontal', help = wording.get('help.face_editor_mouth_position_horizontal'), type = float, default = config.get_float_value('processors.face_editor_mouth_position_horizontal', '0'), choices = processors_choices.face_editor_mouth_position_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_horizontal_range))
-		group_processors.add_argument('--face-editor-mouth-position-vertical', help = wording.get('help.face_editor_mouth_position_vertical'), type = float, default = config.get_float_value('processors.face_editor_mouth_position_vertical', '0'), choices = processors_choices.face_editor_mouth_position_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_vertical_range))
-		group_processors.add_argument('--face-editor-head-pitch', help = wording.get('help.face_editor_head_pitch'), type = float, default = config.get_float_value('processors.face_editor_head_pitch', '0'), choices = processors_choices.face_editor_head_pitch_range, metavar = create_float_metavar(processors_choices.face_editor_head_pitch_range))
-		group_processors.add_argument('--face-editor-head-yaw', help = wording.get('help.face_editor_head_yaw'), type = float, default = config.get_float_value('processors.face_editor_head_yaw', '0'), choices = processors_choices.face_editor_head_yaw_range, metavar = create_float_metavar(processors_choices.face_editor_head_yaw_range))
-		group_processors.add_argument('--face-editor-head-roll', help = wording.get('help.face_editor_head_roll'), type = float, default = config.get_float_value('processors.face_editor_head_roll', '0'), choices = processors_choices.face_editor_head_roll_range, metavar = create_float_metavar(processors_choices.face_editor_head_roll_range))
+		group_processors.add_argument('--face-editor-model', help = wording.get('help.face_editor_model'), default = config.get_str_value('processors', 'face_editor_model', 'live_portrait'), choices = processors_choices.face_editor_models)
+		group_processors.add_argument('--face-editor-eyebrow-direction', help = wording.get('help.face_editor_eyebrow_direction'), type = float, default = config.get_float_value('processors', 'face_editor_eyebrow_direction', '0'), choices = processors_choices.face_editor_eyebrow_direction_range, metavar = create_float_metavar(processors_choices.face_editor_eyebrow_direction_range))
+		group_processors.add_argument('--face-editor-eye-gaze-horizontal', help = wording.get('help.face_editor_eye_gaze_horizontal'), type = float, default = config.get_float_value('processors', 'face_editor_eye_gaze_horizontal', '0'), choices = processors_choices.face_editor_eye_gaze_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_horizontal_range))
+		group_processors.add_argument('--face-editor-eye-gaze-vertical', help = wording.get('help.face_editor_eye_gaze_vertical'), type = float, default = config.get_float_value('processors', 'face_editor_eye_gaze_vertical', '0'), choices = processors_choices.face_editor_eye_gaze_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_vertical_range))
+		group_processors.add_argument('--face-editor-eye-open-ratio', help = wording.get('help.face_editor_eye_open_ratio'), type = float, default = config.get_float_value('processors', 'face_editor_eye_open_ratio', '0'), choices = processors_choices.face_editor_eye_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_eye_open_ratio_range))
+		group_processors.add_argument('--face-editor-lip-open-ratio', help = wording.get('help.face_editor_lip_open_ratio'), type = float, default = config.get_float_value('processors', 'face_editor_lip_open_ratio', '0'), choices = processors_choices.face_editor_lip_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_lip_open_ratio_range))
+		group_processors.add_argument('--face-editor-mouth-grim', help = wording.get('help.face_editor_mouth_grim'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_grim', '0'), choices = processors_choices.face_editor_mouth_grim_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_grim_range))
+		group_processors.add_argument('--face-editor-mouth-pout', help = wording.get('help.face_editor_mouth_pout'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_pout', '0'), choices = processors_choices.face_editor_mouth_pout_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_pout_range))
+		group_processors.add_argument('--face-editor-mouth-purse', help = wording.get('help.face_editor_mouth_purse'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_purse', '0'), choices = processors_choices.face_editor_mouth_purse_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_purse_range))
+		group_processors.add_argument('--face-editor-mouth-smile', help = wording.get('help.face_editor_mouth_smile'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_smile', '0'), choices = processors_choices.face_editor_mouth_smile_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_smile_range))
+		group_processors.add_argument('--face-editor-mouth-position-horizontal', help = wording.get('help.face_editor_mouth_position_horizontal'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_position_horizontal', '0'), choices = processors_choices.face_editor_mouth_position_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_horizontal_range))
+		group_processors.add_argument('--face-editor-mouth-position-vertical', help = wording.get('help.face_editor_mouth_position_vertical'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_position_vertical', '0'), choices = processors_choices.face_editor_mouth_position_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_vertical_range))
+		group_processors.add_argument('--face-editor-head-pitch', help = wording.get('help.face_editor_head_pitch'), type = float, default = config.get_float_value('processors', 'face_editor_head_pitch', '0'), choices = processors_choices.face_editor_head_pitch_range, metavar = create_float_metavar(processors_choices.face_editor_head_pitch_range))
+		group_processors.add_argument('--face-editor-head-yaw', help = wording.get('help.face_editor_head_yaw'), type = float, default = config.get_float_value('processors', 'face_editor_head_yaw', '0'), choices = processors_choices.face_editor_head_yaw_range, metavar = create_float_metavar(processors_choices.face_editor_head_yaw_range))
+		group_processors.add_argument('--face-editor-head-roll', help = wording.get('help.face_editor_head_roll'), type = float, default = config.get_float_value('processors', 'face_editor_head_roll', '0'), choices = processors_choices.face_editor_head_roll_range, metavar = create_float_metavar(processors_choices.face_editor_head_roll_range))
 		facefusion.jobs.job_store.register_step_keys([ 'face_editor_model', 'face_editor_eyebrow_direction', 'face_editor_eye_gaze_horizontal', 'face_editor_eye_gaze_vertical', 'face_editor_eye_open_ratio', 'face_editor_lip_open_ratio', 'face_editor_mouth_grim', 'face_editor_mouth_pout', 'face_editor_mouth_purse', 'face_editor_mouth_smile', 'face_editor_mouth_position_horizontal', 'face_editor_mouth_position_vertical', 'face_editor_head_pitch', 'face_editor_head_yaw', 'face_editor_head_roll' ])
 
 
@@ -158,10 +159,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -171,7 +172,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -179,6 +180,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -195,12 +198,12 @@ def edit_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFram
 	model_size = get_model_options().get('size')
 	face_landmark_5 = scale_face_landmark_5(target_face.landmark_set.get('5/68'), 1.5)
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_template, model_size)
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_vision_frame = prepare_crop_frame(crop_vision_frame)
 	crop_vision_frame = apply_edit(crop_vision_frame, target_face.landmark_set.get('68'))
 	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
-	temp_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, box_mask, affine_matrix)
-	return temp_vision_frame
+	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, box_mask, affine_matrix)
+	return paste_vision_frame
 
 
 def apply_edit(crop_vision_frame : VisionFrame, face_landmark_68 : FaceLandmark68) -> VisionFrame:
@@ -338,8 +341,8 @@ def edit_eye_gaze(expression : LivePortraitExpression) -> LivePortraitExpression
 
 def edit_eye_open(motion_points : LivePortraitMotionPoints, face_landmark_68 : FaceLandmark68) -> LivePortraitMotionPoints:
 	face_editor_eye_open_ratio = state_manager.get_item('face_editor_eye_open_ratio')
-	left_eye_ratio = calc_distance_ratio(face_landmark_68, 37, 40, 39, 36)
-	right_eye_ratio = calc_distance_ratio(face_landmark_68, 43, 46, 45, 42)
+	left_eye_ratio = calculate_distance_ratio(face_landmark_68, 37, 40, 39, 36)
+	right_eye_ratio = calculate_distance_ratio(face_landmark_68, 43, 46, 45, 42)
 
 	if face_editor_eye_open_ratio < 0:
 		eye_motion_points = numpy.concatenate([ motion_points.ravel(), [ left_eye_ratio, right_eye_ratio, 0.0 ] ])
@@ -353,14 +356,14 @@ def edit_eye_open(motion_points : LivePortraitMotionPoints, face_landmark_68 : F
 
 def edit_lip_open(motion_points : LivePortraitMotionPoints, face_landmark_68 : FaceLandmark68) -> LivePortraitMotionPoints:
 	face_editor_lip_open_ratio = state_manager.get_item('face_editor_lip_open_ratio')
-	lip_ratio = calc_distance_ratio(face_landmark_68, 62, 66, 54, 48)
+	lip_ratio = calculate_distance_ratio(face_landmark_68, 62, 66, 54, 48)
 
 	if face_editor_lip_open_ratio < 0:
 		lip_motion_points = numpy.concatenate([ motion_points.ravel(), [ lip_ratio, 0.0 ] ])
 	else:
 		lip_motion_points = numpy.concatenate([ motion_points.ravel(), [ lip_ratio, 1.0 ] ])
 	lip_motion_points = lip_motion_points.reshape(1, -1).astype(numpy.float32)
-	lip_motion_points = forward_retarget_lip(lip_motion_points)	* numpy.abs(face_editor_lip_open_ratio)
+	lip_motion_points = forward_retarget_lip(lip_motion_points) * numpy.abs(face_editor_lip_open_ratio)
 	lip_motion_points = lip_motion_points.reshape(-1, 21, 3)
 	return lip_motion_points
 
@@ -446,12 +449,12 @@ def edit_head_rotation(pitch : LivePortraitPitch, yaw : LivePortraitYaw, roll :
 	edit_pitch = pitch + float(numpy.interp(face_editor_head_pitch, [ -1, 1 ], [ 20, -20 ]))
 	edit_yaw = yaw + float(numpy.interp(face_editor_head_yaw, [ -1, 1 ], [ 60, -60 ]))
 	edit_roll = roll + float(numpy.interp(face_editor_head_roll, [ -1, 1 ], [ -15, 15 ]))
-	edit_pitch, edit_yaw, edit_roll = limit_euler_angles(pitch, yaw, roll, edit_pitch, edit_yaw, edit_roll)
+	edit_pitch, edit_yaw, edit_roll = limit_angle(pitch, yaw, roll, edit_pitch, edit_yaw, edit_roll)
 	rotation = create_rotation(edit_pitch, edit_yaw, edit_roll)
 	return rotation
 
 
-def calc_distance_ratio(face_landmark_68 : FaceLandmark68, top_index : int, bottom_index : int, left_index : int, right_index : int) -> float:
+def calculate_distance_ratio(face_landmark_68 : FaceLandmark68, top_index : int, bottom_index : int, left_index : int, right_index : int) -> float:
 	vertical_direction = face_landmark_68[top_index] - face_landmark_68[bottom_index]
 	horizontal_direction = face_landmark_68[left_index] - face_landmark_68[right_index]
 	distance_ratio = float(numpy.linalg.norm(vertical_direction) / (numpy.linalg.norm(horizontal_direction) + 1e-6))
@@ -474,56 +477,15 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	return crop_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	pass
-
-
 def process_frame(inputs : FaceEditorInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
+	reference_vision_frame = inputs.get('reference_vision_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = edit_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = edit_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = edit_face(similar_face, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = edit_face(target_face, temp_vision_frame)
 
-
-def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_path : str, target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)
+	return temp_vision_frame

facefusion/processors/modules/face_enhancer.py

@@ -1,31 +1,27 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List
 
-import cv2
 import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, wording
 from facefusion.common_helper import create_float_metavar, create_int_metavar
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
+from facefusion.face_masker import create_box_mask, create_occlusion_mask
+from facefusion.face_selector import select_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FaceEnhancerInputs, FaceEnhancerWeight
+from facefusion.processors.types import FaceEnhancerInputs, FaceEnhancerWeight
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import blend_frame, read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -131,7 +127,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/gpen_bfr_256.onnx')
 				}
 			},
-			'template': 'arcface_128_v2',
+			'template': 'arcface_128',
 			'size': (256, 256)
 		},
 		'gpen_bfr_512':
@@ -222,25 +218,28 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('face_enhancer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('face_enhancer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	face_enhancer_model = state_manager.get_item('face_enhancer_model')
-	return create_static_model_set('full').get(face_enhancer_model)
+	model_name = state_manager.get_item('face_enhancer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-enhancer-model', help = wording.get('help.face_enhancer_model'), default = config.get_str_value('processors.face_enhancer_model', 'gfpgan_1.4'), choices = processors_choices.face_enhancer_models)
-		group_processors.add_argument('--face-enhancer-blend', help = wording.get('help.face_enhancer_blend'), type = int, default = config.get_int_value('processors.face_enhancer_blend', '80'), choices = processors_choices.face_enhancer_blend_range, metavar = create_int_metavar(processors_choices.face_enhancer_blend_range))
-		group_processors.add_argument('--face-enhancer-weight', help = wording.get('help.face_enhancer_weight'), type = float, default = config.get_float_value('processors.face_enhancer_weight', '1.0'), choices = processors_choices.face_enhancer_weight_range, metavar = create_float_metavar(processors_choices.face_enhancer_weight_range))
+		group_processors.add_argument('--face-enhancer-model', help = wording.get('help.face_enhancer_model'), default = config.get_str_value('processors', 'face_enhancer_model', 'gfpgan_1.4'), choices = processors_choices.face_enhancer_models)
+		group_processors.add_argument('--face-enhancer-blend', help = wording.get('help.face_enhancer_blend'), type = int, default = config.get_int_value('processors', 'face_enhancer_blend', '80'), choices = processors_choices.face_enhancer_blend_range, metavar = create_int_metavar(processors_choices.face_enhancer_blend_range))
+		group_processors.add_argument('--face-enhancer-weight', help = wording.get('help.face_enhancer_weight'), type = float, default = config.get_float_value('processors', 'face_enhancer_weight', '0.5'), choices = processors_choices.face_enhancer_weight_range, metavar = create_float_metavar(processors_choices.face_enhancer_weight_range))
 		facefusion.jobs.job_store.register_step_keys([ 'face_enhancer_model', 'face_enhancer_blend', 'face_enhancer_weight' ])
 
 
@@ -251,10 +250,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -264,7 +263,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -272,6 +271,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -287,7 +288,7 @@ def enhance_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionF
 	model_template = get_model_options().get('template')
 	model_size = get_model_options().get('size')
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_masks =\
 	[
 		box_mask
@@ -303,7 +304,7 @@ def enhance_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionF
 	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
 	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
 	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
-	temp_vision_frame = blend_frame(temp_vision_frame, paste_vision_frame)
+	temp_vision_frame = blend_paste_frame(temp_vision_frame, paste_vision_frame)
 	return temp_vision_frame
 
 
@@ -329,6 +330,7 @@ def has_weight_input() -> bool:
 	for deep_swapper_input in face_enhancer.get_inputs():
 		if deep_swapper_input.name == 'weight':
 			return True
+
 	return False
 
 
@@ -348,62 +350,21 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	return crop_vision_frame
 
 
-def blend_frame(temp_vision_frame : VisionFrame, paste_vision_frame : VisionFrame) -> VisionFrame:
+def blend_paste_frame(temp_vision_frame : VisionFrame, paste_vision_frame : VisionFrame) -> VisionFrame:
 	face_enhancer_blend = 1 - (state_manager.get_item('face_enhancer_blend') / 100)
-	temp_vision_frame = cv2.addWeighted(temp_vision_frame, face_enhancer_blend, paste_vision_frame, 1 - face_enhancer_blend, 0)
+	temp_vision_frame = blend_frame(temp_vision_frame, paste_vision_frame, 1 - face_enhancer_blend)
 	return temp_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	return enhance_face(target_face, temp_vision_frame)
-
-
 def process_frame(inputs : FaceEnhancerInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
+	reference_vision_frame = inputs.get('reference_vision_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = enhance_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = enhance_face(target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = enhance_face(similar_face, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = enhance_face(target_face, temp_vision_frame)
 
-
-def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_path : str, target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)
+	return temp_vision_frame

facefusion/processors/modules/face_swapper.py

@@ -1,34 +1,33 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List, Tuple
+from typing import List, Optional, Tuple
 
+import cv2
 import numpy
 
 import facefusion.choices
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
-from facefusion.common_helper import get_first
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, wording
+from facefusion.common_helper import get_first, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
-from facefusion.face_analyser import get_average_face, get_many_faces, get_one_face
+from facefusion.face_analyser import get_average_face, get_many_faces, get_one_face, scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_region_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces, sort_faces_by_order
-from facefusion.face_store import get_reference_faces
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
+from facefusion.face_selector import select_faces, sort_faces_by_order
 from facefusion.filesystem import filter_image_paths, has_image, in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.model_helper import get_static_model_initializer
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.pixel_boost import explode_pixel_boost, implode_pixel_boost
-from facefusion.processors.typing import FaceSwapperInputs
+from facefusion.processors.types import FaceSwapperInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Embedding, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, read_static_images, unpack_resolution, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Embedding, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_images, read_static_video_frame, unpack_resolution
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -67,8 +66,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.hash'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
+					'url': resolve_download_url('models-3.4.0', 'crossface_ghost.hash'),
+					'path': resolve_relative_path('../.assets/models/crossface_ghost.hash')
 				}
 			},
 			'sources':
@@ -80,8 +79,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.onnx'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
+					'url': resolve_download_url('models-3.4.0', 'crossface_ghost.onnx'),
+					'path': resolve_relative_path('../.assets/models/crossface_ghost.onnx')
 				}
 			},
 			'type': 'ghost',
@@ -101,8 +100,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.hash'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
+					'url': resolve_download_url('models-3.4.0', 'crossface_ghost.hash'),
+					'path': resolve_relative_path('../.assets/models/crossface_ghost.hash')
 				}
 			},
 			'sources':
@@ -114,8 +113,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.onnx'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
+					'url': resolve_download_url('models-3.4.0', 'crossface_ghost.onnx'),
+					'path': resolve_relative_path('../.assets/models/crossface_ghost.onnx')
 				}
 			},
 			'type': 'ghost',
@@ -135,8 +134,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.hash'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
+					'url': resolve_download_url('models-3.4.0', 'crossface_ghost.hash'),
+					'path': resolve_relative_path('../.assets/models/crossface_ghost.hash')
 				}
 			},
 			'sources':
@@ -148,8 +147,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.onnx'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
+					'url': resolve_download_url('models-3.4.0', 'crossface_ghost.onnx'),
+					'path': resolve_relative_path('../.assets/models/crossface_ghost.onnx')
 				}
 			},
 			'type': 'ghost',
@@ -169,8 +168,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.1.0', 'arcface_converter_hififace.hash'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_hififace.hash')
+					'url': resolve_download_url('models-3.4.0', 'crossface_hififace.hash'),
+					'path': resolve_relative_path('../.assets/models/crossface_hififace.hash')
 				}
 			},
 			'sources':
@@ -182,8 +181,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.1.0', 'arcface_converter_hififace.onnx'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_hififace.onnx')
+					'url': resolve_download_url('models-3.4.0', 'crossface_hififace.onnx'),
+					'path': resolve_relative_path('../.assets/models/crossface_hififace.onnx')
 				}
 			},
 			'type': 'hififace',
@@ -192,6 +191,78 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			'mean': [ 0.5, 0.5, 0.5 ],
 			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
+		'hyperswap_1a_256':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1a_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1a_256.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1a_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1a_256.onnx')
+				}
+			},
+			'type': 'hyperswap',
+			'template': 'arcface_128',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
+		},
+		'hyperswap_1b_256':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1b_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1b_256.hash')
+				}
+			},
+			'sources':
+				{
+					'face_swapper':
+					{
+						'url': resolve_download_url('models-3.3.0', 'hyperswap_1b_256.onnx'),
+						'path': resolve_relative_path('../.assets/models/hyperswap_1b_256.onnx')
+					}
+				},
+			'type': 'hyperswap',
+			'template': 'arcface_128',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
+		},
+		'hyperswap_1c_256':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1c_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1c_256.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1c_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1c_256.onnx')
+				}
+			},
+			'type': 'hyperswap',
+			'template': 'arcface_128',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
+		},
 		'inswapper_128':
 		{
 			'hashes':
@@ -211,7 +282,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				}
 			},
 			'type': 'inswapper',
-			'template': 'arcface_128_v2',
+			'template': 'arcface_128',
 			'size': (128, 128),
 			'mean': [ 0.0, 0.0, 0.0 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -235,7 +306,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				}
 			},
 			'type': 'inswapper',
-			'template': 'arcface_128_v2',
+			'template': 'arcface_128',
 			'size': (128, 128),
 			'mean': [ 0.0, 0.0, 0.0 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -251,8 +322,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.hash'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.hash')
+					'url': resolve_download_url('models-3.4.0', 'crossface_simswap.hash'),
+					'path': resolve_relative_path('../.assets/models/crossface_simswap.hash')
 				}
 			},
 			'sources':
@@ -264,8 +335,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.onnx'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.onnx')
+					'url': resolve_download_url('models-3.4.0', 'crossface_simswap.onnx'),
+					'path': resolve_relative_path('../.assets/models/crossface_simswap.onnx')
 				}
 			},
 			'type': 'simswap',
@@ -285,8 +356,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.hash'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.hash')
+					'url': resolve_download_url('models-3.4.0', 'crossface_simswap.hash'),
+					'path': resolve_relative_path('../.assets/models/crossface_simswap.hash')
 				}
 			},
 			'sources':
@@ -298,8 +369,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 				},
 				'embedding_converter':
 				{
-					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.onnx'),
-					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.onnx')
+					'url': resolve_download_url('models-3.4.0', 'crossface_simswap.onnx'),
+					'path': resolve_relative_path('../.assets/models/crossface_simswap.onnx')
 				}
 			},
 			'type': 'simswap',
@@ -336,71 +407,89 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ get_model_name() ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ get_model_name() ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	face_swapper_model = state_manager.get_item('face_swapper_model')
+	model_name = get_model_name()
+	return create_static_model_set('full').get(model_name)
 
-	if has_execution_provider('coreml') and face_swapper_model == 'inswapper_128_fp16':
-		return create_static_model_set('full').get('inswapper_128')
-	return create_static_model_set('full').get(face_swapper_model)
+
+def get_model_name() -> str:
+	model_name = state_manager.get_item('face_swapper_model')
+
+	if is_macos() and has_execution_provider('coreml') and model_name == 'inswapper_128_fp16':
+		return 'inswapper_128'
+	return model_name
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-swapper-model', help = wording.get('help.face_swapper_model'), default = config.get_str_value('processors.face_swapper_model', 'inswapper_128_fp16'), choices = processors_choices.face_swapper_models)
+		group_processors.add_argument('--face-swapper-model', help = wording.get('help.face_swapper_model'), default = config.get_str_value('processors', 'face_swapper_model', 'hyperswap_1a_256'), choices = processors_choices.face_swapper_models)
 		known_args, _ = program.parse_known_args()
 		face_swapper_pixel_boost_choices = processors_choices.face_swapper_set.get(known_args.face_swapper_model)
-		group_processors.add_argument('--face-swapper-pixel-boost', help = wording.get('help.face_swapper_pixel_boost'), default = config.get_str_value('processors.face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices)), choices = face_swapper_pixel_boost_choices)
-		facefusion.jobs.job_store.register_step_keys([ 'face_swapper_model', 'face_swapper_pixel_boost' ])
+		group_processors.add_argument('--face-swapper-pixel-boost', help = wording.get('help.face_swapper_pixel_boost'), default = config.get_str_value('processors', 'face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices)), choices = face_swapper_pixel_boost_choices)
+		group_processors.add_argument('--face-swapper-weight', help = wording.get('help.face_swapper_weight'), type = float, default = config.get_float_value('processors', 'face_swapper_weight', '0.5'), choices = processors_choices.face_swapper_weight_range)
+		facefusion.jobs.job_store.register_step_keys([ 'face_swapper_model', 'face_swapper_pixel_boost', 'face_swapper_weight' ])
 
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_swapper_model', args.get('face_swapper_model'))
 	apply_state_item('face_swapper_pixel_boost', args.get('face_swapper_pixel_boost'))
+	apply_state_item('face_swapper_weight', args.get('face_swapper_weight'))
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
 	if not has_image(state_manager.get_item('source_paths')):
 		logger.error(wording.get('choose_image_source') + wording.get('exclamation_mark'), __name__)
 		return False
+
 	source_image_paths = filter_image_paths(state_manager.get_item('source_paths'))
 	source_frames = read_static_images(source_image_paths)
 	source_faces = get_many_faces(source_frames)
+
 	if not get_one_face(source_faces):
 		logger.error(wording.get('no_source_face_detected') + wording.get('exclamation_mark'), __name__)
 		return False
+
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(wording.get('choose_image_or_video_target') + wording.get('exclamation_mark'), __name__)
 		return False
+
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
+
 	return True
 
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
-		clear_inference_pool()
 		get_static_model_initializer.cache_clear()
+		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
 		content_analyser.clear_inference_pool()
 		face_classifier.clear_inference_pool()
@@ -420,7 +509,7 @@ def swap_face(source_face : Face, target_face : Face, temp_vision_frame : Vision
 	crop_masks = []
 
 	if 'box' in state_manager.get_item('face_mask_types'):
-		box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
+		box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
 		crop_masks.append(box_mask)
 
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
@@ -430,26 +519,31 @@ def swap_face(source_face : Face, target_face : Face, temp_vision_frame : Vision
 	pixel_boost_vision_frames = implode_pixel_boost(crop_vision_frame, pixel_boost_total, model_size)
 	for pixel_boost_vision_frame in pixel_boost_vision_frames:
 		pixel_boost_vision_frame = prepare_crop_frame(pixel_boost_vision_frame)
-		pixel_boost_vision_frame = forward_swap_face(source_face, pixel_boost_vision_frame)
+		pixel_boost_vision_frame = forward_swap_face(source_face, target_face, pixel_boost_vision_frame)
 		pixel_boost_vision_frame = normalize_crop_frame(pixel_boost_vision_frame)
 		temp_vision_frames.append(pixel_boost_vision_frame)
 	crop_vision_frame = explode_pixel_boost(temp_vision_frames, pixel_boost_total, model_size, pixel_boost_size)
 
+	if 'area' in state_manager.get_item('face_mask_types'):
+		face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, state_manager.get_item('face_mask_areas'))
+		crop_masks.append(area_mask)
+
 	if 'region' in state_manager.get_item('face_mask_types'):
 		region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
 		crop_masks.append(region_mask)
 
 	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
-	temp_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
-	return temp_vision_frame
+	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
+	return paste_vision_frame
 
 
-def forward_swap_face(source_face : Face, crop_vision_frame : VisionFrame) -> VisionFrame:
+def forward_swap_face(source_face : Face, target_face : Face, crop_vision_frame : VisionFrame) -> VisionFrame:
 	face_swapper = get_inference_pool().get('face_swapper')
 	model_type = get_model_options().get('type')
 	face_swapper_inputs = {}
 
-	if has_execution_provider('coreml') and model_type in [ 'ghost', 'uniface' ]:
+	if is_macos() and has_execution_provider('coreml') and model_type in [ 'ghost', 'uniface' ]:
 		face_swapper.set_providers([ facefusion.choices.execution_provider_set.get('cpu') ])
 
 	for face_swapper_input in face_swapper.get_inputs():
@@ -457,7 +551,9 @@ def forward_swap_face(source_face : Face, crop_vision_frame : VisionFrame) -> Vi
 			if model_type in [ 'blendswap', 'uniface' ]:
 				face_swapper_inputs[face_swapper_input.name] = prepare_source_frame(source_face)
 			else:
-				face_swapper_inputs[face_swapper_input.name] = prepare_source_embedding(source_face)
+				source_embedding = prepare_source_embedding(source_face)
+				source_embedding = balance_source_embedding(source_embedding, target_face.embedding)
+				face_swapper_inputs[face_swapper_input.name] = source_embedding
 		if face_swapper_input.name == 'target':
 			face_swapper_inputs[face_swapper_input.name] = crop_vision_frame
 
@@ -467,16 +563,16 @@ def forward_swap_face(source_face : Face, crop_vision_frame : VisionFrame) -> Vi
 	return crop_vision_frame
 
 
-def forward_convert_embedding(embedding : Embedding) -> Embedding:
+def forward_convert_embedding(face_embedding : Embedding) -> Embedding:
 	embedding_converter = get_inference_pool().get('embedding_converter')
 
 	with conditional_thread_semaphore():
-		embedding = embedding_converter.run(None,
+		face_embedding = embedding_converter.run(None,
 		{
-			'input': embedding
+			'input': face_embedding
 		})[0]
 
-	return embedding
+	return face_embedding
 
 
 def prepare_source_frame(source_face : Face) -> VisionFrame:
@@ -485,8 +581,10 @@ def prepare_source_frame(source_face : Face) -> VisionFrame:
 
 	if model_type == 'blendswap':
 		source_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, source_face.landmark_set.get('5/68'), 'arcface_112_v2', (112, 112))
+
 	if model_type == 'uniface':
 		source_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, source_face.landmark_set.get('5/68'), 'ffhq_512', (256, 256))
+
 	source_vision_frame = source_vision_frame[:, :, ::-1] / 255.0
 	source_vision_frame = source_vision_frame.transpose(2, 0, 1)
 	source_vision_frame = numpy.expand_dims(source_vision_frame, axis = 0).astype(numpy.float32)
@@ -497,25 +595,47 @@ def prepare_source_embedding(source_face : Face) -> Embedding:
 	model_type = get_model_options().get('type')
 
 	if model_type == 'ghost':
-		source_embedding, _ = convert_embedding(source_face)
+		source_embedding = source_face.embedding.reshape(-1, 512)
+		source_embedding, _ = convert_source_embedding(source_embedding)
 		source_embedding = source_embedding.reshape(1, -1)
-	elif model_type == 'inswapper':
+		return source_embedding
+
+	if model_type == 'hyperswap':
+		source_embedding = source_face.embedding_norm.reshape((1, -1))
+		return source_embedding
+
+	if model_type == 'inswapper':
 		model_path = get_model_options().get('sources').get('face_swapper').get('path')
 		model_initializer = get_static_model_initializer(model_path)
 		source_embedding = source_face.embedding.reshape((1, -1))
 		source_embedding = numpy.dot(source_embedding, model_initializer) / numpy.linalg.norm(source_embedding)
-	else:
-		_, source_normed_embedding = convert_embedding(source_face)
-		source_embedding = source_normed_embedding.reshape(1, -1)
+		return source_embedding
+
+	source_embedding = source_face.embedding.reshape(-1, 512)
+	_, source_embedding_norm = convert_source_embedding(source_embedding)
+	source_embedding = source_embedding_norm.reshape(1, -1)
 	return source_embedding
 
 
-def convert_embedding(source_face : Face) -> Tuple[Embedding, Embedding]:
-	embedding = source_face.embedding.reshape(-1, 512)
-	embedding = forward_convert_embedding(embedding)
-	embedding = embedding.ravel()
-	normed_embedding = embedding / numpy.linalg.norm(embedding)
-	return embedding, normed_embedding
+def balance_source_embedding(source_embedding : Embedding, target_embedding : Embedding) -> Embedding:
+	model_type = get_model_options().get('type')
+	face_swapper_weight = state_manager.get_item('face_swapper_weight')
+	face_swapper_weight = numpy.interp(face_swapper_weight, [ 0, 1 ], [ 0.35, -0.35 ]).astype(numpy.float32)
+
+	if model_type in [ 'hififace', 'hyperswap', 'inswapper', 'simswap' ]:
+		target_embedding = target_embedding / numpy.linalg.norm(target_embedding)
+
+	source_embedding = source_embedding.reshape(1, -1)
+	target_embedding = target_embedding.reshape(1, -1)
+	source_embedding = source_embedding * (1 - face_swapper_weight) + target_embedding * face_swapper_weight
+	return source_embedding
+
+
+def convert_source_embedding(source_embedding : Embedding) -> Tuple[Embedding, Embedding]:
+	source_embedding = forward_convert_embedding(source_embedding)
+	source_embedding = source_embedding.ravel()
+	source_embedding_norm = source_embedding / numpy.linalg.norm(source_embedding)
+	return source_embedding, source_embedding_norm
 
 
 def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
@@ -535,84 +655,40 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	model_standard_deviation = get_model_options().get('standard_deviation')
 
 	crop_vision_frame = crop_vision_frame.transpose(1, 2, 0)
-	if model_type in [ 'ghost', 'hififace', 'uniface' ]:
+
+	if model_type in [ 'ghost', 'hififace', 'hyperswap', 'uniface' ]:
 		crop_vision_frame = crop_vision_frame * model_standard_deviation + model_mean
+
 	crop_vision_frame = crop_vision_frame.clip(0, 1)
 	crop_vision_frame = crop_vision_frame[:, :, ::-1] * 255
 	return crop_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	return swap_face(source_face, target_face, temp_vision_frame)
+def extract_source_face(source_vision_frames : List[VisionFrame]) -> Optional[Face]:
+	source_faces = []
+
+	if source_vision_frames:
+		for source_vision_frame in source_vision_frames:
+			temp_faces = get_many_faces([source_vision_frame])
+			temp_faces = sort_faces_by_order(temp_faces, 'large-small')
+
+			if temp_faces:
+				source_faces.append(get_first(temp_faces))
+
+	return get_average_face(source_faces)
 
 
 def process_frame(inputs : FaceSwapperInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
-	source_face = inputs.get('source_face')
+	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	source_face = extract_source_face(source_vision_frames)
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = swap_face(source_face, target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = swap_face(source_face, target_face, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = swap_face(source_face, similar_face, target_vision_frame)
-	return target_vision_frame
+	if source_face and target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = swap_face(source_face, target_face, temp_vision_frame)
 
-
-def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	source_frames = read_static_images(source_paths)
-	source_faces = []
-
-	for source_frame in source_frames:
-		temp_faces = get_many_faces([ source_frame ])
-		temp_faces = sort_faces_by_order(temp_faces, 'large-small')
-		if temp_faces:
-			source_faces.append(get_first(temp_faces))
-	source_face = get_average_face(source_faces)
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'source_face': source_face,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	source_frames = read_static_images(source_paths)
-	source_faces = []
-
-	for source_frame in source_frames:
-		temp_faces = get_many_faces([ source_frame ])
-		temp_faces = sort_faces_by_order(temp_faces, 'large-small')
-		if temp_faces:
-			source_faces.append(get_first(temp_faces))
-	source_face = get_average_face(source_faces)
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'source_face': source_face,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(source_paths, temp_frame_paths, process_frames)
+	return temp_vision_frame

facefusion/processors/modules/frame_colorizer.py

@@ -7,20 +7,20 @@ import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, inference_manager, logger, process_manager, state_manager, wording
-from facefusion.common_helper import create_int_metavar
+from facefusion import config, content_analyser, inference_manager, logger, state_manager, video_manager, wording
+from facefusion.common_helper import create_int_metavar, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
+from facefusion.execution import has_execution_provider
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FrameColorizerInputs
+from facefusion.processors.types import FrameColorizerInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, unpack_resolution, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, ExecutionProvider, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import blend_frame, read_static_image, read_static_video_frame, unpack_resolution
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -128,25 +128,34 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('frame_colorizer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('frame_colorizer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
+
+
+def resolve_execution_providers() -> List[ExecutionProvider]:
+	if is_macos() and has_execution_provider('coreml'):
+		return [ 'cpu' ]
+	return state_manager.get_item('execution_providers')
 
 
 def get_model_options() -> ModelOptions:
-	frame_colorizer_model = state_manager.get_item('frame_colorizer_model')
-	return create_static_model_set('full').get(frame_colorizer_model)
+	model_name = state_manager.get_item('frame_colorizer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--frame-colorizer-model', help = wording.get('help.frame_colorizer_model'), default = config.get_str_value('processors.frame_colorizer_model', 'ddcolor'), choices = processors_choices.frame_colorizer_models)
-		group_processors.add_argument('--frame-colorizer-size', help = wording.get('help.frame_colorizer_size'), type = str, default = config.get_str_value('processors.frame_colorizer_size', '256x256'), choices = processors_choices.frame_colorizer_sizes)
-		group_processors.add_argument('--frame-colorizer-blend', help = wording.get('help.frame_colorizer_blend'), type = int, default = config.get_int_value('processors.frame_colorizer_blend', '100'), choices = processors_choices.frame_colorizer_blend_range, metavar = create_int_metavar(processors_choices.frame_colorizer_blend_range))
+		group_processors.add_argument('--frame-colorizer-model', help = wording.get('help.frame_colorizer_model'), default = config.get_str_value('processors', 'frame_colorizer_model', 'ddcolor'), choices = processors_choices.frame_colorizer_models)
+		group_processors.add_argument('--frame-colorizer-size', help = wording.get('help.frame_colorizer_size'), type = str, default = config.get_str_value('processors', 'frame_colorizer_size', '256x256'), choices = processors_choices.frame_colorizer_sizes)
+		group_processors.add_argument('--frame-colorizer-blend', help = wording.get('help.frame_colorizer_blend'), type = int, default = config.get_int_value('processors', 'frame_colorizer_blend', '100'), choices = processors_choices.frame_colorizer_blend_range, metavar = create_int_metavar(processors_choices.frame_colorizer_blend_range))
 		facefusion.jobs.job_store.register_step_keys([ 'frame_colorizer_model', 'frame_colorizer_blend', 'frame_colorizer_size' ])
 
 
@@ -157,10 +166,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -170,7 +179,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -178,6 +187,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -188,7 +199,7 @@ def colorize_frame(temp_vision_frame : VisionFrame) -> VisionFrame:
 	color_vision_frame = prepare_temp_frame(temp_vision_frame)
 	color_vision_frame = forward(color_vision_frame)
 	color_vision_frame = merge_color_frame(temp_vision_frame, color_vision_frame)
-	color_vision_frame = blend_frame(temp_vision_frame, color_vision_frame)
+	color_vision_frame = blend_color_frame(temp_vision_frame, color_vision_frame)
 	return color_vision_frame
 
 
@@ -244,41 +255,12 @@ def merge_color_frame(temp_vision_frame : VisionFrame, color_vision_frame : Visi
 	return color_vision_frame
 
 
-def blend_frame(temp_vision_frame : VisionFrame, paste_vision_frame : VisionFrame) -> VisionFrame:
+def blend_color_frame(temp_vision_frame : VisionFrame, color_vision_frame : VisionFrame) -> VisionFrame:
 	frame_colorizer_blend = 1 - (state_manager.get_item('frame_colorizer_blend') / 100)
-	temp_vision_frame = cv2.addWeighted(temp_vision_frame, frame_colorizer_blend, paste_vision_frame, 1 - frame_colorizer_blend, 0)
+	temp_vision_frame = blend_frame(temp_vision_frame, color_vision_frame, 1 - frame_colorizer_blend)
 	return temp_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	pass
-
-
 def process_frame(inputs : FrameColorizerInputs) -> VisionFrame:
-	target_vision_frame = inputs.get('target_vision_frame')
-	return colorize_frame(target_vision_frame)
-
-
-def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	return colorize_frame(temp_vision_frame)

facefusion/processors/modules/frame_enhancer.py

@@ -1,27 +1,25 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List
 
 import cv2
 import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, inference_manager, logger, process_manager, state_manager, wording
-from facefusion.common_helper import create_int_metavar
+from facefusion import config, content_analyser, inference_manager, logger, state_manager, video_manager, wording
+from facefusion.common_helper import create_int_metavar, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FrameEnhancerInputs
+from facefusion.processors.types import FrameEnhancerInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import create_tile_frames, merge_tile_frames, read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import blend_frame, create_tile_frames, merge_tile_frames, read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
@@ -381,37 +379,66 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			},
 			'size': (128, 8, 4),
 			'scale': 4
+		},
+		'ultra_sharp_2_x4':
+		{
+			'hashes':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'ultra_sharp_2_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/ultra_sharp_2_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'ultra_sharp_2_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/ultra_sharp_2_x4.onnx')
+				}
+			},
+			'size': (1024, 64, 32),
+			'scale': 4
 		}
 	}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ get_frame_enhancer_model() ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ get_frame_enhancer_model() ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
+	model_name = get_frame_enhancer_model()
+	return create_static_model_set('full').get(model_name)
+
+
+def get_frame_enhancer_model() -> str:
 	frame_enhancer_model = state_manager.get_item('frame_enhancer_model')
 
-	if has_execution_provider('coreml'):
+	if is_macos() and has_execution_provider('coreml'):
 		if frame_enhancer_model == 'real_esrgan_x2_fp16':
-			return create_static_model_set('full').get('real_esrgan_x2')
+			return 'real_esrgan_x2'
 		if frame_enhancer_model == 'real_esrgan_x4_fp16':
-			return create_static_model_set('full').get('real_esrgan_x4')
+			return 'real_esrgan_x4'
 		if frame_enhancer_model == 'real_esrgan_x8_fp16':
-			return create_static_model_set('full').get('real_esrgan_x8')
-	return create_static_model_set('full').get(frame_enhancer_model)
+			return 'real_esrgan_x8'
+	return frame_enhancer_model
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--frame-enhancer-model', help = wording.get('help.frame_enhancer_model'), default = config.get_str_value('processors.frame_enhancer_model', 'span_kendata_x4'), choices = processors_choices.frame_enhancer_models)
-		group_processors.add_argument('--frame-enhancer-blend', help = wording.get('help.frame_enhancer_blend'), type = int, default = config.get_int_value('processors.frame_enhancer_blend', '80'), choices = processors_choices.frame_enhancer_blend_range, metavar = create_int_metavar(processors_choices.frame_enhancer_blend_range))
+		group_processors.add_argument('--frame-enhancer-model', help = wording.get('help.frame_enhancer_model'), default = config.get_str_value('processors', 'frame_enhancer_model', 'span_kendata_x4'), choices = processors_choices.frame_enhancer_models)
+		group_processors.add_argument('--frame-enhancer-blend', help = wording.get('help.frame_enhancer_blend'), type = int, default = config.get_int_value('processors', 'frame_enhancer_blend', '80'), choices = processors_choices.frame_enhancer_blend_range, metavar = create_int_metavar(processors_choices.frame_enhancer_blend_range))
 		facefusion.jobs.job_store.register_step_keys([ 'frame_enhancer_model', 'frame_enhancer_blend' ])
 
 
@@ -421,10 +448,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -434,7 +461,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -442,6 +469,8 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -460,7 +489,7 @@ def enhance_frame(temp_vision_frame : VisionFrame) -> VisionFrame:
 		tile_vision_frames[index] = normalize_tile_frame(tile_vision_frame)
 
 	merge_vision_frame = merge_tile_frames(tile_vision_frames, temp_width * model_scale, temp_height * model_scale, pad_width * model_scale, pad_height * model_scale, (model_size[0] * model_scale, model_size[1] * model_scale, model_size[2] * model_scale))
-	temp_vision_frame = blend_frame(temp_vision_frame, merge_vision_frame)
+	temp_vision_frame = blend_merge_frame(temp_vision_frame, merge_vision_frame)
 	return temp_vision_frame
 
 
@@ -476,55 +505,26 @@ def forward(tile_vision_frame : VisionFrame) -> VisionFrame:
 	return tile_vision_frame
 
 
-def prepare_tile_frame(vision_tile_frame : VisionFrame) -> VisionFrame:
-	vision_tile_frame = numpy.expand_dims(vision_tile_frame[:, :, ::-1], axis = 0)
-	vision_tile_frame = vision_tile_frame.transpose(0, 3, 1, 2)
-	vision_tile_frame = vision_tile_frame.astype(numpy.float32) / 255
-	return vision_tile_frame
+def prepare_tile_frame(tile_vision_frame : VisionFrame) -> VisionFrame:
+	tile_vision_frame = numpy.expand_dims(tile_vision_frame[:, :, ::-1], axis = 0)
+	tile_vision_frame = tile_vision_frame.transpose(0, 3, 1, 2)
+	tile_vision_frame = tile_vision_frame.astype(numpy.float32) / 255.0
+	return tile_vision_frame
 
 
-def normalize_tile_frame(vision_tile_frame : VisionFrame) -> VisionFrame:
-	vision_tile_frame = vision_tile_frame.transpose(0, 2, 3, 1).squeeze(0) * 255
-	vision_tile_frame = vision_tile_frame.clip(0, 255).astype(numpy.uint8)[:, :, ::-1]
-	return vision_tile_frame
+def normalize_tile_frame(tile_vision_frame : VisionFrame) -> VisionFrame:
+	tile_vision_frame = tile_vision_frame.transpose(0, 2, 3, 1).squeeze(0) * 255
+	tile_vision_frame = tile_vision_frame.clip(0, 255).astype(numpy.uint8)[:, :, ::-1]
+	return tile_vision_frame
 
 
-def blend_frame(temp_vision_frame : VisionFrame, merge_vision_frame : VisionFrame) -> VisionFrame:
+def blend_merge_frame(temp_vision_frame : VisionFrame, merge_vision_frame : VisionFrame) -> VisionFrame:
 	frame_enhancer_blend = 1 - (state_manager.get_item('frame_enhancer_blend') / 100)
 	temp_vision_frame = cv2.resize(temp_vision_frame, (merge_vision_frame.shape[1], merge_vision_frame.shape[0]))
-	temp_vision_frame = cv2.addWeighted(temp_vision_frame, frame_enhancer_blend, merge_vision_frame, 1 - frame_enhancer_blend, 0)
+	temp_vision_frame = blend_frame(temp_vision_frame, merge_vision_frame, 1 - frame_enhancer_blend)
 	return temp_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	pass
-
-
 def process_frame(inputs : FrameEnhancerInputs) -> VisionFrame:
-	target_vision_frame = inputs.get('target_vision_frame')
-	return enhance_frame(target_vision_frame)
-
-
-def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	for queue_payload in process_manager.manage(queue_payloads):
-		target_vision_path = queue_payload['frame_path']
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	processors.multi_process_frames(None, temp_frame_paths, process_frames)
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	return enhance_frame(temp_vision_frame)

facefusion/processors/modules/lip_syncer.py

@@ -1,35 +1,53 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import List
 
 import cv2
 import numpy
 
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
-import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, voice_extractor, wording
-from facefusion.audio import create_empty_audio_frame, get_voice_frame, read_static_voice
-from facefusion.common_helper import get_first
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, video_manager, voice_extractor, wording
+from facefusion.audio import read_static_voice
+from facefusion.common_helper import create_float_metavar
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_analyser import scale_face
 from facefusion.face_helper import create_bounding_box, paste_back, warp_face_by_bounding_box, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_mouth_mask, create_occlusion_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
-from facefusion.face_store import get_reference_faces
-from facefusion.filesystem import filter_audio_paths, has_audio, in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask
+from facefusion.face_selector import select_faces
+from facefusion.filesystem import has_audio, resolve_relative_path
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import LipSyncerInputs
+from facefusion.processors.types import LipSyncerInputs, LipSyncerWeight
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, AudioFrame, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, restrict_video_fps, write_image
+from facefusion.types import ApplyStateItem, Args, AudioFrame, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_frame
 
 
-@lru_cache(maxsize = None)
+@lru_cache()
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
+		'edtalk_256':
+		{
+			'hashes':
+			{
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'edtalk_256.hash'),
+					'path': resolve_relative_path('../.assets/models/edtalk_256.hash')
+				}
+			},
+			'sources':
+			{
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'edtalk_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/edtalk_256.onnx')
+				}
+			},
+			'type': 'edtalk',
+			'size': (256, 256)
+		},
 		'wav2lip_96':
 		{
 			'hashes':
@@ -48,6 +66,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/wav2lip_96.onnx')
 				}
 			},
+			'type': 'wav2lip',
 			'size': (96, 96)
 		},
 		'wav2lip_gan_96':
@@ -68,62 +87,61 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/wav2lip_gan_96.onnx')
 				}
 			},
+			'type': 'wav2lip',
 			'size': (96, 96)
 		}
 	}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ state_manager.get_item('lip_syncer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('lip_syncer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	lip_syncer_model = state_manager.get_item('lip_syncer_model')
-	return create_static_model_set('full').get(lip_syncer_model)
+	model_name = state_manager.get_item('lip_syncer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('processors.lip_syncer_model', 'wav2lip_gan_96'), choices = processors_choices.lip_syncer_models)
-		facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model' ])
+		group_processors.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('processors', 'lip_syncer_model', 'wav2lip_gan_96'), choices = processors_choices.lip_syncer_models)
+		group_processors.add_argument('--lip-syncer-weight', help = wording.get('help.lip_syncer_weight'), type = float, default = config.get_float_value('processors', 'lip_syncer_weight', '0.5'), choices = processors_choices.lip_syncer_weight_range, metavar = create_float_metavar(processors_choices.lip_syncer_weight_range))
+		facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model', 'lip_syncer_weight' ])
 
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('lip_syncer_model', args.get('lip_syncer_model'))
+	apply_state_item('lip_syncer_weight', args.get('lip_syncer_weight'))
 
 
 def pre_check() -> bool:
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(model_hashes) and conditional_download_sources(model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
 	if not has_audio(state_manager.get_item('source_paths')):
 		logger.error(wording.get('choose_audio_source') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
-		logger.error(wording.get('choose_image_or_video_target') + wording.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
-		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
-		return False
 	return True
 
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	read_static_video_frame.cache_clear()
 	read_static_voice.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -136,136 +154,124 @@ def post_process() -> None:
 		voice_extractor.clear_inference_pool()
 
 
-def sync_lip(target_face : Face, temp_audio_frame : AudioFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
+def sync_lip(target_face : Face, source_voice_frame : AudioFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
+	model_type = get_model_options().get('type')
 	model_size = get_model_options().get('size')
-	temp_audio_frame = prepare_audio_frame(temp_audio_frame)
+	source_voice_frame = prepare_audio_frame(source_voice_frame)
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), 'ffhq_512', (512, 512))
-	face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
-	bounding_box = create_bounding_box(face_landmark_68)
-	bounding_box[1] -= numpy.abs(bounding_box[3] - bounding_box[1]) * 0.125
-	mouth_mask = create_mouth_mask(face_landmark_68)
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
-	crop_masks =\
-	[
-		mouth_mask,
-		box_mask
-	]
+	crop_masks = []
 
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
 		occlusion_mask = create_occlusion_mask(crop_vision_frame)
 		crop_masks.append(occlusion_mask)
 
-	close_vision_frame, close_matrix = warp_face_by_bounding_box(crop_vision_frame, bounding_box, model_size)
-	close_vision_frame = prepare_crop_frame(close_vision_frame)
-	close_vision_frame = forward(temp_audio_frame, close_vision_frame)
-	close_vision_frame = normalize_close_frame(close_vision_frame)
-	crop_vision_frame = cv2.warpAffine(close_vision_frame, cv2.invertAffineTransform(close_matrix), (512, 512), borderMode = cv2.BORDER_REPLICATE)
+	if model_type == 'edtalk':
+		lip_syncer_weight = numpy.array([ state_manager.get_item('lip_syncer_weight') ]).astype(numpy.float32)
+		box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
+		crop_masks.append(box_mask)
+		crop_vision_frame = prepare_crop_frame(crop_vision_frame)
+		crop_vision_frame = forward_edtalk(source_voice_frame, crop_vision_frame, lip_syncer_weight)
+		crop_vision_frame = normalize_crop_frame(crop_vision_frame)
+
+	if model_type == 'wav2lip':
+		face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, [ 'lower-face' ])
+		crop_masks.append(area_mask)
+		bounding_box = create_bounding_box(face_landmark_68)
+		area_vision_frame, area_matrix = warp_face_by_bounding_box(crop_vision_frame, bounding_box, model_size)
+		area_vision_frame = prepare_crop_frame(area_vision_frame)
+		area_vision_frame = forward_wav2lip(source_voice_frame, area_vision_frame)
+		area_vision_frame = normalize_crop_frame(area_vision_frame)
+		crop_vision_frame = cv2.warpAffine(area_vision_frame, cv2.invertAffineTransform(area_matrix), (512, 512), borderMode = cv2.BORDER_REPLICATE)
+
 	crop_mask = numpy.minimum.reduce(crop_masks)
 	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
 	return paste_vision_frame
 
 
-def forward(temp_audio_frame : AudioFrame, close_vision_frame : VisionFrame) -> VisionFrame:
+def forward_edtalk(temp_audio_frame : AudioFrame, crop_vision_frame : VisionFrame, lip_syncer_weight : LipSyncerWeight) -> VisionFrame:
 	lip_syncer = get_inference_pool().get('lip_syncer')
 
 	with conditional_thread_semaphore():
-		close_vision_frame = lip_syncer.run(None,
+		crop_vision_frame = lip_syncer.run(None,
 		{
 			'source': temp_audio_frame,
-			'target': close_vision_frame
+			'target': crop_vision_frame,
+			'weight': lip_syncer_weight
 		})[0]
 
-	return close_vision_frame
+	return crop_vision_frame
+
+
+def forward_wav2lip(temp_audio_frame : AudioFrame, area_vision_frame : VisionFrame) -> VisionFrame:
+	lip_syncer = get_inference_pool().get('lip_syncer')
+
+	with conditional_thread_semaphore():
+		area_vision_frame = lip_syncer.run(None,
+		{
+			'source': temp_audio_frame,
+			'target': area_vision_frame
+		})[0]
+
+	return area_vision_frame
 
 
 def prepare_audio_frame(temp_audio_frame : AudioFrame) -> AudioFrame:
+	model_type = get_model_options().get('type')
 	temp_audio_frame = numpy.maximum(numpy.exp(-5 * numpy.log(10)), temp_audio_frame)
 	temp_audio_frame = numpy.log10(temp_audio_frame) * 1.6 + 3.2
 	temp_audio_frame = temp_audio_frame.clip(-4, 4).astype(numpy.float32)
+
+	if model_type == 'wav2lip':
+		temp_audio_frame = temp_audio_frame * state_manager.get_item('lip_syncer_weight') * 2.0
+
 	temp_audio_frame = numpy.expand_dims(temp_audio_frame, axis = (0, 1))
 	return temp_audio_frame
 
 
 def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
-	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
-	prepare_vision_frame = crop_vision_frame.copy()
-	prepare_vision_frame[:, 48:] = 0
-	crop_vision_frame = numpy.concatenate((prepare_vision_frame, crop_vision_frame), axis = 3)
-	crop_vision_frame = crop_vision_frame.transpose(0, 3, 1, 2).astype('float32') / 255.0
+	model_type = get_model_options().get('type')
+	model_size = get_model_options().get('size')
+
+	if model_type == 'edtalk':
+		crop_vision_frame = cv2.resize(crop_vision_frame, model_size, interpolation = cv2.INTER_AREA)
+		crop_vision_frame = crop_vision_frame[:, :, ::-1] / 255.0
+		crop_vision_frame = numpy.expand_dims(crop_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
+
+	if model_type == 'wav2lip':
+		crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
+		prepare_vision_frame = crop_vision_frame.copy()
+		prepare_vision_frame[:, model_size[0] // 2:] = 0
+		crop_vision_frame = numpy.concatenate((prepare_vision_frame, crop_vision_frame), axis = 3)
+		crop_vision_frame = crop_vision_frame.transpose(0, 3, 1, 2).astype(numpy.float32) / 255.0
+
 	return crop_vision_frame
 
 
-def normalize_close_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	model_type = get_model_options().get('type')
 	crop_vision_frame = crop_vision_frame[0].transpose(1, 2, 0)
 	crop_vision_frame = crop_vision_frame.clip(0, 1) * 255
 	crop_vision_frame = crop_vision_frame.astype(numpy.uint8)
+
+	if model_type == 'edtalk':
+		crop_vision_frame = crop_vision_frame[:, :, ::-1]
+		crop_vision_frame = cv2.resize(crop_vision_frame, (512, 512), interpolation = cv2.INTER_CUBIC)
+
 	return crop_vision_frame
 
 
-def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	pass
-
-
 def process_frame(inputs : LipSyncerInputs) -> VisionFrame:
-	reference_faces = inputs.get('reference_faces')
-	source_audio_frame = inputs.get('source_audio_frame')
+	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_voice_frame = inputs.get('source_voice_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
-	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+	temp_vision_frame = inputs.get('temp_vision_frame')
+	target_faces = select_faces(reference_vision_frame, target_vision_frame)
 
-	if state_manager.get_item('face_selector_mode') == 'many':
-		if many_faces:
-			for target_face in many_faces:
-				target_vision_frame = sync_lip(target_face, source_audio_frame, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(many_faces)
-		if target_face:
-			target_vision_frame = sync_lip(target_face, source_audio_frame, target_vision_frame)
-	if state_manager.get_item('face_selector_mode') == 'reference':
-		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
-		if similar_faces:
-			for similar_face in similar_faces:
-				target_vision_frame = sync_lip(similar_face, source_audio_frame, target_vision_frame)
-	return target_vision_frame
+	if target_faces:
+		for target_face in target_faces:
+			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
+			temp_vision_frame = sync_lip(target_face, source_voice_frame, temp_vision_frame)
 
+	return temp_vision_frame
 
-def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	source_audio_path = get_first(filter_audio_paths(source_paths))
-	temp_video_fps = restrict_video_fps(state_manager.get_item('target_path'), state_manager.get_item('output_video_fps'))
-
-	for queue_payload in process_manager.manage(queue_payloads):
-		frame_number = queue_payload.get('frame_number')
-		target_vision_path = queue_payload.get('frame_path')
-		source_audio_frame = get_voice_frame(source_audio_path, temp_video_fps, frame_number)
-		if not numpy.any(source_audio_frame):
-			source_audio_frame = create_empty_audio_frame()
-		target_vision_frame = read_image(target_vision_path)
-		output_vision_frame = process_frame(
-		{
-			'reference_faces': reference_faces,
-			'source_audio_frame': source_audio_frame,
-			'target_vision_frame': target_vision_frame
-		})
-		write_image(target_vision_path, output_vision_frame)
-		update_progress(1)
-
-
-def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
-	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
-	source_audio_frame = create_empty_audio_frame()
-	target_vision_frame = read_static_image(target_path)
-	output_vision_frame = process_frame(
-	{
-		'reference_faces': reference_faces,
-		'source_audio_frame': source_audio_frame,
-		'target_vision_frame': target_vision_frame
-	})
-	write_image(output_path, output_vision_frame)
-
-
-def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
-	source_audio_paths = filter_audio_paths(state_manager.get_item('source_paths'))
-	temp_video_fps = restrict_video_fps(state_manager.get_item('target_path'), state_manager.get_item('output_video_fps'))
-	for source_audio_path in source_audio_paths:
-		read_static_voice(source_audio_path, temp_video_fps)
-	processors.multi_process_frames(source_paths, temp_frame_paths, process_frames)

facefusion/processors/pixel_boost.py

@@ -3,7 +3,7 @@ from typing import List
 import numpy
 from cv2.typing import Size
 
-from facefusion.typing import VisionFrame
+from facefusion.types import VisionFrame
 
 
 def implode_pixel_boost(crop_vision_frame : VisionFrame, pixel_boost_total : int, model_size : Size) -> VisionFrame:
@@ -13,6 +13,6 @@ def implode_pixel_boost(crop_vision_frame : VisionFrame, pixel_boost_total : int
 
 
 def explode_pixel_boost(temp_vision_frames : List[VisionFrame], pixel_boost_total : int, model_size : Size, pixel_boost_size : Size) -> VisionFrame:
-	crop_vision_frame = numpy.stack(temp_vision_frames, axis = 0).reshape(pixel_boost_total, pixel_boost_total, model_size[0], model_size[1], 3)
+	crop_vision_frame = numpy.stack(temp_vision_frames).reshape(pixel_boost_total, pixel_boost_total, model_size[0], model_size[1], 3)
 	crop_vision_frame = crop_vision_frame.transpose(2, 0, 3, 1, 4).reshape(pixel_boost_size[0], pixel_boost_size[1], 3)
 	return crop_vision_frame

facefusion/processors/types.py

@@ -1,74 +1,100 @@
-from typing import Any, Dict, List, Literal, TypedDict
+from typing import Any, Dict, List, Literal, TypeAlias, TypedDict
 
-from numpy._typing import NDArray
+from numpy.typing import NDArray
 
-from facefusion.typing import AppContext, AudioFrame, Face, FaceSet, VisionFrame
+from facefusion.types import AppContext, AudioFrame, VisionFrame
 
 AgeModifierModel = Literal['styleganex_age']
-DeepSwapperModel = str
+DeepSwapperModel : TypeAlias = str
 ExpressionRestorerModel = Literal['live_portrait']
-FaceDebuggerItem = Literal['bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask', 'face-detector-score', 'face-landmarker-score', 'age', 'gender', 'race']
+ExpressionRestorerArea = Literal['upper-face', 'lower-face']
+FaceDebuggerItem = Literal['bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask']
 FaceEditorModel = Literal['live_portrait']
 FaceEnhancerModel = Literal['codeformer', 'gfpgan_1.2', 'gfpgan_1.3', 'gfpgan_1.4', 'gpen_bfr_256', 'gpen_bfr_512', 'gpen_bfr_1024', 'gpen_bfr_2048', 'restoreformer_plus_plus']
-FaceSwapperModel = Literal['blendswap_256', 'ghost_1_256', 'ghost_2_256', 'ghost_3_256', 'hififace_unofficial_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_unofficial_512', 'uniface_256']
+FaceSwapperModel = Literal['blendswap_256', 'ghost_1_256', 'ghost_2_256', 'ghost_3_256', 'hififace_unofficial_256', 'hyperswap_1a_256', 'hyperswap_1b_256', 'hyperswap_1c_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_unofficial_512', 'uniface_256']
 FrameColorizerModel = Literal['ddcolor', 'ddcolor_artistic', 'deoldify', 'deoldify_artistic', 'deoldify_stable']
-FrameEnhancerModel = Literal['clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'ultra_sharp_x4']
-LipSyncerModel = Literal['wav2lip_96', 'wav2lip_gan_96']
+FrameEnhancerModel = Literal['clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'ultra_sharp_x4', 'ultra_sharp_2_x4']
+LipSyncerModel = Literal['edtalk_256', 'wav2lip_96', 'wav2lip_gan_96']
 
-FaceSwapperSet = Dict[FaceSwapperModel, List[str]]
+FaceSwapperSet : TypeAlias = Dict[FaceSwapperModel, List[str]]
 
 AgeModifierInputs = TypedDict('AgeModifierInputs',
 {
-	'reference_faces' : FaceSet,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 DeepSwapperInputs = TypedDict('DeepSwapperInputs',
 {
-	'reference_faces' : FaceSet,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 ExpressionRestorerInputs = TypedDict('ExpressionRestorerInputs',
 {
-	'reference_faces' : FaceSet,
-	'source_vision_frame' : VisionFrame,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 FaceDebuggerInputs = TypedDict('FaceDebuggerInputs',
 {
-	'reference_faces' : FaceSet,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 FaceEditorInputs = TypedDict('FaceEditorInputs',
 {
-	'reference_faces' : FaceSet,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 FaceEnhancerInputs = TypedDict('FaceEnhancerInputs',
 {
-	'reference_faces' : FaceSet,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 FaceSwapperInputs = TypedDict('FaceSwapperInputs',
 {
-	'reference_faces' : FaceSet,
-	'source_face' : Face,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 FrameColorizerInputs = TypedDict('FrameColorizerInputs',
 {
-	'target_vision_frame' : VisionFrame
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 FrameEnhancerInputs = TypedDict('FrameEnhancerInputs',
 {
-	'target_vision_frame' : VisionFrame
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 LipSyncerInputs = TypedDict('LipSyncerInputs',
 {
-	'reference_faces' : FaceSet,
-	'source_audio_frame' : AudioFrame,
-	'target_vision_frame' : VisionFrame
+	'reference_vision_frame' : VisionFrame,
+	'source_voice_frame' : AudioFrame,
+	'target_vision_frame' : VisionFrame,
+	'temp_vision_frame' : VisionFrame
 })
 
+AgeModifierDirection : TypeAlias = NDArray[Any]
+DeepSwapperMorph : TypeAlias = NDArray[Any]
+FaceEnhancerWeight : TypeAlias = NDArray[Any]
+FaceSwapperWeight : TypeAlias = float
+LipSyncerWeight : TypeAlias = NDArray[Any]
+LivePortraitPitch : TypeAlias = float
+LivePortraitYaw : TypeAlias = float
+LivePortraitRoll : TypeAlias = float
+LivePortraitExpression : TypeAlias = NDArray[Any]
+LivePortraitFeatureVolume : TypeAlias = NDArray[Any]
+LivePortraitMotionPoints : TypeAlias = NDArray[Any]
+LivePortraitRotation : TypeAlias = NDArray[Any]
+LivePortraitScale : TypeAlias = NDArray[Any]
+LivePortraitTranslation : TypeAlias = NDArray[Any]
+
 ProcessorStateKey = Literal\
 [
 	'age_modifier_model',
@@ -77,6 +103,7 @@ ProcessorStateKey = Literal\
 	'deep_swapper_morph',
 	'expression_restorer_model',
 	'expression_restorer_factor',
+	'expression_restorer_areas',
 	'face_debugger_items',
 	'face_editor_model',
 	'face_editor_eyebrow_direction',
@@ -98,12 +125,14 @@ ProcessorStateKey = Literal\
 	'face_enhancer_weight',
 	'face_swapper_model',
 	'face_swapper_pixel_boost',
+	'face_swapper_weight',
 	'frame_colorizer_model',
 	'frame_colorizer_size',
 	'frame_colorizer_blend',
 	'frame_enhancer_model',
 	'frame_enhancer_blend',
-	'lip_syncer_model'
+	'lip_syncer_model',
+	'lip_syncer_weight'
 ]
 ProcessorState = TypedDict('ProcessorState',
 {
@@ -113,6 +142,7 @@ ProcessorState = TypedDict('ProcessorState',
 	'deep_swapper_morph' : int,
 	'expression_restorer_model' : ExpressionRestorerModel,
 	'expression_restorer_factor' : int,
+	'expression_restorer_areas' : List[ExpressionRestorerArea],
 	'face_debugger_items' : List[FaceDebuggerItem],
 	'face_editor_model' : FaceEditorModel,
 	'face_editor_eyebrow_direction' : float,
@@ -131,27 +161,16 @@ ProcessorState = TypedDict('ProcessorState',
 	'face_editor_head_roll' : float,
 	'face_enhancer_model' : FaceEnhancerModel,
 	'face_enhancer_blend' : int,
-	'face_enhancer_weight' : float,
+	'face_enhancer_weight' : FaceEnhancerWeight,
 	'face_swapper_model' : FaceSwapperModel,
 	'face_swapper_pixel_boost' : str,
+	'face_swapper_weight' : FaceSwapperWeight,
 	'frame_colorizer_model' : FrameColorizerModel,
 	'frame_colorizer_size' : str,
 	'frame_colorizer_blend' : int,
 	'frame_enhancer_model' : FrameEnhancerModel,
 	'frame_enhancer_blend' : int,
-	'lip_syncer_model' : LipSyncerModel
+	'lip_syncer_model' : LipSyncerModel,
+	'lip_syncer_weight' : LipSyncerWeight
 })
-ProcessorStateSet = Dict[AppContext, ProcessorState]
-
-AgeModifierDirection = NDArray[Any]
-DeepSwapperMorph = NDArray[Any]
-FaceEnhancerWeight = NDArray[Any]
-LivePortraitPitch = float
-LivePortraitYaw = float
-LivePortraitRoll = float
-LivePortraitExpression = NDArray[Any]
-LivePortraitFeatureVolume = NDArray[Any]
-LivePortraitMotionPoints = NDArray[Any]
-LivePortraitRotation = NDArray[Any]
-LivePortraitScale = NDArray[Any]
-LivePortraitTranslation = NDArray[Any]
+ProcessorStateSet : TypeAlias = Dict[AppContext, ProcessorState]

facefusion/program.py

@@ -3,9 +3,10 @@ from argparse import ArgumentParser, HelpFormatter
 
 import facefusion.choices
 from facefusion import config, metadata, state_manager, wording
-from facefusion.common_helper import create_float_metavar, create_int_metavar, get_last
+from facefusion.common_helper import create_float_metavar, create_int_metavar, get_first, get_last
 from facefusion.execution import get_available_execution_providers
-from facefusion.filesystem import list_directory
+from facefusion.ffmpeg import get_available_encoder_set
+from facefusion.filesystem import get_file_name, resolve_file_paths
 from facefusion.jobs import job_store
 from facefusion.processors.core import get_processors_modules
 
@@ -30,7 +31,7 @@ def create_config_path_program() -> ArgumentParser:
 def create_temp_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('--temp-path', help = wording.get('help.temp_path'), default = config.get_str_value('paths.temp_path', tempfile.gettempdir()))
+	group_paths.add_argument('--temp-path', help = wording.get('help.temp_path'), default = config.get_str_value('paths', 'temp_path', tempfile.gettempdir()))
 	job_store.register_job_keys([ 'temp_path' ])
 	return program
 
@@ -38,7 +39,7 @@ def create_temp_path_program() -> ArgumentParser:
 def create_jobs_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('--jobs-path', help = wording.get('help.jobs_path'), default = config.get_str_value('paths.jobs_path', '.jobs'))
+	group_paths.add_argument('--jobs-path', help = wording.get('help.jobs_path'), default = config.get_str_value('paths', 'jobs_path', '.jobs'))
 	job_store.register_job_keys([ 'jobs_path' ])
 	return program
 
@@ -46,7 +47,7 @@ def create_jobs_path_program() -> ArgumentParser:
 def create_source_paths_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('-s', '--source-paths', help = wording.get('help.source_paths'), default = config.get_str_list('paths.source_paths'), nargs = '+')
+	group_paths.add_argument('-s', '--source-paths', help = wording.get('help.source_paths'), default = config.get_str_list('paths', 'source_paths'), nargs = '+')
 	job_store.register_step_keys([ 'source_paths' ])
 	return program
 
@@ -54,7 +55,7 @@ def create_source_paths_program() -> ArgumentParser:
 def create_target_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('-t', '--target-path', help = wording.get('help.target_path'), default = config.get_str_value('paths.target_path'))
+	group_paths.add_argument('-t', '--target-path', help = wording.get('help.target_path'), default = config.get_str_value('paths', 'target_path'))
 	job_store.register_step_keys([ 'target_path' ])
 	return program
 
@@ -62,7 +63,7 @@ def create_target_path_program() -> ArgumentParser:
 def create_output_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('-o', '--output-path', help = wording.get('help.output_path'), default = config.get_str_value('paths.output_path'))
+	group_paths.add_argument('-o', '--output-path', help = wording.get('help.output_path'), default = config.get_str_value('paths', 'output_path'))
 	job_store.register_step_keys([ 'output_path' ])
 	return program
 
@@ -70,7 +71,7 @@ def create_output_path_program() -> ArgumentParser:
 def create_source_pattern_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_patterns = program.add_argument_group('patterns')
-	group_patterns.add_argument('-s', '--source-pattern', help = wording.get('help.source_pattern'), default = config.get_str_value('patterns.source_pattern'))
+	group_patterns.add_argument('-s', '--source-pattern', help = wording.get('help.source_pattern'), default = config.get_str_value('patterns', 'source_pattern'))
 	job_store.register_job_keys([ 'source_pattern' ])
 	return program
 
@@ -78,7 +79,7 @@ def create_source_pattern_program() -> ArgumentParser:
 def create_target_pattern_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_patterns = program.add_argument_group('patterns')
-	group_patterns.add_argument('-t', '--target-pattern', help = wording.get('help.target_pattern'), default = config.get_str_value('patterns.target_pattern'))
+	group_patterns.add_argument('-t', '--target-pattern', help = wording.get('help.target_pattern'), default = config.get_str_value('patterns', 'target_pattern'))
 	job_store.register_job_keys([ 'target_pattern' ])
 	return program
 
@@ -86,7 +87,7 @@ def create_target_pattern_program() -> ArgumentParser:
 def create_output_pattern_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_patterns = program.add_argument_group('patterns')
-	group_patterns.add_argument('-o', '--output-pattern', help = wording.get('help.output_pattern'), default = config.get_str_value('patterns.output_pattern'))
+	group_patterns.add_argument('-o', '--output-pattern', help = wording.get('help.output_pattern'), default = config.get_str_value('patterns', 'output_pattern'))
 	job_store.register_job_keys([ 'output_pattern' ])
 	return program
 
@@ -94,12 +95,12 @@ def create_output_pattern_program() -> ArgumentParser:
 def create_face_detector_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_detector = program.add_argument_group('face detector')
-	group_face_detector.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_detector.face_detector_model', 'yoloface'), choices = facefusion.choices.face_detector_models)
+	group_face_detector.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_detector', 'face_detector_model', 'yolo_face'), choices = facefusion.choices.face_detector_models)
 	known_args, _ = program.parse_known_args()
 	face_detector_size_choices = facefusion.choices.face_detector_set.get(known_args.face_detector_model)
-	group_face_detector.add_argument('--face-detector-size', help = wording.get('help.face_detector_size'), default = config.get_str_value('face_detector.face_detector_size', get_last(face_detector_size_choices)), choices = face_detector_size_choices)
-	group_face_detector.add_argument('--face-detector-angles', help = wording.get('help.face_detector_angles'), type = int, default = config.get_int_list('face_detector.face_detector_angles', '0'), choices = facefusion.choices.face_detector_angles, nargs = '+', metavar = 'FACE_DETECTOR_ANGLES')
-	group_face_detector.add_argument('--face-detector-score', help = wording.get('help.face_detector_score'), type = float, default = config.get_float_value('face_detector.face_detector_score', '0.5'), choices = facefusion.choices.face_detector_score_range, metavar = create_float_metavar(facefusion.choices.face_detector_score_range))
+	group_face_detector.add_argument('--face-detector-size', help = wording.get('help.face_detector_size'), default = config.get_str_value('face_detector', 'face_detector_size', get_last(face_detector_size_choices)), choices = face_detector_size_choices)
+	group_face_detector.add_argument('--face-detector-angles', help = wording.get('help.face_detector_angles'), type = int, default = config.get_int_list('face_detector', 'face_detector_angles', '0'), choices = facefusion.choices.face_detector_angles, nargs = '+', metavar = 'FACE_DETECTOR_ANGLES')
+	group_face_detector.add_argument('--face-detector-score', help = wording.get('help.face_detector_score'), type = float, default = config.get_float_value('face_detector', 'face_detector_score', '0.5'), choices = facefusion.choices.face_detector_score_range, metavar = create_float_metavar(facefusion.choices.face_detector_score_range))
 	job_store.register_step_keys([ 'face_detector_model', 'face_detector_angles', 'face_detector_size', 'face_detector_score' ])
 	return program
 
@@ -107,8 +108,8 @@ def create_face_detector_program() -> ArgumentParser:
 def create_face_landmarker_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_landmarker = program.add_argument_group('face landmarker')
-	group_face_landmarker.add_argument('--face-landmarker-model', help = wording.get('help.face_landmarker_model'), default = config.get_str_value('face_landmarker.face_landmarker_model', '2dfan4'), choices = facefusion.choices.face_landmarker_models)
-	group_face_landmarker.add_argument('--face-landmarker-score', help = wording.get('help.face_landmarker_score'), type = float, default = config.get_float_value('face_landmarker.face_landmarker_score', '0.5'), choices = facefusion.choices.face_landmarker_score_range, metavar = create_float_metavar(facefusion.choices.face_landmarker_score_range))
+	group_face_landmarker.add_argument('--face-landmarker-model', help = wording.get('help.face_landmarker_model'), default = config.get_str_value('face_landmarker', 'face_landmarker_model', '2dfan4'), choices = facefusion.choices.face_landmarker_models)
+	group_face_landmarker.add_argument('--face-landmarker-score', help = wording.get('help.face_landmarker_score'), type = float, default = config.get_float_value('face_landmarker', 'face_landmarker_score', '0.5'), choices = facefusion.choices.face_landmarker_score_range, metavar = create_float_metavar(facefusion.choices.face_landmarker_score_range))
 	job_store.register_step_keys([ 'face_landmarker_model', 'face_landmarker_score' ])
 	return program
 
@@ -116,15 +117,15 @@ def create_face_landmarker_program() -> ArgumentParser:
 def create_face_selector_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_selector = program.add_argument_group('face selector')
-	group_face_selector.add_argument('--face-selector-mode', help = wording.get('help.face_selector_mode'), default = config.get_str_value('face_selector.face_selector_mode', 'reference'), choices = facefusion.choices.face_selector_modes)
-	group_face_selector.add_argument('--face-selector-order', help = wording.get('help.face_selector_order'), default = config.get_str_value('face_selector.face_selector_order', 'large-small'), choices = facefusion.choices.face_selector_orders)
-	group_face_selector.add_argument('--face-selector-age-start', help = wording.get('help.face_selector_age_start'), type = int, default = config.get_int_value('face_selector.face_selector_age_start'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
-	group_face_selector.add_argument('--face-selector-age-end', help = wording.get('help.face_selector_age_end'), type = int, default = config.get_int_value('face_selector.face_selector_age_end'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
-	group_face_selector.add_argument('--face-selector-gender', help = wording.get('help.face_selector_gender'), default = config.get_str_value('face_selector.face_selector_gender'), choices = facefusion.choices.face_selector_genders)
-	group_face_selector.add_argument('--face-selector-race', help = wording.get('help.face_selector_race'), default = config.get_str_value('face_selector.face_selector_race'), choices = facefusion.choices.face_selector_races)
-	group_face_selector.add_argument('--reference-face-position', help = wording.get('help.reference_face_position'), type = int, default = config.get_int_value('face_selector.reference_face_position', '0'))
-	group_face_selector.add_argument('--reference-face-distance', help = wording.get('help.reference_face_distance'), type = float, default = config.get_float_value('face_selector.reference_face_distance', '0.6'), choices = facefusion.choices.reference_face_distance_range, metavar = create_float_metavar(facefusion.choices.reference_face_distance_range))
-	group_face_selector.add_argument('--reference-frame-number', help = wording.get('help.reference_frame_number'), type = int, default = config.get_int_value('face_selector.reference_frame_number', '0'))
+	group_face_selector.add_argument('--face-selector-mode', help = wording.get('help.face_selector_mode'), default = config.get_str_value('face_selector', 'face_selector_mode', 'reference'), choices = facefusion.choices.face_selector_modes)
+	group_face_selector.add_argument('--face-selector-order', help = wording.get('help.face_selector_order'), default = config.get_str_value('face_selector', 'face_selector_order', 'large-small'), choices = facefusion.choices.face_selector_orders)
+	group_face_selector.add_argument('--face-selector-age-start', help = wording.get('help.face_selector_age_start'), type = int, default = config.get_int_value('face_selector', 'face_selector_age_start'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
+	group_face_selector.add_argument('--face-selector-age-end', help = wording.get('help.face_selector_age_end'), type = int, default = config.get_int_value('face_selector', 'face_selector_age_end'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
+	group_face_selector.add_argument('--face-selector-gender', help = wording.get('help.face_selector_gender'), default = config.get_str_value('face_selector', 'face_selector_gender'), choices = facefusion.choices.face_selector_genders)
+	group_face_selector.add_argument('--face-selector-race', help = wording.get('help.face_selector_race'), default = config.get_str_value('face_selector', 'face_selector_race'), choices = facefusion.choices.face_selector_races)
+	group_face_selector.add_argument('--reference-face-position', help = wording.get('help.reference_face_position'), type = int, default = config.get_int_value('face_selector', 'reference_face_position', '0'))
+	group_face_selector.add_argument('--reference-face-distance', help = wording.get('help.reference_face_distance'), type = float, default = config.get_float_value('face_selector', 'reference_face_distance', '0.3'), choices = facefusion.choices.reference_face_distance_range, metavar = create_float_metavar(facefusion.choices.reference_face_distance_range))
+	group_face_selector.add_argument('--reference-frame-number', help = wording.get('help.reference_frame_number'), type = int, default = config.get_int_value('face_selector', 'reference_frame_number', '0'))
 	job_store.register_step_keys([ 'face_selector_mode', 'face_selector_order', 'face_selector_gender', 'face_selector_race', 'face_selector_age_start', 'face_selector_age_end', 'reference_face_position', 'reference_face_distance', 'reference_frame_number' ])
 	return program
 
@@ -132,48 +133,59 @@ def create_face_selector_program() -> ArgumentParser:
 def create_face_masker_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_masker = program.add_argument_group('face masker')
-	group_face_masker.add_argument('--face-occluder-model', help = wording.get('help.face_occluder_model'), default = config.get_str_value('face_detector.face_occluder_model', 'xseg_1'), choices = facefusion.choices.face_occluder_models)
-	group_face_masker.add_argument('--face-parser-model', help = wording.get('help.face_parser_model'), default = config.get_str_value('face_detector.face_parser_model', 'bisenet_resnet_34'), choices = facefusion.choices.face_parser_models)
-	group_face_masker.add_argument('--face-mask-types', help = wording.get('help.face_mask_types').format(choices = ', '.join(facefusion.choices.face_mask_types)), default = config.get_str_list('face_masker.face_mask_types', 'box'), choices = facefusion.choices.face_mask_types, nargs = '+', metavar = 'FACE_MASK_TYPES')
-	group_face_masker.add_argument('--face-mask-blur', help = wording.get('help.face_mask_blur'), type = float, default = config.get_float_value('face_masker.face_mask_blur', '0.3'), choices = facefusion.choices.face_mask_blur_range, metavar = create_float_metavar(facefusion.choices.face_mask_blur_range))
-	group_face_masker.add_argument('--face-mask-padding', help = wording.get('help.face_mask_padding'), type = int, default = config.get_int_list('face_masker.face_mask_padding', '0 0 0 0'), nargs = '+')
-	group_face_masker.add_argument('--face-mask-regions', help = wording.get('help.face_mask_regions').format(choices = ', '.join(facefusion.choices.face_mask_regions)), default = config.get_str_list('face_masker.face_mask_regions', ' '.join(facefusion.choices.face_mask_regions)), choices = facefusion.choices.face_mask_regions, nargs = '+', metavar = 'FACE_MASK_REGIONS')
-	job_store.register_step_keys([ 'face_occluder_model', 'face_parser_model', 'face_mask_types', 'face_mask_blur', 'face_mask_padding', 'face_mask_regions' ])
+	group_face_masker.add_argument('--face-occluder-model', help = wording.get('help.face_occluder_model'), default = config.get_str_value('face_masker', 'face_occluder_model', 'xseg_1'), choices = facefusion.choices.face_occluder_models)
+	group_face_masker.add_argument('--face-parser-model', help = wording.get('help.face_parser_model'), default = config.get_str_value('face_masker', 'face_parser_model', 'bisenet_resnet_34'), choices = facefusion.choices.face_parser_models)
+	group_face_masker.add_argument('--face-mask-types', help = wording.get('help.face_mask_types').format(choices = ', '.join(facefusion.choices.face_mask_types)), default = config.get_str_list('face_masker', 'face_mask_types', 'box'), choices = facefusion.choices.face_mask_types, nargs = '+', metavar = 'FACE_MASK_TYPES')
+	group_face_masker.add_argument('--face-mask-areas', help = wording.get('help.face_mask_areas').format(choices = ', '.join(facefusion.choices.face_mask_areas)), default = config.get_str_list('face_masker', 'face_mask_areas', ' '.join(facefusion.choices.face_mask_areas)), choices = facefusion.choices.face_mask_areas, nargs = '+', metavar = 'FACE_MASK_AREAS')
+	group_face_masker.add_argument('--face-mask-regions', help = wording.get('help.face_mask_regions').format(choices = ', '.join(facefusion.choices.face_mask_regions)), default = config.get_str_list('face_masker', 'face_mask_regions', ' '.join(facefusion.choices.face_mask_regions)), choices = facefusion.choices.face_mask_regions, nargs = '+', metavar = 'FACE_MASK_REGIONS')
+	group_face_masker.add_argument('--face-mask-blur', help = wording.get('help.face_mask_blur'), type = float, default = config.get_float_value('face_masker', 'face_mask_blur', '0.3'), choices = facefusion.choices.face_mask_blur_range, metavar = create_float_metavar(facefusion.choices.face_mask_blur_range))
+	group_face_masker.add_argument('--face-mask-padding', help = wording.get('help.face_mask_padding'), type = int, default = config.get_int_list('face_masker', 'face_mask_padding', '0 0 0 0'), nargs = '+')
+	job_store.register_step_keys([ 'face_occluder_model', 'face_parser_model', 'face_mask_types', 'face_mask_areas', 'face_mask_regions', 'face_mask_blur', 'face_mask_padding' ])
+	return program
+
+
+def create_voice_extractor_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_voice_extractor = program.add_argument_group('voice extractor')
+	group_voice_extractor.add_argument('--voice-extractor-model', help = wording.get('help.voice_extractor_model'), default = config.get_str_value('voice_extractor', 'voice_extractor_model', 'kim_vocal_2'), choices = facefusion.choices.voice_extractor_models)
+	job_store.register_step_keys([ 'voice_extractor_model' ])
 	return program
 
 
 def create_frame_extraction_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_frame_extraction = program.add_argument_group('frame extraction')
-	group_frame_extraction.add_argument('--trim-frame-start', help = wording.get('help.trim_frame_start'), type = int, default = facefusion.config.get_int_value('frame_extraction.trim_frame_start'))
-	group_frame_extraction.add_argument('--trim-frame-end',	help = wording.get('help.trim_frame_end'), type = int, default = facefusion.config.get_int_value('frame_extraction.trim_frame_end'))
-	group_frame_extraction.add_argument('--temp-frame-format', help = wording.get('help.temp_frame_format'), default = config.get_str_value('frame_extraction.temp_frame_format', 'png'), choices = facefusion.choices.temp_frame_formats)
-	group_frame_extraction.add_argument('--keep-temp', help = wording.get('help.keep_temp'), action = 'store_true',	default = config.get_bool_value('frame_extraction.keep_temp'))
+	group_frame_extraction.add_argument('--trim-frame-start', help = wording.get('help.trim_frame_start'), type = int, default = facefusion.config.get_int_value('frame_extraction', 'trim_frame_start'))
+	group_frame_extraction.add_argument('--trim-frame-end', help = wording.get('help.trim_frame_end'), type = int, default = facefusion.config.get_int_value('frame_extraction', 'trim_frame_end'))
+	group_frame_extraction.add_argument('--temp-frame-format', help = wording.get('help.temp_frame_format'), default = config.get_str_value('frame_extraction', 'temp_frame_format', 'png'), choices = facefusion.choices.temp_frame_formats)
+	group_frame_extraction.add_argument('--keep-temp', help = wording.get('help.keep_temp'), action = 'store_true', default = config.get_bool_value('frame_extraction', 'keep_temp'))
 	job_store.register_step_keys([ 'trim_frame_start', 'trim_frame_end', 'temp_frame_format', 'keep_temp' ])
 	return program
 
 
 def create_output_creation_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
+	available_encoder_set = get_available_encoder_set()
 	group_output_creation = program.add_argument_group('output creation')
-	group_output_creation.add_argument('--output-image-quality', help = wording.get('help.output_image_quality'), type = int, default = config.get_int_value('output_creation.output_image_quality', '80'), choices = facefusion.choices.output_image_quality_range, metavar = create_int_metavar(facefusion.choices.output_image_quality_range))
-	group_output_creation.add_argument('--output-image-resolution', help = wording.get('help.output_image_resolution'), default = config.get_str_value('output_creation.output_image_resolution'))
-	group_output_creation.add_argument('--output-audio-encoder', help = wording.get('help.output_audio_encoder'), default = config.get_str_value('output_creation.output_audio_encoder', 'aac'), choices = facefusion.choices.output_audio_encoders)
-	group_output_creation.add_argument('--output-video-encoder', help = wording.get('help.output_video_encoder'), default = config.get_str_value('output_creation.output_video_encoder', 'libx264'), choices = facefusion.choices.output_video_encoders)
-	group_output_creation.add_argument('--output-video-preset', help = wording.get('help.output_video_preset'), default = config.get_str_value('output_creation.output_video_preset', 'veryfast'), choices = facefusion.choices.output_video_presets)
-	group_output_creation.add_argument('--output-video-quality', help = wording.get('help.output_video_quality'), type = int, default = config.get_int_value('output_creation.output_video_quality', '80'), choices = facefusion.choices.output_video_quality_range, metavar = create_int_metavar(facefusion.choices.output_video_quality_range))
-	group_output_creation.add_argument('--output-video-resolution', help = wording.get('help.output_video_resolution'), default = config.get_str_value('output_creation.output_video_resolution'))
-	group_output_creation.add_argument('--output-video-fps', help = wording.get('help.output_video_fps'), type = float, default = config.get_str_value('output_creation.output_video_fps'))
-	group_output_creation.add_argument('--skip-audio', help = wording.get('help.skip_audio'), action = 'store_true', default = config.get_bool_value('output_creation.skip_audio'))
-	job_store.register_step_keys([ 'output_image_quality', 'output_image_resolution', 'output_audio_encoder', 'output_video_encoder', 'output_video_preset', 'output_video_quality', 'output_video_resolution', 'output_video_fps', 'skip_audio' ])
+	group_output_creation.add_argument('--output-image-quality', help = wording.get('help.output_image_quality'), type = int, default = config.get_int_value('output_creation', 'output_image_quality', '80'), choices = facefusion.choices.output_image_quality_range, metavar = create_int_metavar(facefusion.choices.output_image_quality_range))
+	group_output_creation.add_argument('--output-image-scale', help = wording.get('help.output_image_scale'), type = float, default = config.get_float_value('output_creation', 'output_image_scale', '1.0'), choices = facefusion.choices.output_image_scale_range)
+	group_output_creation.add_argument('--output-audio-encoder', help = wording.get('help.output_audio_encoder'), default = config.get_str_value('output_creation', 'output_audio_encoder', get_first(available_encoder_set.get('audio'))), choices = available_encoder_set.get('audio'))
+	group_output_creation.add_argument('--output-audio-quality', help = wording.get('help.output_audio_quality'), type = int, default = config.get_int_value('output_creation', 'output_audio_quality', '80'), choices = facefusion.choices.output_audio_quality_range, metavar = create_int_metavar(facefusion.choices.output_audio_quality_range))
+	group_output_creation.add_argument('--output-audio-volume', help = wording.get('help.output_audio_volume'), type = int, default = config.get_int_value('output_creation', 'output_audio_volume', '100'), choices = facefusion.choices.output_audio_volume_range, metavar = create_int_metavar(facefusion.choices.output_audio_volume_range))
+	group_output_creation.add_argument('--output-video-encoder', help = wording.get('help.output_video_encoder'), default = config.get_str_value('output_creation', 'output_video_encoder', get_first(available_encoder_set.get('video'))), choices = available_encoder_set.get('video'))
+	group_output_creation.add_argument('--output-video-preset', help = wording.get('help.output_video_preset'), default = config.get_str_value('output_creation', 'output_video_preset', 'veryfast'), choices = facefusion.choices.output_video_presets)
+	group_output_creation.add_argument('--output-video-quality', help = wording.get('help.output_video_quality'), type = int, default = config.get_int_value('output_creation', 'output_video_quality', '80'), choices = facefusion.choices.output_video_quality_range, metavar = create_int_metavar(facefusion.choices.output_video_quality_range))
+	group_output_creation.add_argument('--output-video-scale', help = wording.get('help.output_video_scale'), type = float, default = config.get_float_value('output_creation', 'output_video_scale', '1.0'), choices = facefusion.choices.output_video_scale_range)
+	group_output_creation.add_argument('--output-video-fps', help = wording.get('help.output_video_fps'), type = float, default = config.get_float_value('output_creation', 'output_video_fps'))
+	job_store.register_step_keys([ 'output_image_quality', 'output_image_scale', 'output_audio_encoder', 'output_audio_quality', 'output_audio_volume', 'output_video_encoder', 'output_video_preset', 'output_video_quality', 'output_video_scale', 'output_video_fps' ])
 	return program
 
 
 def create_processors_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	available_processors = [ file.get('name') for file in list_directory('facefusion/processors/modules') ]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	group_processors = program.add_argument_group('processors')
-	group_processors.add_argument('--processors', help = wording.get('help.processors').format(choices = ', '.join(available_processors)), default = config.get_str_list('processors.processors', 'face_swapper'), nargs = '+')
+	group_processors.add_argument('--processors', help = wording.get('help.processors').format(choices = ', '.join(available_processors)), default = config.get_str_list('processors', 'processors', 'face_swapper'), nargs = '+')
 	job_store.register_step_keys([ 'processors' ])
 	for processor_module in get_processors_modules(available_processors):
 		processor_module.register_args(program)
@@ -182,31 +194,18 @@ def create_processors_program() -> ArgumentParser:
 
 def create_uis_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	available_ui_layouts = [ file.get('name') for file in list_directory('facefusion/uis/layouts') ]
+	available_ui_layouts = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/uis/layouts') ]
 	group_uis = program.add_argument_group('uis')
-	group_uis.add_argument('--open-browser', help = wording.get('help.open_browser'), action = 'store_true', default = config.get_bool_value('uis.open_browser'))
-	group_uis.add_argument('--ui-layouts', help = wording.get('help.ui_layouts').format(choices = ', '.join(available_ui_layouts)), default = config.get_str_list('uis.ui_layouts', 'default'), nargs = '+')
-	group_uis.add_argument('--ui-workflow', help = wording.get('help.ui_workflow'), default = config.get_str_value('uis.ui_workflow', 'instant_runner'), choices = facefusion.choices.ui_workflows)
-	return program
-
-
-def create_execution_program() -> ArgumentParser:
-	program = ArgumentParser(add_help = False)
-	available_execution_providers = get_available_execution_providers()
-	group_execution = program.add_argument_group('execution')
-	group_execution.add_argument('--execution-device-id', help = wording.get('help.execution_device_id'), default = config.get_str_value('execution.execution_device_id', '0'))
-	group_execution.add_argument('--execution-providers', help = wording.get('help.execution_providers').format(choices = ', '.join(available_execution_providers)), default = config.get_str_list('execution.execution_providers', 'cpu'), choices = available_execution_providers, nargs = '+', metavar = 'EXECUTION_PROVIDERS')
-	group_execution.add_argument('--execution-thread-count', help = wording.get('help.execution_thread_count'), type = int, default = config.get_int_value('execution.execution_thread_count', '4'), choices = facefusion.choices.execution_thread_count_range, metavar = create_int_metavar(facefusion.choices.execution_thread_count_range))
-	group_execution.add_argument('--execution-queue-count', help = wording.get('help.execution_queue_count'), type = int, default = config.get_int_value('execution.execution_queue_count', '1'), choices = facefusion.choices.execution_queue_count_range, metavar = create_int_metavar(facefusion.choices.execution_queue_count_range))
-	job_store.register_job_keys([ 'execution_device_id', 'execution_providers', 'execution_thread_count', 'execution_queue_count' ])
+	group_uis.add_argument('--open-browser', help = wording.get('help.open_browser'), action = 'store_true', default = config.get_bool_value('uis', 'open_browser'))
+	group_uis.add_argument('--ui-layouts', help = wording.get('help.ui_layouts').format(choices = ', '.join(available_ui_layouts)), default = config.get_str_list('uis', 'ui_layouts', 'default'), nargs = '+')
+	group_uis.add_argument('--ui-workflow', help = wording.get('help.ui_workflow'), default = config.get_str_value('uis', 'ui_workflow', 'instant_runner'), choices = facefusion.choices.ui_workflows)
 	return program
 
 
 def create_download_providers_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	download_providers = list(facefusion.choices.download_provider_set.keys())
 	group_download = program.add_argument_group('download')
-	group_download.add_argument('--download-providers', help = wording.get('help.download_providers').format(choices = ', '.join(download_providers)), default = config.get_str_list('download.download_providers', ' '.join(facefusion.choices.download_providers)), choices = download_providers, nargs = '+', metavar = 'DOWNLOAD_PROVIDERS')
+	group_download.add_argument('--download-providers', help = wording.get('help.download_providers').format(choices = ', '.join(facefusion.choices.download_providers)), default = config.get_str_list('download', 'download_providers', ' '.join(facefusion.choices.download_providers)), choices = facefusion.choices.download_providers, nargs = '+', metavar = 'DOWNLOAD_PROVIDERS')
 	job_store.register_job_keys([ 'download_providers' ])
 	return program
 
@@ -214,29 +213,56 @@ def create_download_providers_program() -> ArgumentParser:
 def create_download_scope_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_download = program.add_argument_group('download')
-	group_download.add_argument('--download-scope', help = wording.get('help.download_scope'), default = config.get_str_value('download.download_scope', 'lite'), choices = facefusion.choices.download_scopes)
+	group_download.add_argument('--download-scope', help = wording.get('help.download_scope'), default = config.get_str_value('download', 'download_scope', 'lite'), choices = facefusion.choices.download_scopes)
 	job_store.register_job_keys([ 'download_scope' ])
 	return program
 
 
+def create_benchmark_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_benchmark = program.add_argument_group('benchmark')
+	group_benchmark.add_argument('--benchmark-mode', help = wording.get('help.benchmark_mode'), default = config.get_str_value('benchmark', 'benchmark_mode', 'warm'), choices = facefusion.choices.benchmark_modes)
+	group_benchmark.add_argument('--benchmark-resolutions', help = wording.get('help.benchmark_resolutions'), default = config.get_str_list('benchmark', 'benchmark_resolutions', get_first(facefusion.choices.benchmark_resolutions)), choices = facefusion.choices.benchmark_resolutions, nargs = '+')
+	group_benchmark.add_argument('--benchmark-cycle-count', help = wording.get('help.benchmark_cycle_count'), type = int, default = config.get_int_value('benchmark', 'benchmark_cycle_count', '5'), choices = facefusion.choices.benchmark_cycle_count_range)
+	return program
+
+
+def create_execution_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	available_execution_providers = get_available_execution_providers()
+	group_execution = program.add_argument_group('execution')
+	group_execution.add_argument('--execution-device-ids', help = wording.get('help.execution_device_ids'), default = config.get_str_list('execution', 'execution_device_ids', '0'), nargs = '+', metavar = 'EXECUTION_DEVICE_IDS')
+	group_execution.add_argument('--execution-providers', help = wording.get('help.execution_providers').format(choices = ', '.join(available_execution_providers)), default = config.get_str_list('execution', 'execution_providers', get_first(available_execution_providers)), choices = available_execution_providers, nargs = '+', metavar = 'EXECUTION_PROVIDERS')
+	group_execution.add_argument('--execution-thread-count', help = wording.get('help.execution_thread_count'), type = int, default = config.get_int_value('execution', 'execution_thread_count', '4'), choices = facefusion.choices.execution_thread_count_range, metavar = create_int_metavar(facefusion.choices.execution_thread_count_range))
+	job_store.register_job_keys([ 'execution_device_ids', 'execution_providers', 'execution_thread_count' ])
+	return program
+
+
 def create_memory_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_memory = program.add_argument_group('memory')
-	group_memory.add_argument('--video-memory-strategy', help = wording.get('help.video_memory_strategy'), default = config.get_str_value('memory.video_memory_strategy', 'strict'), choices = facefusion.choices.video_memory_strategies)
-	group_memory.add_argument('--system-memory-limit', help = wording.get('help.system_memory_limit'), type = int, default = config.get_int_value('memory.system_memory_limit', '0'), choices = facefusion.choices.system_memory_limit_range, metavar = create_int_metavar(facefusion.choices.system_memory_limit_range))
+	group_memory.add_argument('--video-memory-strategy', help = wording.get('help.video_memory_strategy'), default = config.get_str_value('memory', 'video_memory_strategy', 'strict'), choices = facefusion.choices.video_memory_strategies)
+	group_memory.add_argument('--system-memory-limit', help = wording.get('help.system_memory_limit'), type = int, default = config.get_int_value('memory', 'system_memory_limit', '0'), choices = facefusion.choices.system_memory_limit_range, metavar = create_int_metavar(facefusion.choices.system_memory_limit_range))
 	job_store.register_job_keys([ 'video_memory_strategy', 'system_memory_limit' ])
 	return program
 
 
-def create_misc_program() -> ArgumentParser:
+def create_log_level_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	log_level_keys = list(facefusion.choices.log_level_set.keys())
 	group_misc = program.add_argument_group('misc')
-	group_misc.add_argument('--log-level', help = wording.get('help.log_level'), default = config.get_str_value('misc.log_level', 'info'), choices = log_level_keys)
+	group_misc.add_argument('--log-level', help = wording.get('help.log_level'), default = config.get_str_value('misc', 'log_level', 'info'), choices = facefusion.choices.log_levels)
 	job_store.register_job_keys([ 'log_level' ])
 	return program
 
 
+def create_halt_on_error_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_misc = program.add_argument_group('misc')
+	group_misc.add_argument('--halt-on-error', help = wording.get('help.halt_on_error'), action = 'store_true', default = config.get_bool_value('misc', 'halt_on_error'))
+	job_store.register_job_keys([ 'halt_on_error' ])
+	return program
+
+
 def create_job_id_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	program.add_argument('job_id', help = wording.get('help.job_id'))
@@ -257,11 +283,11 @@ def create_step_index_program() -> ArgumentParser:
 
 
 def collect_step_program() -> ArgumentParser:
-	return ArgumentParser(parents= [ create_face_detector_program(), create_face_landmarker_program(), create_face_selector_program(), create_face_masker_program(), create_frame_extraction_program(), create_output_creation_program(), create_processors_program() ], add_help = False)
+	return ArgumentParser(parents = [ create_face_detector_program(), create_face_landmarker_program(), create_face_selector_program(), create_face_masker_program(), create_voice_extractor_program(), create_frame_extraction_program(), create_output_creation_program(), create_processors_program() ], add_help = False)
 
 
 def collect_job_program() -> ArgumentParser:
-	return ArgumentParser(parents= [ create_execution_program(), create_download_providers_program(), create_memory_program(), create_misc_program() ], add_help = False)
+	return ArgumentParser(parents = [ create_execution_program(), create_download_providers_program(), create_memory_program(), create_log_level_program() ], add_help = False)
 
 
 def create_program() -> ArgumentParser:
@@ -270,27 +296,28 @@ def create_program() -> ArgumentParser:
 	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
 	sub_program = program.add_subparsers(dest = 'command')
 	# general
-	sub_program.add_parser('run', help = wording.get('help.run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_uis_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('run', help = wording.get('help.run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_uis_program(), create_benchmark_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('headless-run', help = wording.get('help.headless_run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('batch-run', help = wording.get('help.batch_run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_pattern_program(), create_target_pattern_program(), create_output_pattern_program(), collect_step_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('force-download', help = wording.get('help.force_download'), parents = [ create_download_providers_program(), create_download_scope_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('force-download', help = wording.get('help.force_download'), parents = [ create_download_providers_program(), create_download_scope_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('benchmark', help = wording.get('help.benchmark'), parents = [ create_temp_path_program(), collect_step_program(), create_benchmark_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
 	# job manager
-	sub_program.add_parser('job-list', help = wording.get('help.job_list'), parents = [ create_job_status_program(), create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-create', help = wording.get('help.job_create'), parents = [ create_job_id_program(), create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-submit', help = wording.get('help.job_submit'), parents = [ create_job_id_program(), create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-submit-all', help = wording.get('help.job_submit_all'), parents = [ create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-delete', help = wording.get('help.job_delete'), parents = [ create_job_id_program(), create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-delete-all', help = wording.get('help.job_delete_all'), parents = [ create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-add-step', help = wording.get('help.job_add_step'), parents = [ create_job_id_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-remix-step', help = wording.get('help.job_remix_step'), parents = [ create_job_id_program(), create_step_index_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_output_path_program(), collect_step_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-insert-step', help = wording.get('help.job_insert_step'), parents = [ create_job_id_program(), create_step_index_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-remove-step', help = wording.get('help.job_remove_step'), parents = [ create_job_id_program(), create_step_index_program(), create_jobs_path_program(), create_misc_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-list', help = wording.get('help.job_list'), parents = [ create_job_status_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-create', help = wording.get('help.job_create'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-submit', help = wording.get('help.job_submit'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-submit-all', help = wording.get('help.job_submit_all'), parents = [ create_jobs_path_program(), create_log_level_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-delete', help = wording.get('help.job_delete'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-delete-all', help = wording.get('help.job_delete_all'), parents = [ create_jobs_path_program(), create_log_level_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-add-step', help = wording.get('help.job_add_step'), parents = [ create_job_id_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-remix-step', help = wording.get('help.job_remix_step'), parents = [ create_job_id_program(), create_step_index_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_output_path_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-insert-step', help = wording.get('help.job_insert_step'), parents = [ create_job_id_program(), create_step_index_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-remove-step', help = wording.get('help.job_remove_step'), parents = [ create_job_id_program(), create_step_index_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
 	# job runner
 	sub_program.add_parser('job-run', help = wording.get('help.job_run'), parents = [ create_job_id_program(), create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-run-all', help = wording.get('help.job_run_all'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-run-all', help = wording.get('help.job_run_all'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('job-retry', help = wording.get('help.job_retry'), parents = [ create_job_id_program(), create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-retry-all', help = wording.get('help.job_retry_all'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	return ArgumentParser(parents = [ program ], formatter_class = create_help_formatter_small, add_help = True)
+	sub_program.add_parser('job-retry-all', help = wording.get('help.job_retry_all'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
+	return ArgumentParser(parents = [ program ], formatter_class = create_help_formatter_small)
 
 
 def apply_config_path(program : ArgumentParser) -> None:

facefusion/state_manager.py

@@ -1,37 +1,41 @@
 from typing import Any, Union
 
 from facefusion.app_context import detect_app_context
-from facefusion.processors.typing import ProcessorState, ProcessorStateKey
-from facefusion.typing import State, StateKey, StateSet
+from facefusion.processors.types import ProcessorState, ProcessorStateKey, ProcessorStateSet
+from facefusion.types import State, StateKey, StateSet
 
-STATES : Union[StateSet, ProcessorState] =\
+STATE_SET : Union[StateSet, ProcessorStateSet] =\
 {
-	'cli': {}, #type:ignore[typeddict-item]
-	'ui': {} #type:ignore[typeddict-item]
+	'cli': {}, #type:ignore[assignment]
+	'ui': {} #type:ignore[assignment]
 }
 
 
 def get_state() -> Union[State, ProcessorState]:
 	app_context = detect_app_context()
-	return STATES.get(app_context) #type:ignore
+	return STATE_SET.get(app_context)
+
+
+def sync_state() -> None:
+	STATE_SET['cli'] = STATE_SET.get('ui') #type:ignore[assignment]
 
 
 def init_item(key : Union[StateKey, ProcessorStateKey], value : Any) -> None:
-	STATES['cli'][key] = value #type:ignore
-	STATES['ui'][key] = value #type:ignore
+	STATE_SET['cli'][key] = value #type:ignore[literal-required]
+	STATE_SET['ui'][key] = value #type:ignore[literal-required]
 
 
 def get_item(key : Union[StateKey, ProcessorStateKey]) -> Any:
-	return get_state().get(key) #type:ignore
+	return get_state().get(key) #type:ignore[literal-required]
 
 
 def set_item(key : Union[StateKey, ProcessorStateKey], value : Any) -> None:
 	app_context = detect_app_context()
-	STATES[app_context][key] = value #type:ignore
+	STATE_SET[app_context][key] = value #type:ignore[literal-required]
 
 
 def sync_item(key : Union[StateKey, ProcessorStateKey]) -> None:
-	STATES['cli'][key] = STATES.get('ui').get(key) #type:ignore
+	STATE_SET['cli'][key] = STATE_SET.get('ui').get(key) #type:ignore[literal-required]
 
 
 def clear_item(key : Union[StateKey, ProcessorStateKey]) -> None:

facefusion/statistics.py

@@ -1,51 +0,0 @@
-from typing import Any, Dict
-
-import numpy
-
-from facefusion import logger, state_manager
-from facefusion.face_store import get_face_store
-from facefusion.typing import FaceSet
-
-
-def create_statistics(static_faces : FaceSet) -> Dict[str, Any]:
-	face_detector_scores = []
-	face_landmarker_scores = []
-	statistics =\
-	{
-		'min_face_detector_score': 0,
-		'min_face_landmarker_score': 0,
-		'max_face_detector_score': 0,
-		'max_face_landmarker_score': 0,
-		'average_face_detector_score': 0,
-		'average_face_landmarker_score': 0,
-		'total_face_landmark_5_fallbacks': 0,
-		'total_frames_with_faces': 0,
-		'total_faces': 0
-	}
-
-	for faces in static_faces.values():
-		statistics['total_frames_with_faces'] = statistics.get('total_frames_with_faces') + 1
-		for face in faces:
-			statistics['total_faces'] = statistics.get('total_faces') + 1
-			face_detector_scores.append(face.score_set.get('detector'))
-			face_landmarker_scores.append(face.score_set.get('landmarker'))
-			if numpy.array_equal(face.landmark_set.get('5'), face.landmark_set.get('5/68')):
-				statistics['total_face_landmark_5_fallbacks'] = statistics.get('total_face_landmark_5_fallbacks') + 1
-
-	if face_detector_scores:
-		statistics['min_face_detector_score'] = round(min(face_detector_scores), 2)
-		statistics['max_face_detector_score'] = round(max(face_detector_scores), 2)
-		statistics['average_face_detector_score'] = round(numpy.mean(face_detector_scores), 2)
-	if face_landmarker_scores:
-		statistics['min_face_landmarker_score'] = round(min(face_landmarker_scores), 2)
-		statistics['max_face_landmarker_score'] = round(max(face_landmarker_scores), 2)
-		statistics['average_face_landmarker_score'] = round(numpy.mean(face_landmarker_scores), 2)
-	return statistics
-
-
-def conditional_log_statistics() -> None:
-	if state_manager.get_item('log_level') == 'debug':
-		statistics = create_statistics(get_face_store().get('static_faces'))
-
-		for name, value in statistics.items():
-			logger.debug(str(name) + ': ' + str(value), __name__)

facefusion/streamer.py

@@ -0,0 +1,98 @@
+import os
+import subprocess
+from collections import deque
+from concurrent.futures import ThreadPoolExecutor
+from typing import Deque, Generator
+
+import cv2
+import numpy
+from tqdm import tqdm
+
+from facefusion import ffmpeg_builder, logger, state_manager, wording
+from facefusion.audio import create_empty_audio_frame
+from facefusion.content_analyser import analyse_stream
+from facefusion.ffmpeg import open_ffmpeg
+from facefusion.filesystem import is_directory
+from facefusion.processors.core import get_processors_modules
+from facefusion.types import Fps, StreamMode, VisionFrame
+from facefusion.vision import read_static_images
+
+
+def multi_process_capture(camera_capture : cv2.VideoCapture, camera_fps : Fps) -> Generator[VisionFrame, None, None]:
+	capture_deque : Deque[VisionFrame] = deque()
+
+	with tqdm(desc = wording.get('streaming'), unit = 'frame', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+		with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
+			futures = []
+
+			while camera_capture and camera_capture.isOpened():
+				_, capture_frame = camera_capture.read()
+				if analyse_stream(capture_frame, camera_fps):
+					camera_capture.release()
+
+				if numpy.any(capture_frame):
+					future = executor.submit(process_stream_frame, capture_frame)
+					futures.append(future)
+
+				for future_done in [ future for future in futures if future.done() ]:
+					capture_frame = future_done.result()
+					capture_deque.append(capture_frame)
+					futures.remove(future_done)
+
+				while capture_deque:
+					progress.update()
+					yield capture_deque.popleft()
+
+
+def process_stream_frame(target_vision_frame : VisionFrame) -> VisionFrame:
+	source_vision_frames = read_static_images(state_manager.get_item('source_paths'))
+	source_audio_frame = create_empty_audio_frame()
+	source_voice_frame = create_empty_audio_frame()
+	temp_vision_frame = target_vision_frame.copy()
+
+	for processor_module in get_processors_modules(state_manager.get_item('processors')):
+		logger.disable()
+		if processor_module.pre_process('stream'):
+			logger.enable()
+			temp_vision_frame = processor_module.process_frame(
+			{
+				'source_vision_frames': source_vision_frames,
+				'source_audio_frame': source_audio_frame,
+				'source_voice_frame': source_voice_frame,
+				'target_vision_frame': target_vision_frame,
+				'temp_vision_frame': temp_vision_frame
+			})
+		logger.enable()
+
+	return temp_vision_frame
+
+
+def open_stream(stream_mode : StreamMode, stream_resolution : str, stream_fps : Fps) -> subprocess.Popen[bytes]:
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.capture_video(),
+		ffmpeg_builder.set_media_resolution(stream_resolution),
+		ffmpeg_builder.set_input_fps(stream_fps)
+	)
+
+	if stream_mode == 'udp':
+		commands.extend(ffmpeg_builder.set_input('-'))
+		commands.extend(ffmpeg_builder.set_stream_mode('udp'))
+		commands.extend(ffmpeg_builder.set_stream_quality(2000))
+		commands.extend(ffmpeg_builder.set_output('udp://localhost:27000?pkt_size=1316'))
+
+	if stream_mode == 'v4l2':
+		device_directory_path = '/sys/devices/virtual/video4linux'
+		commands.extend(ffmpeg_builder.set_input('-'))
+		commands.extend(ffmpeg_builder.set_stream_mode('v4l2'))
+
+		if is_directory(device_directory_path):
+			device_names = os.listdir(device_directory_path)
+
+			for device_name in device_names:
+				device_path = '/dev/' + device_name
+				commands.extend(ffmpeg_builder.set_output(device_path))
+
+		else:
+			logger.error(wording.get('stream_not_loaded').format(stream_mode = stream_mode), __name__)
+
+	return open_ffmpeg(commands)

facefusion/temp_helper.py

@@ -2,12 +2,12 @@ import os
 from typing import List
 
 from facefusion import state_manager
-from facefusion.filesystem import create_directory, move_file, remove_directory, resolve_file_pattern
+from facefusion.filesystem import create_directory, get_file_extension, get_file_name, move_file, remove_directory, resolve_file_pattern
 
 
 def get_temp_file_path(file_path : str) -> str:
-	_, temp_file_extension = os.path.splitext(os.path.basename(file_path))
 	temp_directory_path = get_temp_directory_path(file_path)
+	temp_file_extension = get_file_extension(file_path)
 	return os.path.join(temp_directory_path, 'temp' + temp_file_extension)
 
 
@@ -16,8 +16,18 @@ def move_temp_file(file_path : str, move_path : str) -> bool:
 	return move_file(temp_file_path, move_path)
 
 
+def resolve_temp_frame_paths(target_path : str) -> List[str]:
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '*')
+	return resolve_file_pattern(temp_frames_pattern)
+
+
+def get_temp_frames_pattern(target_path : str, temp_frame_prefix : str) -> str:
+	temp_directory_path = get_temp_directory_path(target_path)
+	return os.path.join(temp_directory_path, temp_frame_prefix + '.' + state_manager.get_item('temp_frame_format'))
+
+
 def get_temp_directory_path(file_path : str) -> str:
-	temp_file_name, _ = os.path.splitext(os.path.basename(file_path))
+	temp_file_name = get_file_name(file_path)
 	return os.path.join(state_manager.get_item('temp_path'), 'facefusion', temp_file_name)
 
 
@@ -31,13 +41,3 @@ def clear_temp_directory(file_path : str) -> bool:
 		temp_directory_path = get_temp_directory_path(file_path)
 		return remove_directory(temp_directory_path)
 	return True
-
-
-def get_temp_frame_paths(target_path : str) -> List[str]:
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '*')
-	return resolve_file_pattern(temp_frames_pattern)
-
-
-def get_temp_frames_pattern(target_path : str, temp_frame_prefix : str) -> str:
-	temp_directory_path = get_temp_directory_path(target_path)
-	return os.path.join(temp_directory_path, temp_frame_prefix + '.' + state_manager.get_item('temp_frame_format'))

facefusion/thread_helper.py

@@ -2,6 +2,7 @@ import threading
 from contextlib import nullcontext
 from typing import ContextManager, Union
 
+from facefusion.common_helper import is_linux, is_windows
 from facefusion.execution import has_execution_provider
 
 THREAD_LOCK : threading.Lock = threading.Lock()
@@ -18,6 +19,6 @@ def thread_semaphore() -> threading.Semaphore:
 
 
 def conditional_thread_semaphore() -> Union[threading.Semaphore, ContextManager[None]]:
-	if has_execution_provider('directml') or has_execution_provider('rocm'):
+	if is_windows() and has_execution_provider('directml') or is_linux() and has_execution_provider('migraphx') or is_linux() and has_execution_provider('rocm'):
 		return THREAD_SEMAPHORE
 	return NULL_CONTEXT

facefusion/time_helper.py

@@ -1,4 +1,5 @@
 from datetime import datetime, timedelta
+from time import time
 from typing import Optional, Tuple
 
 from facefusion import wording
@@ -8,6 +9,10 @@ def get_current_date_time() -> datetime:
 	return datetime.now().astimezone()
 
 
+def calculate_end_time(start_time : float) -> float:
+	return round(time() - start_time, 2)
+
+
 def split_time_delta(time_delta : timedelta) -> Tuple[int, int, int, int]:
 	days, hours = divmod(time_delta.total_seconds(), 86400)
 	hours, minutes = divmod(hours, 3600)

facefusion/types.py

@@ -1,20 +1,21 @@
 from collections import namedtuple
-from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, TypedDict
+from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, TypeAlias, TypedDict
 
+import cv2
 import numpy
 from numpy.typing import NDArray
 from onnxruntime import InferenceSession
 
-Scale = float
-Score = float
-Angle = int
+Scale : TypeAlias = float
+Score : TypeAlias = float
+Angle : TypeAlias = int
 
-Detection = NDArray[Any]
-Prediction = NDArray[Any]
+Detection : TypeAlias = NDArray[Any]
+Prediction : TypeAlias = NDArray[Any]
 
-BoundingBox = NDArray[Any]
-FaceLandmark5 = NDArray[Any]
-FaceLandmark68 = NDArray[Any]
+BoundingBox : TypeAlias = NDArray[Any]
+FaceLandmark5 : TypeAlias = NDArray[Any]
+FaceLandmark68 : TypeAlias = NDArray[Any]
 FaceLandmarkSet = TypedDict('FaceLandmarkSet',
 {
 	'5' : FaceLandmark5, #type:ignore[valid-type]
@@ -27,9 +28,9 @@ FaceScoreSet = TypedDict('FaceScoreSet',
 	'detector' : Score,
 	'landmarker' : Score
 })
-Embedding = NDArray[numpy.float64]
+Embedding : TypeAlias = NDArray[numpy.float64]
 Gender = Literal['female', 'male']
-Age = range
+Age : TypeAlias = range
 Race = Literal['white', 'black', 'latino', 'asian', 'indian', 'arabic']
 Face = namedtuple('Face',
 [
@@ -38,86 +39,130 @@ Face = namedtuple('Face',
 	'landmark_set',
 	'angle',
 	'embedding',
-	'normed_embedding',
+	'embedding_norm',
 	'gender',
 	'age',
 	'race'
 ])
-FaceSet = Dict[str, List[Face]]
+FaceSet : TypeAlias = Dict[str, List[Face]]
 FaceStore = TypedDict('FaceStore',
 {
-	'static_faces' : FaceSet,
-	'reference_faces' : FaceSet
+	'static_faces' : FaceSet
 })
 
-VisionFrame = NDArray[Any]
-Mask = NDArray[Any]
-Points = NDArray[Any]
-Distance = NDArray[Any]
-Matrix = NDArray[Any]
-Anchors = NDArray[Any]
-Translation = NDArray[Any]
+VideoCaptureSet : TypeAlias = Dict[str, cv2.VideoCapture]
+VideoWriterSet : TypeAlias = Dict[str, cv2.VideoWriter]
+CameraCaptureSet : TypeAlias = Dict[str, cv2.VideoCapture]
+VideoPoolSet = TypedDict('VideoPoolSet',
+{
+	'capture': VideoCaptureSet,
+	'writer': VideoWriterSet
+})
+CameraPoolSet = TypedDict('CameraPoolSet',
+{
+	'capture': CameraCaptureSet
+})
 
-AudioBuffer = bytes
-Audio = NDArray[Any]
-AudioChunk = NDArray[Any]
-AudioFrame = NDArray[Any]
-Spectrogram = NDArray[Any]
-Mel = NDArray[Any]
-MelFilterBank = NDArray[Any]
+VisionFrame : TypeAlias = NDArray[Any]
+Mask : TypeAlias = NDArray[Any]
+Points : TypeAlias = NDArray[Any]
+Distance : TypeAlias = NDArray[Any]
+Matrix : TypeAlias = NDArray[Any]
+Anchors : TypeAlias = NDArray[Any]
+Translation : TypeAlias = NDArray[Any]
 
-Fps = float
-Duration = float
-Padding = Tuple[int, int, int, int]
+AudioBuffer : TypeAlias = bytes
+Audio : TypeAlias = NDArray[Any]
+AudioChunk : TypeAlias = NDArray[Any]
+AudioFrame : TypeAlias = NDArray[Any]
+Spectrogram : TypeAlias = NDArray[Any]
+Mel : TypeAlias = NDArray[Any]
+MelFilterBank : TypeAlias = NDArray[Any]
+Voice : TypeAlias = NDArray[Any]
+VoiceChunk : TypeAlias = NDArray[Any]
+
+Fps : TypeAlias = float
+Duration : TypeAlias = float
+Padding : TypeAlias = Tuple[int, int, int, int]
 Orientation = Literal['landscape', 'portrait']
-Resolution = Tuple[int, int]
+Resolution : TypeAlias = Tuple[int, int]
 
 ProcessState = Literal['checking', 'processing', 'stopping', 'pending']
-QueuePayload = TypedDict('QueuePayload',
-{
-	'frame_number' : int,
-	'frame_path' : str
-})
-Args = Dict[str, Any]
-UpdateProgress = Callable[[int], None]
-ProcessFrames = Callable[[List[str], List[QueuePayload], UpdateProgress], None]
-ProcessStep = Callable[[str, int, Args], bool]
+Args : TypeAlias = Dict[str, Any]
+UpdateProgress : TypeAlias = Callable[[int], None]
+ProcessStep : TypeAlias = Callable[[str, int, Args], bool]
 
-Content = Dict[str, Any]
+Content : TypeAlias = Dict[str, Any]
 
-WarpTemplate = Literal['arcface_112_v1', 'arcface_112_v2', 'arcface_128_v2', 'dfl_whole_face', 'ffhq_512', 'mtcnn_512', 'styleganex_384']
-WarpTemplateSet = Dict[WarpTemplate, NDArray[Any]]
+Commands : TypeAlias = List[str]
+
+WarpTemplate = Literal['arcface_112_v1', 'arcface_112_v2', 'arcface_128', 'dfl_whole_face', 'ffhq_512', 'mtcnn_512', 'styleganex_384']
+WarpTemplateSet : TypeAlias = Dict[WarpTemplate, NDArray[Any]]
 ProcessMode = Literal['output', 'preview', 'stream']
 
 ErrorCode = Literal[0, 1, 2, 3, 4]
 LogLevel = Literal['error', 'warn', 'info', 'debug']
-LogLevelSet = Dict[LogLevel, int]
+LogLevelSet : TypeAlias = Dict[LogLevel, int]
 
 TableHeaders = List[str]
 TableContents = List[List[Any]]
 
-FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yoloface']
+FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yolo_face', 'yunet']
 FaceLandmarkerModel = Literal['many', '2dfan4', 'peppa_wutz']
-FaceDetectorSet = Dict[FaceDetectorModel, List[str]]
+FaceDetectorSet : TypeAlias = Dict[FaceDetectorModel, List[str]]
 FaceSelectorMode = Literal['many', 'one', 'reference']
 FaceSelectorOrder = Literal['left-right', 'right-left', 'top-bottom', 'bottom-top', 'small-large', 'large-small', 'best-worst', 'worst-best']
-FaceOccluderModel = Literal['xseg_1', 'xseg_2']
+FaceOccluderModel = Literal['many', 'xseg_1', 'xseg_2', 'xseg_3']
 FaceParserModel = Literal['bisenet_resnet_18', 'bisenet_resnet_34']
-FaceMaskType = Literal['box', 'occlusion', 'region']
+FaceMaskType = Literal['box', 'occlusion', 'area', 'region']
+FaceMaskArea = Literal['upper-face', 'lower-face', 'mouth']
 FaceMaskRegion = Literal['skin', 'left-eyebrow', 'right-eyebrow', 'left-eye', 'right-eye', 'glasses', 'nose', 'mouth', 'upper-lip', 'lower-lip']
-FaceMaskRegionSet = Dict[FaceMaskRegion, int]
-TempFrameFormat = Literal['bmp', 'jpg', 'png']
-OutputAudioEncoder = Literal['aac', 'libmp3lame', 'libopus', 'libvorbis']
-OutputVideoEncoder = Literal['libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf','h264_qsv', 'hevc_qsv', 'h264_videotoolbox', 'hevc_videotoolbox']
-OutputVideoPreset = Literal['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow']
+FaceMaskRegionSet : TypeAlias = Dict[FaceMaskRegion, int]
+FaceMaskAreaSet : TypeAlias = Dict[FaceMaskArea, List[int]]
 
-ModelOptions = Dict[str, Any]
-ModelSet = Dict[str, ModelOptions]
-ModelInitializer = NDArray[Any]
+VoiceExtractorModel = Literal['kim_vocal_1', 'kim_vocal_2', 'uvr_mdxnet']
 
-ExecutionProvider = Literal['cpu', 'coreml', 'cuda', 'directml', 'openvino', 'rocm', 'tensorrt']
-ExecutionProviderValue = Literal['CPUExecutionProvider', 'CoreMLExecutionProvider', 'CUDAExecutionProvider', 'DmlExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'TensorrtExecutionProvider']
-ExecutionProviderSet = Dict[ExecutionProvider, ExecutionProviderValue]
+AudioFormat = Literal['flac', 'm4a', 'mp3', 'ogg', 'opus', 'wav']
+ImageFormat = Literal['bmp', 'jpeg', 'png', 'tiff', 'webp']
+VideoFormat = Literal['avi', 'm4v', 'mkv', 'mov', 'mp4', 'webm', 'wmv']
+TempFrameFormat = Literal['bmp', 'jpeg', 'png', 'tiff']
+AudioTypeSet : TypeAlias = Dict[AudioFormat, str]
+ImageTypeSet : TypeAlias = Dict[ImageFormat, str]
+VideoTypeSet : TypeAlias = Dict[VideoFormat, str]
+
+AudioEncoder = Literal['flac', 'aac', 'libmp3lame', 'libopus', 'libvorbis', 'pcm_s16le', 'pcm_s32le']
+VideoEncoder = Literal['libx264', 'libx264rgb', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_qsv', 'hevc_qsv', 'h264_videotoolbox', 'hevc_videotoolbox', 'rawvideo']
+EncoderSet = TypedDict('EncoderSet',
+{
+	'audio' : List[AudioEncoder],
+	'video' : List[VideoEncoder]
+})
+VideoPreset = Literal['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow']
+
+BenchmarkMode = Literal['warm', 'cold']
+BenchmarkResolution = Literal['240p', '360p', '540p', '720p', '1080p', '1440p', '2160p']
+BenchmarkSet : TypeAlias = Dict[BenchmarkResolution, str]
+BenchmarkCycleSet = TypedDict('BenchmarkCycleSet',
+{
+	'target_path' : str,
+	'cycle_count' : int,
+	'average_run' : float,
+	'fastest_run' : float,
+	'slowest_run' : float,
+	'relative_fps' : float
+})
+
+WebcamMode = Literal['inline', 'udp', 'v4l2']
+StreamMode = Literal['udp', 'v4l2']
+
+ModelOptions : TypeAlias = Dict[str, Any]
+ModelSet : TypeAlias = Dict[str, ModelOptions]
+ModelInitializer : TypeAlias = NDArray[Any]
+
+ExecutionProvider = Literal['cpu', 'coreml', 'cuda', 'directml', 'openvino', 'migraphx', 'rocm', 'tensorrt']
+ExecutionProviderValue = Literal['CPUExecutionProvider', 'CoreMLExecutionProvider', 'CUDAExecutionProvider', 'DmlExecutionProvider', 'OpenVINOExecutionProvider', 'MIGraphXExecutionProvider', 'ROCMExecutionProvider', 'TensorrtExecutionProvider']
+ExecutionProviderSet : TypeAlias = Dict[ExecutionProvider, ExecutionProviderValue]
+InferenceSessionProvider : TypeAlias = Any
 ValueAndUnit = TypedDict('ValueAndUnit',
 {
 	'value' : int,
@@ -154,38 +199,30 @@ ExecutionDevice = TypedDict('ExecutionDevice',
 	'framework' : ExecutionDeviceFramework,
 	'product' : ExecutionDeviceProduct,
 	'video_memory' : ExecutionDeviceVideoMemory,
-	'temperature': ExecutionDeviceTemperature,
+	'temperature' : ExecutionDeviceTemperature,
 	'utilization' : ExecutionDeviceUtilization
 })
 
 DownloadProvider = Literal['github', 'huggingface']
 DownloadProviderValue = TypedDict('DownloadProviderValue',
 {
-	'url' : str,
+	'urls' : List[str],
 	'path' : str
 })
-DownloadProviderSet = Dict[DownloadProvider, DownloadProviderValue]
+DownloadProviderSet : TypeAlias = Dict[DownloadProvider, DownloadProviderValue]
 DownloadScope = Literal['lite', 'full']
 Download = TypedDict('Download',
 {
 	'url' : str,
 	'path' : str
 })
-DownloadSet = Dict[str, Download]
+DownloadSet : TypeAlias = Dict[str, Download]
 
 VideoMemoryStrategy = Literal['strict', 'moderate', 'tolerant']
-
-File = TypedDict('File',
-{
-	'name' : str,
-	'extension' : str,
-	'path': str
-})
-
 AppContext = Literal['cli', 'ui']
 
-InferencePool = Dict[str, InferenceSession]
-InferencePoolSet = Dict[AppContext, Dict[str, InferencePool]]
+InferencePool : TypeAlias = Dict[str, InferenceSession]
+InferencePoolSet : TypeAlias = Dict[AppContext, Dict[str, InferencePool]]
 
 UiWorkflow = Literal['instant_runner', 'job_runner', 'job_manager']
 
@@ -194,7 +231,7 @@ JobStore = TypedDict('JobStore',
 	'job_keys' : List[str],
 	'step_keys' : List[str]
 })
-JobOutputSet = Dict[str, List[str]]
+JobOutputSet : TypeAlias = Dict[str, List[str]]
 JobStatus = Literal['drafted', 'queued', 'completed', 'failed']
 JobStepStatus = Literal['drafted', 'queued', 'started', 'completed', 'failed']
 JobStep = TypedDict('JobStep',
@@ -209,9 +246,8 @@ Job = TypedDict('Job',
 	'date_updated' : Optional[str],
 	'steps' : List[JobStep]
 })
-JobSet = Dict[str, Job]
+JobSet : TypeAlias = Dict[str, Job]
 
-ApplyStateItem = Callable[[Any, Any], None]
 StateKey = Literal\
 [
 	'command',
@@ -224,6 +260,11 @@ StateKey = Literal\
 	'source_pattern',
 	'target_pattern',
 	'output_pattern',
+	'download_providers',
+	'download_scope',
+	'benchmark_mode',
+	'benchmark_resolutions',
+	'benchmark_cycle_count',
 	'face_detector_model',
 	'face_detector_size',
 	'face_detector_angles',
@@ -242,35 +283,36 @@ StateKey = Literal\
 	'face_occluder_model',
 	'face_parser_model',
 	'face_mask_types',
+	'face_mask_areas',
+	'face_mask_regions',
 	'face_mask_blur',
 	'face_mask_padding',
-	'face_mask_regions',
+	'voice_extractor_model',
 	'trim_frame_start',
 	'trim_frame_end',
 	'temp_frame_format',
 	'keep_temp',
 	'output_image_quality',
-	'output_image_resolution',
+	'output_image_scale',
 	'output_audio_encoder',
+	'output_audio_quality',
+	'output_audio_volume',
 	'output_video_encoder',
 	'output_video_preset',
 	'output_video_quality',
-	'output_video_resolution',
+	'output_video_scale',
 	'output_video_fps',
-	'skip_audio',
 	'processors',
 	'open_browser',
 	'ui_layouts',
 	'ui_workflow',
-	'execution_device_id',
+	'execution_device_ids',
 	'execution_providers',
 	'execution_thread_count',
-	'execution_queue_count',
-	'download_providers',
-	'download_scope',
 	'video_memory_strategy',
 	'system_memory_limit',
 	'log_level',
+	'halt_on_error',
 	'job_id',
 	'job_status',
 	'step_index'
@@ -287,6 +329,11 @@ State = TypedDict('State',
 	'source_pattern' : str,
 	'target_pattern' : str,
 	'output_pattern' : str,
+	'download_providers' : List[DownloadProvider],
+	'download_scope' : DownloadScope,
+	'benchmark_mode' : BenchmarkMode,
+	'benchmark_resolutions' : List[BenchmarkResolution],
+	'benchmark_cycle_count' : int,
 	'face_detector_model' : FaceDetectorModel,
 	'face_detector_size' : str,
 	'face_detector_angles' : List[Angle],
@@ -305,37 +352,40 @@ State = TypedDict('State',
 	'face_occluder_model' : FaceOccluderModel,
 	'face_parser_model' : FaceParserModel,
 	'face_mask_types' : List[FaceMaskType],
+	'face_mask_areas' : List[FaceMaskArea],
+	'face_mask_regions' : List[FaceMaskRegion],
 	'face_mask_blur' : float,
 	'face_mask_padding' : Padding,
-	'face_mask_regions' : List[FaceMaskRegion],
+	'voice_extractor_model': VoiceExtractorModel,
 	'trim_frame_start' : int,
 	'trim_frame_end' : int,
 	'temp_frame_format' : TempFrameFormat,
 	'keep_temp' : bool,
 	'output_image_quality' : int,
-	'output_image_resolution' : str,
-	'output_audio_encoder' : OutputAudioEncoder,
-	'output_video_encoder' : OutputVideoEncoder,
-	'output_video_preset' : OutputVideoPreset,
+	'output_image_scale' : Scale,
+	'output_audio_encoder' : AudioEncoder,
+	'output_audio_quality' : int,
+	'output_audio_volume' : int,
+	'output_video_encoder' : VideoEncoder,
+	'output_video_preset' : VideoPreset,
 	'output_video_quality' : int,
-	'output_video_resolution' : str,
+	'output_video_scale' : Scale,
 	'output_video_fps' : float,
-	'skip_audio' : bool,
 	'processors' : List[str],
 	'open_browser' : bool,
 	'ui_layouts' : List[str],
 	'ui_workflow' : UiWorkflow,
-	'execution_device_id' : str,
+	'execution_device_ids' : List[str],
 	'execution_providers' : List[ExecutionProvider],
 	'execution_thread_count' : int,
-	'execution_queue_count' : int,
-	'download_providers' : List[DownloadProvider],
-	'download_scope' : DownloadScope,
 	'video_memory_strategy' : VideoMemoryStrategy,
 	'system_memory_limit' : int,
 	'log_level' : LogLevel,
+	'halt_on_error' : bool,
 	'job_id' : str,
 	'job_status' : JobStatus,
 	'step_index' : int
 })
-StateSet = Dict[AppContext, State]
+ApplyStateItem : TypeAlias = Callable[[Any, Any], None]
+StateSet : TypeAlias = Dict[AppContext, State]
+

facefusion/uis/assets/overrides.css

@@ -1,9 +1,13 @@
 :root:root:root:root .gradio-container
 {
-	max-width: 110em;
 	overflow: unset;
 }
 
+:root:root:root:root main
+{
+	max-width: 110em;
+}
+
 :root:root:root:root input[type="number"]
 {
 	appearance: textfield;
@@ -65,6 +69,12 @@
 	min-height: unset;
 }
 
+:root:root:root:root .box-face-selector .empty,
+:root:root:root:root .box-face-selector .gallery-container
+{
+	min-height: 7.375rem;
+}
+
 :root:root:root:root .tab-wrapper
 {
 	padding: 0 0.625rem;

facefusion/uis/choices.py

@@ -1,11 +1,15 @@
 from typing import List
 
-from facefusion.uis.typing import JobManagerAction, JobRunnerAction, WebcamMode
+from facefusion.types import WebcamMode
+from facefusion.uis.types import JobManagerAction, JobRunnerAction, PreviewMode
 
 job_manager_actions : List[JobManagerAction] = [ 'job-create', 'job-submit', 'job-delete', 'job-add-step', 'job-remix-step', 'job-insert-step', 'job-remove-step' ]
 job_runner_actions : List[JobRunnerAction] = [ 'job-run', 'job-run-all', 'job-retry', 'job-retry-all' ]
 
-common_options : List[str] = [ 'keep-temp', 'skip-audio' ]
+common_options : List[str] = [ 'keep-temp' ]
+
+preview_modes : List[PreviewMode] = [ 'default', 'frame-by-frame', 'face-by-face' ]
+preview_resolutions : List[str] = [ '512x512', '768x768', '1024x1024' ]
 
 webcam_modes : List[WebcamMode] = [ 'inline', 'udp', 'v4l2' ]
-webcam_resolutions : List[str] = [ '320x240', '640x480', '800x600', '1024x768', '1280x720', '1280x960', '1920x1080', '2560x1440', '3840x2160' ]
+webcam_resolutions : List[str] = [ '320x240', '640x480', '800x600', '1024x768', '1280x720', '1280x960', '1920x1080' ]

facefusion/uis/components/age_modifier_options.py

@@ -3,10 +3,10 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_float_step
+from facefusion.common_helper import calculate_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import AgeModifierModel
+from facefusion.processors.types import AgeModifierModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 AGE_MODIFIER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -27,7 +27,7 @@ def render() -> None:
 	AGE_MODIFIER_DIRECTION_SLIDER = gradio.Slider(
 		label = wording.get('uis.age_modifier_direction_slider'),
 		value = state_manager.get_item('age_modifier_direction'),
-		step = calc_float_step(processors_choices.age_modifier_direction_range),
+		step = calculate_float_step(processors_choices.age_modifier_direction_range),
 		minimum = processors_choices.age_modifier_direction_range[0],
 		maximum = processors_choices.age_modifier_direction_range[-1],
 		visible = has_age_modifier

facefusion/uis/components/benchmark.py

@@ -1,44 +1,22 @@
-import hashlib
-import os
-import statistics
-import tempfile
-from time import perf_counter
-from typing import Any, Dict, Generator, List, Optional
+from typing import Any, Generator, List, Optional
 
 import gradio
 
-from facefusion import state_manager, wording
-from facefusion.core import conditional_process
-from facefusion.filesystem import is_video
-from facefusion.memory import limit_system_memory
-from facefusion.uis.core import get_ui_component
-from facefusion.vision import count_video_frame_total, detect_video_fps, detect_video_resolution, pack_resolution
+from facefusion import benchmarker, state_manager, wording
 
 BENCHMARK_BENCHMARKS_DATAFRAME : Optional[gradio.Dataframe] = None
 BENCHMARK_START_BUTTON : Optional[gradio.Button] = None
-BENCHMARK_CLEAR_BUTTON : Optional[gradio.Button] = None
-BENCHMARKS : Dict[str, str] =\
-{
-	'240p': '.assets/examples/target-240p.mp4',
-	'360p': '.assets/examples/target-360p.mp4',
-	'540p': '.assets/examples/target-540p.mp4',
-	'720p': '.assets/examples/target-720p.mp4',
-	'1080p': '.assets/examples/target-1080p.mp4',
-	'1440p': '.assets/examples/target-1440p.mp4',
-	'2160p': '.assets/examples/target-2160p.mp4'
-}
 
 
 def render() -> None:
 	global BENCHMARK_BENCHMARKS_DATAFRAME
 	global BENCHMARK_START_BUTTON
-	global BENCHMARK_CLEAR_BUTTON
 
 	BENCHMARK_BENCHMARKS_DATAFRAME = gradio.Dataframe(
 		headers =
 		[
 			'target_path',
-			'benchmark_cycles',
+			'cycle_count',
 			'average_run',
 			'fastest_run',
 			'slowest_run',
@@ -63,72 +41,11 @@ def render() -> None:
 
 
 def listen() -> None:
-	benchmark_runs_checkbox_group = get_ui_component('benchmark_runs_checkbox_group')
-	benchmark_cycles_slider = get_ui_component('benchmark_cycles_slider')
-
-	if benchmark_runs_checkbox_group and benchmark_cycles_slider:
-		BENCHMARK_START_BUTTON.click(start, inputs = [ benchmark_runs_checkbox_group, benchmark_cycles_slider ], outputs = BENCHMARK_BENCHMARKS_DATAFRAME)
+	BENCHMARK_START_BUTTON.click(start, outputs = BENCHMARK_BENCHMARKS_DATAFRAME)
 
 
-def suggest_output_path(target_path : str) -> Optional[str]:
-	if is_video(target_path):
-		_, target_extension = os.path.splitext(target_path)
-		return os.path.join(tempfile.gettempdir(), hashlib.sha1().hexdigest()[:8] + target_extension)
-	return None
+def start() -> Generator[List[Any], None, None]:
+	state_manager.sync_state()
 
-
-def start(benchmark_runs : List[str], benchmark_cycles : int) -> Generator[List[Any], None, None]:
-	state_manager.init_item('source_paths', [ '.assets/examples/source.jpg', '.assets/examples/source.mp3' ])
-	state_manager.init_item('face_landmarker_score', 0)
-	state_manager.init_item('temp_frame_format', 'bmp')
-	state_manager.init_item('output_video_preset', 'ultrafast')
-	state_manager.init_item('skip_audio', True)
-	state_manager.sync_item('execution_providers')
-	state_manager.sync_item('execution_thread_count')
-	state_manager.sync_item('execution_queue_count')
-	state_manager.sync_item('system_memory_limit')
-	benchmark_results = []
-	target_paths = [ BENCHMARKS[benchmark_run] for benchmark_run in benchmark_runs if benchmark_run in BENCHMARKS ]
-
-	if target_paths:
-		pre_process()
-		for target_path in target_paths:
-			state_manager.init_item('target_path', target_path)
-			state_manager.init_item('output_path', suggest_output_path(state_manager.get_item('target_path')))
-			benchmark_results.append(benchmark(benchmark_cycles))
-			yield benchmark_results
-
-
-def pre_process() -> None:
-	system_memory_limit = state_manager.get_item('system_memory_limit')
-	if system_memory_limit and system_memory_limit > 0:
-		limit_system_memory(system_memory_limit)
-
-
-def benchmark(benchmark_cycles : int) -> List[Any]:
-	process_times = []
-	video_frame_total = count_video_frame_total(state_manager.get_item('target_path'))
-	output_video_resolution = detect_video_resolution(state_manager.get_item('target_path'))
-	state_manager.init_item('output_video_resolution', pack_resolution(output_video_resolution))
-	state_manager.init_item('output_video_fps', detect_video_fps(state_manager.get_item('target_path')))
-
-	conditional_process()
-	for index in range(benchmark_cycles):
-		start_time = perf_counter()
-		conditional_process()
-		end_time = perf_counter()
-		process_times.append(end_time - start_time)
-	average_run = round(statistics.mean(process_times), 2)
-	fastest_run = round(min(process_times), 2)
-	slowest_run = round(max(process_times), 2)
-	relative_fps = round(video_frame_total * benchmark_cycles / sum(process_times), 2)
-
-	return\
-	[
-		state_manager.get_item('target_path'),
-		benchmark_cycles,
-		average_run,
-		fastest_run,
-		slowest_run,
-		relative_fps
-	]
+	for benchmark in benchmarker.run():
+		yield [ list(benchmark_set.values()) for benchmark_set in benchmark ]

facefusion/uis/components/benchmark_options.py

@@ -1,30 +1,54 @@
-from typing import Optional
+from typing import List, Optional
 
 import gradio
 
-from facefusion import wording
-from facefusion.uis.components.benchmark import BENCHMARKS
-from facefusion.uis.core import register_ui_component
+import facefusion.choices
+from facefusion import state_manager, wording
+from facefusion.common_helper import calculate_int_step
+from facefusion.types import BenchmarkMode, BenchmarkResolution
 
-BENCHMARK_RUNS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
-BENCHMARK_CYCLES_SLIDER : Optional[gradio.Button] = None
+BENCHMARK_MODE_DROPDOWN : Optional[gradio.Dropdown] = None
+BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
+BENCHMARK_CYCLE_COUNT_SLIDER : Optional[gradio.Button] = None
 
 
 def render() -> None:
-	global BENCHMARK_RUNS_CHECKBOX_GROUP
-	global BENCHMARK_CYCLES_SLIDER
+	global BENCHMARK_MODE_DROPDOWN
+	global BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP
+	global BENCHMARK_CYCLE_COUNT_SLIDER
 
-	BENCHMARK_RUNS_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('uis.benchmark_runs_checkbox_group'),
-		choices = list(BENCHMARKS.keys()),
-		value = list(BENCHMARKS.keys())
+	BENCHMARK_MODE_DROPDOWN = gradio.Dropdown(
+		label = wording.get('uis.benchmark_mode_dropdown'),
+		choices = facefusion.choices.benchmark_modes,
+		value = state_manager.get_item('benchmark_mode')
 	)
-	BENCHMARK_CYCLES_SLIDER = gradio.Slider(
-		label = wording.get('uis.benchmark_cycles_slider'),
-		value = 5,
-		step = 1,
-		minimum = 1,
-		maximum = 10
+	BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.benchmark_resolutions_checkbox_group'),
+		choices = facefusion.choices.benchmark_resolutions,
+		value = state_manager.get_item('benchmark_resolutions')
 	)
-	register_ui_component('benchmark_runs_checkbox_group', BENCHMARK_RUNS_CHECKBOX_GROUP)
-	register_ui_component('benchmark_cycles_slider', BENCHMARK_CYCLES_SLIDER)
+	BENCHMARK_CYCLE_COUNT_SLIDER = gradio.Slider(
+		label = wording.get('uis.benchmark_cycle_count_slider'),
+		value = state_manager.get_item('benchmark_cycle_count'),
+		step = calculate_int_step(facefusion.choices.benchmark_cycle_count_range),
+		minimum = facefusion.choices.benchmark_cycle_count_range[0],
+		maximum = facefusion.choices.benchmark_cycle_count_range[-1]
+	)
+
+
+def listen() -> None:
+	BENCHMARK_MODE_DROPDOWN.change(update_benchmark_mode, inputs = BENCHMARK_MODE_DROPDOWN)
+	BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP.change(update_benchmark_resolutions, inputs = BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP)
+	BENCHMARK_CYCLE_COUNT_SLIDER.release(update_benchmark_cycle_count, inputs = BENCHMARK_CYCLE_COUNT_SLIDER)
+
+
+def update_benchmark_mode(benchmark_mode : BenchmarkMode) -> None:
+	state_manager.set_item('benchmark_mode', benchmark_mode)
+
+
+def update_benchmark_resolutions(benchmark_resolutions : List[BenchmarkResolution]) -> None:
+	state_manager.set_item('benchmark_resolutions', benchmark_resolutions)
+
+
+def update_benchmark_cycle_count(benchmark_cycle_count : int) -> None:
+	state_manager.set_item('benchmark_cycle_count', benchmark_cycle_count)

facefusion/uis/components/common_options.py

@@ -15,8 +15,6 @@ def render() -> None:
 
 	if state_manager.get_item('keep_temp'):
 		common_options.append('keep-temp')
-	if state_manager.get_item('skip_audio'):
-		common_options.append('skip-audio')
 
 	COMMON_OPTIONS_CHECKBOX_GROUP = gradio.Checkboxgroup(
 		label = wording.get('uis.common_options_checkbox_group'),
@@ -31,6 +29,4 @@ def listen() -> None:
 
 def update(common_options : List[str]) -> None:
 	keep_temp = 'keep-temp' in common_options
-	skip_audio = 'skip-audio' in common_options
 	state_manager.set_item('keep_temp', keep_temp)
-	state_manager.set_item('skip_audio', skip_audio)

facefusion/uis/components/deep_swapper_options.py

@@ -3,11 +3,10 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
+from facefusion.common_helper import calculate_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.modules.deep_swapper import has_morph_input
-from facefusion.processors.typing import DeepSwapperModel
+from facefusion.processors.types import DeepSwapperModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 DEEP_SWAPPER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -28,10 +27,10 @@ def render() -> None:
 	DEEP_SWAPPER_MORPH_SLIDER = gradio.Slider(
 		label = wording.get('uis.deep_swapper_morph_slider'),
 		value = state_manager.get_item('deep_swapper_morph'),
-		step = calc_int_step(processors_choices.deep_swapper_morph_range),
+		step = calculate_int_step(processors_choices.deep_swapper_morph_range),
 		minimum = processors_choices.deep_swapper_morph_range[0],
 		maximum = processors_choices.deep_swapper_morph_range[-1],
-		visible = has_deep_swapper and has_morph_input()
+		visible = has_deep_swapper and load_processor_module('deep_swapper').get_inference_pool() and load_processor_module('deep_swapper').has_morph_input()
 	)
 	register_ui_component('deep_swapper_model_dropdown', DEEP_SWAPPER_MODEL_DROPDOWN)
 	register_ui_component('deep_swapper_morph_slider', DEEP_SWAPPER_MORPH_SLIDER)
@@ -48,7 +47,7 @@ def listen() -> None:
 
 def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
 	has_deep_swapper = 'deep_swapper' in processors
-	return gradio.Dropdown(visible = has_deep_swapper), gradio.Slider(visible = has_deep_swapper and has_morph_input())
+	return gradio.Dropdown(visible = has_deep_swapper), gradio.Slider(visible = has_deep_swapper and load_processor_module('deep_swapper').get_inference_pool() and load_processor_module('deep_swapper').has_morph_input())
 
 
 def update_deep_swapper_model(deep_swapper_model : DeepSwapperModel) -> Tuple[gradio.Dropdown, gradio.Slider]:
@@ -57,7 +56,7 @@ def update_deep_swapper_model(deep_swapper_model : DeepSwapperModel) -> Tuple[gr
 	state_manager.set_item('deep_swapper_model', deep_swapper_model)
 
 	if deep_swapper_module.pre_check():
-		return gradio.Dropdown(value = state_manager.get_item('deep_swapper_model')), gradio.Slider(visible = has_morph_input())
+		return gradio.Dropdown(value = state_manager.get_item('deep_swapper_model')), gradio.Slider(visible = deep_swapper_module.has_morph_input())
 	return gradio.Dropdown(), gradio.Slider()
 
 

facefusion/uis/components/download.py

@@ -4,9 +4,9 @@ import gradio
 
 import facefusion.choices
 from facefusion import content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, state_manager, voice_extractor, wording
-from facefusion.filesystem import list_directory
+from facefusion.filesystem import get_file_name, resolve_file_paths
 from facefusion.processors.core import get_processors_modules
-from facefusion.typing import DownloadProvider
+from facefusion.types import DownloadProvider
 
 DOWNLOAD_PROVIDERS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 
@@ -36,7 +36,7 @@ def update_download_providers(download_providers : List[DownloadProvider]) -> gr
 		face_masker,
 		voice_extractor
 	]
-	available_processors = [ file.get('name') for file in list_directory('facefusion/processors/modules') ]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	processor_modules = get_processors_modules(available_processors)
 
 	for module in common_modules + processor_modules:

facefusion/uis/components/execution.py

@@ -4,9 +4,9 @@ import gradio
 
 from facefusion import content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, state_manager, voice_extractor, wording
 from facefusion.execution import get_available_execution_providers
-from facefusion.filesystem import list_directory
+from facefusion.filesystem import get_file_name, resolve_file_paths
 from facefusion.processors.core import get_processors_modules
-from facefusion.typing import ExecutionProvider
+from facefusion.types import ExecutionProvider
 
 EXECUTION_PROVIDERS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 
@@ -36,7 +36,7 @@ def update_execution_providers(execution_providers : List[ExecutionProvider]) ->
 		face_recognizer,
 		voice_extractor
 	]
-	available_processors = [ file.get('name') for file in list_directory('facefusion/processors/modules') ]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	processor_modules = get_processors_modules(available_processors)
 
 	for module in common_modules + processor_modules:

facefusion/uis/components/execution_queue_count.py

@@ -1,29 +0,0 @@
-from typing import Optional
-
-import gradio
-
-import facefusion.choices
-from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
-
-EXECUTION_QUEUE_COUNT_SLIDER : Optional[gradio.Slider] = None
-
-
-def render() -> None:
-	global EXECUTION_QUEUE_COUNT_SLIDER
-
-	EXECUTION_QUEUE_COUNT_SLIDER = gradio.Slider(
-		label = wording.get('uis.execution_queue_count_slider'),
-		value = state_manager.get_item('execution_queue_count'),
-		step = calc_int_step(facefusion.choices.execution_queue_count_range),
-		minimum = facefusion.choices.execution_queue_count_range[0],
-		maximum = facefusion.choices.execution_queue_count_range[-1]
-	)
-
-
-def listen() -> None:
-	EXECUTION_QUEUE_COUNT_SLIDER.release(update_execution_queue_count, inputs = EXECUTION_QUEUE_COUNT_SLIDER)
-
-
-def update_execution_queue_count(execution_queue_count : float) -> None:
-	state_manager.set_item('execution_queue_count', int(execution_queue_count))

facefusion/uis/components/execution_thread_count.py

@@ -4,7 +4,7 @@ import gradio
 
 import facefusion.choices
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
+from facefusion.common_helper import calculate_int_step
 
 EXECUTION_THREAD_COUNT_SLIDER : Optional[gradio.Slider] = None
 
@@ -15,7 +15,7 @@ def render() -> None:
 	EXECUTION_THREAD_COUNT_SLIDER = gradio.Slider(
 		label = wording.get('uis.execution_thread_count_slider'),
 		value = state_manager.get_item('execution_thread_count'),
-		step = calc_int_step(facefusion.choices.execution_thread_count_range),
+		step = calculate_int_step(facefusion.choices.execution_thread_count_range),
 		minimum = facefusion.choices.execution_thread_count_range[0],
 		maximum = facefusion.choices.execution_thread_count_range[-1]
 	)

facefusion/uis/components/expression_restorer_options.py

@@ -3,19 +3,21 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_float_step
+from facefusion.common_helper import calculate_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import ExpressionRestorerModel
+from facefusion.processors.types import ExpressionRestorerArea, ExpressionRestorerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 EXPRESSION_RESTORER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 EXPRESSION_RESTORER_FACTOR_SLIDER : Optional[gradio.Slider] = None
+EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 
 
 def render() -> None:
 	global EXPRESSION_RESTORER_MODEL_DROPDOWN
 	global EXPRESSION_RESTORER_FACTOR_SLIDER
+	global EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP
 
 	has_expression_restorer = 'expression_restorer' in state_manager.get_item('processors')
 	EXPRESSION_RESTORER_MODEL_DROPDOWN = gradio.Dropdown(
@@ -27,27 +29,35 @@ def render() -> None:
 	EXPRESSION_RESTORER_FACTOR_SLIDER = gradio.Slider(
 		label = wording.get('uis.expression_restorer_factor_slider'),
 		value = state_manager.get_item('expression_restorer_factor'),
-		step = calc_float_step(processors_choices.expression_restorer_factor_range),
+		step = calculate_float_step(processors_choices.expression_restorer_factor_range),
 		minimum = processors_choices.expression_restorer_factor_range[0],
 		maximum = processors_choices.expression_restorer_factor_range[-1],
 		visible = has_expression_restorer
 	)
+	EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.expression_restorer_areas_checkbox_group'),
+		choices = processors_choices.expression_restorer_areas,
+		value = state_manager.get_item('expression_restorer_areas'),
+		visible = has_expression_restorer
+	)
 	register_ui_component('expression_restorer_model_dropdown', EXPRESSION_RESTORER_MODEL_DROPDOWN)
 	register_ui_component('expression_restorer_factor_slider', EXPRESSION_RESTORER_FACTOR_SLIDER)
+	register_ui_component('expression_restorer_areas_checkbox_group', EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP)
 
 
 def listen() -> None:
 	EXPRESSION_RESTORER_MODEL_DROPDOWN.change(update_expression_restorer_model, inputs = EXPRESSION_RESTORER_MODEL_DROPDOWN, outputs = EXPRESSION_RESTORER_MODEL_DROPDOWN)
 	EXPRESSION_RESTORER_FACTOR_SLIDER.release(update_expression_restorer_factor, inputs = EXPRESSION_RESTORER_FACTOR_SLIDER)
+	EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP.change(update_expression_restorer_areas, inputs = EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP, outputs = EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP)
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ EXPRESSION_RESTORER_MODEL_DROPDOWN, EXPRESSION_RESTORER_FACTOR_SLIDER ])
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ EXPRESSION_RESTORER_MODEL_DROPDOWN, EXPRESSION_RESTORER_FACTOR_SLIDER, EXPRESSION_RESTORER_AREAS_CHECKBOX_GROUP ])
 
 
-def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider, gradio.CheckboxGroup]:
 	has_expression_restorer = 'expression_restorer' in processors
-	return gradio.Dropdown(visible = has_expression_restorer), gradio.Slider(visible = has_expression_restorer)
+	return gradio.Dropdown(visible = has_expression_restorer), gradio.Slider(visible = has_expression_restorer), gradio.CheckboxGroup(visible = has_expression_restorer)
 
 
 def update_expression_restorer_model(expression_restorer_model : ExpressionRestorerModel) -> gradio.Dropdown:
@@ -62,3 +72,9 @@ def update_expression_restorer_model(expression_restorer_model : ExpressionResto
 
 def update_expression_restorer_factor(expression_restorer_factor : float) -> None:
 	state_manager.set_item('expression_restorer_factor', int(expression_restorer_factor))
+
+
+def update_expression_restorer_areas(expression_restorer_areas : List[ExpressionRestorerArea]) -> gradio.CheckboxGroup:
+	expression_restorer_areas = expression_restorer_areas or processors_choices.expression_restorer_areas
+	state_manager.set_item('expression_restorer_areas', expression_restorer_areas)
+	return gradio.CheckboxGroup(value = state_manager.get_item('expression_restorer_areas'))

facefusion/uis/components/face_debugger_options.py

@@ -4,7 +4,7 @@ import gradio
 
 from facefusion import state_manager, wording
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FaceDebuggerItem
+from facefusion.processors.types import FaceDebuggerItem
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None

facefusion/uis/components/face_detector.py

@@ -4,10 +4,10 @@ import gradio
 
 import facefusion.choices
 from facefusion import face_detector, state_manager, wording
-from facefusion.common_helper import calc_float_step, get_last
-from facefusion.typing import Angle, FaceDetectorModel, Score
+from facefusion.common_helper import calculate_float_step, get_last
+from facefusion.types import Angle, FaceDetectorModel, Score
 from facefusion.uis.core import register_ui_component
-from facefusion.uis.typing import ComponentOptions
+from facefusion.uis.types import ComponentOptions
 
 FACE_DETECTOR_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_DETECTOR_SIZE_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -43,7 +43,7 @@ def render() -> None:
 	FACE_DETECTOR_SCORE_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_detector_score_slider'),
 		value = state_manager.get_item('face_detector_score'),
-		step = calc_float_step(facefusion.choices.face_detector_score_range),
+		step = calculate_float_step(facefusion.choices.face_detector_score_range),
 		minimum = facefusion.choices.face_detector_score_range[0],
 		maximum = facefusion.choices.face_detector_score_range[-1]
 	)

facefusion/uis/components/face_editor_options.py

@@ -3,10 +3,10 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_float_step
+from facefusion.common_helper import calculate_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FaceEditorModel
+from facefusion.processors.types import FaceEditorModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_EDITOR_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -53,7 +53,7 @@ def render() -> None:
 	FACE_EDITOR_EYEBROW_DIRECTION_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eyebrow_direction_slider'),
 		value = state_manager.get_item('face_editor_eyebrow_direction'),
-		step = calc_float_step(processors_choices.face_editor_eyebrow_direction_range),
+		step = calculate_float_step(processors_choices.face_editor_eyebrow_direction_range),
 		minimum = processors_choices.face_editor_eyebrow_direction_range[0],
 		maximum = processors_choices.face_editor_eyebrow_direction_range[-1],
 		visible = has_face_editor
@@ -61,7 +61,7 @@ def render() -> None:
 	FACE_EDITOR_EYE_GAZE_HORIZONTAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eye_gaze_horizontal_slider'),
 		value = state_manager.get_item('face_editor_eye_gaze_horizontal'),
-		step = calc_float_step(processors_choices.face_editor_eye_gaze_horizontal_range),
+		step = calculate_float_step(processors_choices.face_editor_eye_gaze_horizontal_range),
 		minimum = processors_choices.face_editor_eye_gaze_horizontal_range[0],
 		maximum = processors_choices.face_editor_eye_gaze_horizontal_range[-1],
 		visible = has_face_editor
@@ -69,7 +69,7 @@ def render() -> None:
 	FACE_EDITOR_EYE_GAZE_VERTICAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eye_gaze_vertical_slider'),
 		value = state_manager.get_item('face_editor_eye_gaze_vertical'),
-		step = calc_float_step(processors_choices.face_editor_eye_gaze_vertical_range),
+		step = calculate_float_step(processors_choices.face_editor_eye_gaze_vertical_range),
 		minimum = processors_choices.face_editor_eye_gaze_vertical_range[0],
 		maximum = processors_choices.face_editor_eye_gaze_vertical_range[-1],
 		visible = has_face_editor
@@ -77,7 +77,7 @@ def render() -> None:
 	FACE_EDITOR_EYE_OPEN_RATIO_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eye_open_ratio_slider'),
 		value = state_manager.get_item('face_editor_eye_open_ratio'),
-		step = calc_float_step(processors_choices.face_editor_eye_open_ratio_range),
+		step = calculate_float_step(processors_choices.face_editor_eye_open_ratio_range),
 		minimum = processors_choices.face_editor_eye_open_ratio_range[0],
 		maximum = processors_choices.face_editor_eye_open_ratio_range[-1],
 		visible = has_face_editor
@@ -85,7 +85,7 @@ def render() -> None:
 	FACE_EDITOR_LIP_OPEN_RATIO_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_lip_open_ratio_slider'),
 		value = state_manager.get_item('face_editor_lip_open_ratio'),
-		step = calc_float_step(processors_choices.face_editor_lip_open_ratio_range),
+		step = calculate_float_step(processors_choices.face_editor_lip_open_ratio_range),
 		minimum = processors_choices.face_editor_lip_open_ratio_range[0],
 		maximum = processors_choices.face_editor_lip_open_ratio_range[-1],
 		visible = has_face_editor
@@ -93,7 +93,7 @@ def render() -> None:
 	FACE_EDITOR_MOUTH_GRIM_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_grim_slider'),
 		value = state_manager.get_item('face_editor_mouth_grim'),
-		step = calc_float_step(processors_choices.face_editor_mouth_grim_range),
+		step = calculate_float_step(processors_choices.face_editor_mouth_grim_range),
 		minimum = processors_choices.face_editor_mouth_grim_range[0],
 		maximum = processors_choices.face_editor_mouth_grim_range[-1],
 		visible = has_face_editor
@@ -101,7 +101,7 @@ def render() -> None:
 	FACE_EDITOR_MOUTH_POUT_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_pout_slider'),
 		value = state_manager.get_item('face_editor_mouth_pout'),
-		step = calc_float_step(processors_choices.face_editor_mouth_pout_range),
+		step = calculate_float_step(processors_choices.face_editor_mouth_pout_range),
 		minimum = processors_choices.face_editor_mouth_pout_range[0],
 		maximum = processors_choices.face_editor_mouth_pout_range[-1],
 		visible = has_face_editor
@@ -109,7 +109,7 @@ def render() -> None:
 	FACE_EDITOR_MOUTH_PURSE_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_purse_slider'),
 		value = state_manager.get_item('face_editor_mouth_purse'),
-		step = calc_float_step(processors_choices.face_editor_mouth_purse_range),
+		step = calculate_float_step(processors_choices.face_editor_mouth_purse_range),
 		minimum = processors_choices.face_editor_mouth_purse_range[0],
 		maximum = processors_choices.face_editor_mouth_purse_range[-1],
 		visible = has_face_editor
@@ -117,7 +117,7 @@ def render() -> None:
 	FACE_EDITOR_MOUTH_SMILE_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_smile_slider'),
 		value = state_manager.get_item('face_editor_mouth_smile'),
-		step = calc_float_step(processors_choices.face_editor_mouth_smile_range),
+		step = calculate_float_step(processors_choices.face_editor_mouth_smile_range),
 		minimum = processors_choices.face_editor_mouth_smile_range[0],
 		maximum = processors_choices.face_editor_mouth_smile_range[-1],
 		visible = has_face_editor
@@ -125,7 +125,7 @@ def render() -> None:
 	FACE_EDITOR_MOUTH_POSITION_HORIZONTAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_position_horizontal_slider'),
 		value = state_manager.get_item('face_editor_mouth_position_horizontal'),
-		step = calc_float_step(processors_choices.face_editor_mouth_position_horizontal_range),
+		step = calculate_float_step(processors_choices.face_editor_mouth_position_horizontal_range),
 		minimum = processors_choices.face_editor_mouth_position_horizontal_range[0],
 		maximum = processors_choices.face_editor_mouth_position_horizontal_range[-1],
 		visible = has_face_editor
@@ -133,7 +133,7 @@ def render() -> None:
 	FACE_EDITOR_MOUTH_POSITION_VERTICAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_position_vertical_slider'),
 		value = state_manager.get_item('face_editor_mouth_position_vertical'),
-		step = calc_float_step(processors_choices.face_editor_mouth_position_vertical_range),
+		step = calculate_float_step(processors_choices.face_editor_mouth_position_vertical_range),
 		minimum = processors_choices.face_editor_mouth_position_vertical_range[0],
 		maximum = processors_choices.face_editor_mouth_position_vertical_range[-1],
 		visible = has_face_editor
@@ -141,7 +141,7 @@ def render() -> None:
 	FACE_EDITOR_HEAD_PITCH_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_head_pitch_slider'),
 		value = state_manager.get_item('face_editor_head_pitch'),
-		step = calc_float_step(processors_choices.face_editor_head_pitch_range),
+		step = calculate_float_step(processors_choices.face_editor_head_pitch_range),
 		minimum = processors_choices.face_editor_head_pitch_range[0],
 		maximum = processors_choices.face_editor_head_pitch_range[-1],
 		visible = has_face_editor
@@ -149,7 +149,7 @@ def render() -> None:
 	FACE_EDITOR_HEAD_YAW_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_head_yaw_slider'),
 		value = state_manager.get_item('face_editor_head_yaw'),
-		step = calc_float_step(processors_choices.face_editor_head_yaw_range),
+		step = calculate_float_step(processors_choices.face_editor_head_yaw_range),
 		minimum = processors_choices.face_editor_head_yaw_range[0],
 		maximum = processors_choices.face_editor_head_yaw_range[-1],
 		visible = has_face_editor
@@ -157,7 +157,7 @@ def render() -> None:
 	FACE_EDITOR_HEAD_ROLL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_head_roll_slider'),
 		value = state_manager.get_item('face_editor_head_roll'),
-		step = calc_float_step(processors_choices.face_editor_head_roll_range),
+		step = calculate_float_step(processors_choices.face_editor_head_roll_range),
 		minimum = processors_choices.face_editor_head_roll_range[0],
 		maximum = processors_choices.face_editor_head_roll_range[-1],
 		visible = has_face_editor
@@ -198,7 +198,7 @@ def listen() -> None:
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [FACE_EDITOR_MODEL_DROPDOWN, FACE_EDITOR_EYEBROW_DIRECTION_SLIDER, FACE_EDITOR_EYE_GAZE_HORIZONTAL_SLIDER, FACE_EDITOR_EYE_GAZE_VERTICAL_SLIDER, FACE_EDITOR_EYE_OPEN_RATIO_SLIDER, FACE_EDITOR_LIP_OPEN_RATIO_SLIDER, FACE_EDITOR_MOUTH_GRIM_SLIDER, FACE_EDITOR_MOUTH_POUT_SLIDER, FACE_EDITOR_MOUTH_PURSE_SLIDER, FACE_EDITOR_MOUTH_SMILE_SLIDER, FACE_EDITOR_MOUTH_POSITION_HORIZONTAL_SLIDER, FACE_EDITOR_MOUTH_POSITION_VERTICAL_SLIDER, FACE_EDITOR_HEAD_PITCH_SLIDER, FACE_EDITOR_HEAD_YAW_SLIDER, FACE_EDITOR_HEAD_ROLL_SLIDER])
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ FACE_EDITOR_MODEL_DROPDOWN, FACE_EDITOR_EYEBROW_DIRECTION_SLIDER, FACE_EDITOR_EYE_GAZE_HORIZONTAL_SLIDER, FACE_EDITOR_EYE_GAZE_VERTICAL_SLIDER, FACE_EDITOR_EYE_OPEN_RATIO_SLIDER, FACE_EDITOR_LIP_OPEN_RATIO_SLIDER, FACE_EDITOR_MOUTH_GRIM_SLIDER, FACE_EDITOR_MOUTH_POUT_SLIDER, FACE_EDITOR_MOUTH_PURSE_SLIDER, FACE_EDITOR_MOUTH_SMILE_SLIDER, FACE_EDITOR_MOUTH_POSITION_HORIZONTAL_SLIDER, FACE_EDITOR_MOUTH_POSITION_VERTICAL_SLIDER, FACE_EDITOR_HEAD_PITCH_SLIDER, FACE_EDITOR_HEAD_YAW_SLIDER, FACE_EDITOR_HEAD_ROLL_SLIDER ])
 
 
 def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider]:

facefusion/uis/components/face_enhancer_options.py

@@ -3,11 +3,10 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_float_step, calc_int_step
+from facefusion.common_helper import calculate_float_step, calculate_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.modules.face_enhancer import has_weight_input
-from facefusion.processors.typing import FaceEnhancerModel
+from facefusion.processors.types import FaceEnhancerModel, FaceEnhancerWeight
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_ENHANCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -30,7 +29,7 @@ def render() -> None:
 	FACE_ENHANCER_BLEND_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_enhancer_blend_slider'),
 		value = state_manager.get_item('face_enhancer_blend'),
-		step = calc_int_step(processors_choices.face_enhancer_blend_range),
+		step = calculate_int_step(processors_choices.face_enhancer_blend_range),
 		minimum = processors_choices.face_enhancer_blend_range[0],
 		maximum = processors_choices.face_enhancer_blend_range[-1],
 		visible = has_face_enhancer
@@ -38,10 +37,10 @@ def render() -> None:
 	FACE_ENHANCER_WEIGHT_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_enhancer_weight_slider'),
 		value = state_manager.get_item('face_enhancer_weight'),
-		step = calc_float_step(processors_choices.face_enhancer_weight_range),
+		step = calculate_float_step(processors_choices.face_enhancer_weight_range),
 		minimum = processors_choices.face_enhancer_weight_range[0],
 		maximum = processors_choices.face_enhancer_weight_range[-1],
-		visible = has_face_enhancer and has_weight_input()
+		visible = has_face_enhancer and load_processor_module('face_enhancer').get_inference_pool() and load_processor_module('face_enhancer').has_weight_input()
 	)
 	register_ui_component('face_enhancer_model_dropdown', FACE_ENHANCER_MODEL_DROPDOWN)
 	register_ui_component('face_enhancer_blend_slider', FACE_ENHANCER_BLEND_SLIDER)
@@ -60,7 +59,7 @@ def listen() -> None:
 
 def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider, gradio.Slider]:
 	has_face_enhancer = 'face_enhancer' in processors
-	return gradio.Dropdown(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer and has_weight_input())
+	return gradio.Dropdown(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer and load_processor_module('face_enhancer').get_inference_pool() and load_processor_module('face_enhancer').has_weight_input())
 
 
 def update_face_enhancer_model(face_enhancer_model : FaceEnhancerModel) -> Tuple[gradio.Dropdown, gradio.Slider]:
@@ -69,7 +68,7 @@ def update_face_enhancer_model(face_enhancer_model : FaceEnhancerModel) -> Tuple
 	state_manager.set_item('face_enhancer_model', face_enhancer_model)
 
 	if face_enhancer_module.pre_check():
-		return gradio.Dropdown(value = state_manager.get_item('face_enhancer_model')), gradio.Slider(visible = has_weight_input())
+		return gradio.Dropdown(value = state_manager.get_item('face_enhancer_model')), gradio.Slider(visible = face_enhancer_module.has_weight_input())
 	return gradio.Dropdown(), gradio.Slider()
 
 
@@ -77,6 +76,6 @@ def update_face_enhancer_blend(face_enhancer_blend : float) -> None:
 	state_manager.set_item('face_enhancer_blend', int(face_enhancer_blend))
 
 
-def update_face_enhancer_weight(face_enhancer_weight : float) -> None:
+def update_face_enhancer_weight(face_enhancer_weight : FaceEnhancerWeight) -> None:
 	state_manager.set_item('face_enhancer_weight', face_enhancer_weight)
 

facefusion/uis/components/face_landmarker.py

@@ -4,8 +4,8 @@ import gradio
 
 import facefusion.choices
 from facefusion import face_landmarker, state_manager, wording
-from facefusion.common_helper import calc_float_step
-from facefusion.typing import FaceLandmarkerModel, Score
+from facefusion.common_helper import calculate_float_step
+from facefusion.types import FaceLandmarkerModel, Score
 from facefusion.uis.core import register_ui_component
 
 FACE_LANDMARKER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -24,7 +24,7 @@ def render() -> None:
 	FACE_LANDMARKER_SCORE_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_landmarker_score_slider'),
 		value = state_manager.get_item('face_landmarker_score'),
-		step = calc_float_step(facefusion.choices.face_landmarker_score_range),
+		step = calculate_float_step(facefusion.choices.face_landmarker_score_range),
 		minimum = facefusion.choices.face_landmarker_score_range[0],
 		maximum = facefusion.choices.face_landmarker_score_range[-1]
 	)

facefusion/uis/components/face_masker.py

@@ -4,13 +4,14 @@ import gradio
 
 import facefusion.choices
 from facefusion import face_masker, state_manager, wording
-from facefusion.common_helper import calc_float_step, calc_int_step
-from facefusion.typing import FaceMaskRegion, FaceMaskType, FaceOccluderModel, FaceParserModel
+from facefusion.common_helper import calculate_float_step, calculate_int_step
+from facefusion.types import FaceMaskArea, FaceMaskRegion, FaceMaskType, FaceOccluderModel, FaceParserModel
 from facefusion.uis.core import register_ui_component
 
 FACE_OCCLUDER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_PARSER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_MASK_TYPES_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
+FACE_MASK_AREAS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 FACE_MASK_REGIONS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 FACE_MASK_BLUR_SLIDER : Optional[gradio.Slider] = None
 FACE_MASK_PADDING_TOP_SLIDER : Optional[gradio.Slider] = None
@@ -23,6 +24,7 @@ def render() -> None:
 	global FACE_OCCLUDER_MODEL_DROPDOWN
 	global FACE_PARSER_MODEL_DROPDOWN
 	global FACE_MASK_TYPES_CHECKBOX_GROUP
+	global FACE_MASK_AREAS_CHECKBOX_GROUP
 	global FACE_MASK_REGIONS_CHECKBOX_GROUP
 	global FACE_MASK_BLUR_SLIDER
 	global FACE_MASK_PADDING_TOP_SLIDER
@@ -32,6 +34,7 @@ def render() -> None:
 
 	has_box_mask = 'box' in state_manager.get_item('face_mask_types')
 	has_region_mask = 'region' in state_manager.get_item('face_mask_types')
+	has_area_mask = 'area' in state_manager.get_item('face_mask_types')
 	with gradio.Row():
 		FACE_OCCLUDER_MODEL_DROPDOWN = gradio.Dropdown(
 			label = wording.get('uis.face_occluder_model_dropdown'),
@@ -48,6 +51,12 @@ def render() -> None:
 		choices = facefusion.choices.face_mask_types,
 		value = state_manager.get_item('face_mask_types')
 	)
+	FACE_MASK_AREAS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.face_mask_areas_checkbox_group'),
+		choices = facefusion.choices.face_mask_areas,
+		value = state_manager.get_item('face_mask_areas'),
+		visible = has_area_mask
+	)
 	FACE_MASK_REGIONS_CHECKBOX_GROUP = gradio.CheckboxGroup(
 		label = wording.get('uis.face_mask_regions_checkbox_group'),
 		choices = facefusion.choices.face_mask_regions,
@@ -56,7 +65,7 @@ def render() -> None:
 	)
 	FACE_MASK_BLUR_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_mask_blur_slider'),
-		step = calc_float_step(facefusion.choices.face_mask_blur_range),
+		step = calculate_float_step(facefusion.choices.face_mask_blur_range),
 		minimum = facefusion.choices.face_mask_blur_range[0],
 		maximum = facefusion.choices.face_mask_blur_range[-1],
 		value = state_manager.get_item('face_mask_blur'),
@@ -66,7 +75,7 @@ def render() -> None:
 		with gradio.Row():
 			FACE_MASK_PADDING_TOP_SLIDER = gradio.Slider(
 				label = wording.get('uis.face_mask_padding_top_slider'),
-				step = calc_int_step(facefusion.choices.face_mask_padding_range),
+				step = calculate_int_step(facefusion.choices.face_mask_padding_range),
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
 				value = state_manager.get_item('face_mask_padding')[0],
@@ -74,7 +83,7 @@ def render() -> None:
 			)
 			FACE_MASK_PADDING_RIGHT_SLIDER = gradio.Slider(
 				label = wording.get('uis.face_mask_padding_right_slider'),
-				step = calc_int_step(facefusion.choices.face_mask_padding_range),
+				step = calculate_int_step(facefusion.choices.face_mask_padding_range),
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
 				value = state_manager.get_item('face_mask_padding')[1],
@@ -83,7 +92,7 @@ def render() -> None:
 		with gradio.Row():
 			FACE_MASK_PADDING_BOTTOM_SLIDER = gradio.Slider(
 				label = wording.get('uis.face_mask_padding_bottom_slider'),
-				step = calc_int_step(facefusion.choices.face_mask_padding_range),
+				step = calculate_int_step(facefusion.choices.face_mask_padding_range),
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
 				value = state_manager.get_item('face_mask_padding')[2],
@@ -91,7 +100,7 @@ def render() -> None:
 			)
 			FACE_MASK_PADDING_LEFT_SLIDER = gradio.Slider(
 				label = wording.get('uis.face_mask_padding_left_slider'),
-				step = calc_int_step(facefusion.choices.face_mask_padding_range),
+				step = calculate_int_step(facefusion.choices.face_mask_padding_range),
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
 				value = state_manager.get_item('face_mask_padding')[3],
@@ -100,6 +109,7 @@ def render() -> None:
 	register_ui_component('face_occluder_model_dropdown', FACE_OCCLUDER_MODEL_DROPDOWN)
 	register_ui_component('face_parser_model_dropdown', FACE_PARSER_MODEL_DROPDOWN)
 	register_ui_component('face_mask_types_checkbox_group', FACE_MASK_TYPES_CHECKBOX_GROUP)
+	register_ui_component('face_mask_areas_checkbox_group', FACE_MASK_AREAS_CHECKBOX_GROUP)
 	register_ui_component('face_mask_regions_checkbox_group', FACE_MASK_REGIONS_CHECKBOX_GROUP)
 	register_ui_component('face_mask_blur_slider', FACE_MASK_BLUR_SLIDER)
 	register_ui_component('face_mask_padding_top_slider', FACE_MASK_PADDING_TOP_SLIDER)
@@ -111,9 +121,11 @@ def render() -> None:
 def listen() -> None:
 	FACE_OCCLUDER_MODEL_DROPDOWN.change(update_face_occluder_model, inputs = FACE_OCCLUDER_MODEL_DROPDOWN)
 	FACE_PARSER_MODEL_DROPDOWN.change(update_face_parser_model, inputs = FACE_PARSER_MODEL_DROPDOWN)
-	FACE_MASK_TYPES_CHECKBOX_GROUP.change(update_face_mask_types, inputs = FACE_MASK_TYPES_CHECKBOX_GROUP, outputs = [ FACE_MASK_TYPES_CHECKBOX_GROUP, FACE_MASK_REGIONS_CHECKBOX_GROUP, FACE_MASK_BLUR_SLIDER, FACE_MASK_PADDING_TOP_SLIDER, FACE_MASK_PADDING_RIGHT_SLIDER, FACE_MASK_PADDING_BOTTOM_SLIDER, FACE_MASK_PADDING_LEFT_SLIDER ])
+	FACE_MASK_TYPES_CHECKBOX_GROUP.change(update_face_mask_types, inputs = FACE_MASK_TYPES_CHECKBOX_GROUP, outputs = [ FACE_MASK_TYPES_CHECKBOX_GROUP, FACE_MASK_AREAS_CHECKBOX_GROUP, FACE_MASK_REGIONS_CHECKBOX_GROUP, FACE_MASK_BLUR_SLIDER, FACE_MASK_PADDING_TOP_SLIDER, FACE_MASK_PADDING_RIGHT_SLIDER, FACE_MASK_PADDING_BOTTOM_SLIDER, FACE_MASK_PADDING_LEFT_SLIDER ])
+	FACE_MASK_AREAS_CHECKBOX_GROUP.change(update_face_mask_areas, inputs = FACE_MASK_AREAS_CHECKBOX_GROUP, outputs = FACE_MASK_AREAS_CHECKBOX_GROUP)
 	FACE_MASK_REGIONS_CHECKBOX_GROUP.change(update_face_mask_regions, inputs = FACE_MASK_REGIONS_CHECKBOX_GROUP, outputs = FACE_MASK_REGIONS_CHECKBOX_GROUP)
 	FACE_MASK_BLUR_SLIDER.release(update_face_mask_blur, inputs = FACE_MASK_BLUR_SLIDER)
+
 	face_mask_padding_sliders = [ FACE_MASK_PADDING_TOP_SLIDER, FACE_MASK_PADDING_RIGHT_SLIDER, FACE_MASK_PADDING_BOTTOM_SLIDER, FACE_MASK_PADDING_LEFT_SLIDER ]
 	for face_mask_padding_slider in face_mask_padding_sliders:
 		face_mask_padding_slider.release(update_face_mask_padding, inputs = face_mask_padding_sliders)
@@ -137,12 +149,19 @@ def update_face_parser_model(face_parser_model : FaceParserModel) -> gradio.Drop
 	return gradio.Dropdown()
 
 
-def update_face_mask_types(face_mask_types : List[FaceMaskType]) -> Tuple[gradio.CheckboxGroup, gradio.CheckboxGroup, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider]:
+def update_face_mask_types(face_mask_types : List[FaceMaskType]) -> Tuple[gradio.CheckboxGroup, gradio.CheckboxGroup, gradio.CheckboxGroup, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider]:
 	face_mask_types = face_mask_types or facefusion.choices.face_mask_types
 	state_manager.set_item('face_mask_types', face_mask_types)
 	has_box_mask = 'box' in face_mask_types
+	has_area_mask = 'area' in face_mask_types
 	has_region_mask = 'region' in face_mask_types
-	return gradio.CheckboxGroup(value = state_manager.get_item('face_mask_types')), gradio.CheckboxGroup(visible = has_region_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask)
+	return gradio.CheckboxGroup(value = state_manager.get_item('face_mask_types')), gradio.CheckboxGroup(visible = has_area_mask), gradio.CheckboxGroup(visible = has_region_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask)
+
+
+def update_face_mask_areas(face_mask_areas : List[FaceMaskArea]) -> gradio.CheckboxGroup:
+	face_mask_areas = face_mask_areas or facefusion.choices.face_mask_areas
+	state_manager.set_item('face_mask_areas', face_mask_areas)
+	return gradio.CheckboxGroup(value = state_manager.get_item('face_mask_areas'))
 
 
 def update_face_mask_regions(face_mask_regions : List[FaceMaskRegion]) -> gradio.CheckboxGroup:

facefusion/uis/components/face_selector.py

@@ -1,20 +1,21 @@
 from typing import List, Optional, Tuple
 
+import cv2
 import gradio
 from gradio_rangeslider import RangeSlider
 
 import facefusion.choices
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_float_step, calc_int_step
+from facefusion.common_helper import calculate_float_step, calculate_int_step
 from facefusion.face_analyser import get_many_faces
 from facefusion.face_selector import sort_and_filter_faces
-from facefusion.face_store import clear_reference_faces, clear_static_faces
+from facefusion.face_store import clear_static_faces
 from facefusion.filesystem import is_image, is_video
-from facefusion.typing import FaceSelectorMode, FaceSelectorOrder, Gender, Race, VisionFrame
+from facefusion.types import FaceSelectorMode, FaceSelectorOrder, Gender, Race, VisionFrame
 from facefusion.uis.core import get_ui_component, get_ui_components, register_ui_component
-from facefusion.uis.typing import ComponentOptions
+from facefusion.uis.types import ComponentOptions
 from facefusion.uis.ui_helper import convert_str_none
-from facefusion.vision import get_video_frame, normalize_frame_color, read_static_image
+from facefusion.vision import fit_cover_frame, read_static_image, read_video_frame
 
 FACE_SELECTOR_MODE_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_SELECTOR_ORDER_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -38,16 +39,17 @@ def render() -> None:
 	{
 		'label': wording.get('uis.reference_face_gallery'),
 		'object_fit': 'cover',
-		'columns': 8,
+		'columns': 7,
 		'allow_preview': False,
+		'elem_classes': 'box-face-selector',
 		'visible': 'reference' in state_manager.get_item('face_selector_mode')
 	}
 	if is_image(state_manager.get_item('target_path')):
-		reference_frame = read_static_image(state_manager.get_item('target_path'))
-		reference_face_gallery_options['value'] = extract_gallery_frames(reference_frame)
+		target_vision_frame = read_static_image(state_manager.get_item('target_path'))
+		reference_face_gallery_options['value'] = extract_gallery_frames(target_vision_frame)
 	if is_video(state_manager.get_item('target_path')):
-		reference_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
-		reference_face_gallery_options['value'] = extract_gallery_frames(reference_frame)
+		target_vision_frame = read_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
+		reference_face_gallery_options['value'] = extract_gallery_frames(target_vision_frame)
 	FACE_SELECTOR_MODE_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.face_selector_mode_dropdown'),
 		choices = facefusion.choices.face_selector_modes,
@@ -68,7 +70,7 @@ def render() -> None:
 			)
 			FACE_SELECTOR_RACE_DROPDOWN = gradio.Dropdown(
 				label = wording.get('uis.face_selector_race_dropdown'),
-				choices = ['none'] + facefusion.choices.face_selector_races,
+				choices = [ 'none' ] + facefusion.choices.face_selector_races,
 				value = state_manager.get_item('face_selector_race') or 'none'
 			)
 		with gradio.Row():
@@ -79,12 +81,12 @@ def render() -> None:
 				minimum = facefusion.choices.face_selector_age_range[0],
 				maximum = facefusion.choices.face_selector_age_range[-1],
 				value = (face_selector_age_start, face_selector_age_end),
-				step = calc_int_step(facefusion.choices.face_selector_age_range)
+				step = calculate_int_step(facefusion.choices.face_selector_age_range)
 			)
 	REFERENCE_FACE_DISTANCE_SLIDER = gradio.Slider(
 		label = wording.get('uis.reference_face_distance_slider'),
 		value = state_manager.get_item('reference_face_distance'),
-		step = calc_float_step(facefusion.choices.reference_face_distance_range),
+		step = calculate_float_step(facefusion.choices.reference_face_distance_range),
 		minimum = facefusion.choices.reference_face_distance_range[0],
 		maximum = facefusion.choices.reference_face_distance_range[-1],
 		visible = 'reference' in state_manager.get_item('face_selector_mode')
@@ -104,16 +106,21 @@ def listen() -> None:
 	FACE_SELECTOR_GENDER_DROPDOWN.change(update_face_selector_gender, inputs = FACE_SELECTOR_GENDER_DROPDOWN, outputs = REFERENCE_FACE_POSITION_GALLERY)
 	FACE_SELECTOR_RACE_DROPDOWN.change(update_face_selector_race, inputs = FACE_SELECTOR_RACE_DROPDOWN, outputs = REFERENCE_FACE_POSITION_GALLERY)
 	FACE_SELECTOR_AGE_RANGE_SLIDER.release(update_face_selector_age_range, inputs = FACE_SELECTOR_AGE_RANGE_SLIDER, outputs = REFERENCE_FACE_POSITION_GALLERY)
-	REFERENCE_FACE_POSITION_GALLERY.select(clear_and_update_reference_face_position)
 	REFERENCE_FACE_DISTANCE_SLIDER.release(update_reference_face_distance, inputs = REFERENCE_FACE_DISTANCE_SLIDER)
 
+	preview_frame_slider = get_ui_component('preview_frame_slider')
+	if preview_frame_slider:
+		REFERENCE_FACE_POSITION_GALLERY.select(update_reference_frame_number, inputs = preview_frame_slider)
+		REFERENCE_FACE_POSITION_GALLERY.select(update_reference_face_position)
+
 	for ui_component in get_ui_components(
 	[
 		'target_image',
 		'target_video'
 	]):
-		for method in [ 'upload', 'change', 'clear' ]:
-			getattr(ui_component, method)(update_reference_face_position)
+		for method in [ 'change', 'clear' ]:
+			getattr(ui_component, method)(clear_reference_frame_number)
+			getattr(ui_component, method)(clear_reference_face_position)
 			getattr(ui_component, method)(update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY)
 
 	for ui_component in get_ui_components(
@@ -126,12 +133,12 @@ def listen() -> None:
 
 	face_detector_score_slider = get_ui_component('face_detector_score_slider')
 	if face_detector_score_slider:
-		face_detector_score_slider.release(clear_and_update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY)
+		face_detector_score_slider.release(update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY)
 
 	preview_frame_slider = get_ui_component('preview_frame_slider')
 	if preview_frame_slider:
-		preview_frame_slider.release(update_reference_frame_number, inputs = preview_frame_slider)
-		preview_frame_slider.release(update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY)
+		for method in [ 'change', 'release' ]:
+			getattr(preview_frame_slider, method)(update_reference_position_gallery, inputs = preview_frame_slider, outputs = REFERENCE_FACE_POSITION_GALLERY, show_progress = 'hidden')
 
 
 def update_face_selector_mode(face_selector_mode : FaceSelectorMode) -> Tuple[gradio.Gallery, gradio.Slider]:
@@ -166,47 +173,48 @@ def update_face_selector_age_range(face_selector_age_range : Tuple[float, float]
 	return update_reference_position_gallery()
 
 
-def clear_and_update_reference_face_position(event : gradio.SelectData) -> gradio.Gallery:
-	clear_reference_faces()
-	clear_static_faces()
-	update_reference_face_position(event.index)
-	return update_reference_position_gallery()
+def update_reference_face_position(event : gradio.SelectData) -> None:
+	state_manager.set_item('reference_face_position', event.index)
 
 
-def update_reference_face_position(reference_face_position : int = 0) -> None:
-	state_manager.set_item('reference_face_position', reference_face_position)
+def clear_reference_face_position() -> None:
+	state_manager.set_item('reference_face_position', 0)
 
 
 def update_reference_face_distance(reference_face_distance : float) -> None:
 	state_manager.set_item('reference_face_distance', reference_face_distance)
 
 
-def update_reference_frame_number(reference_frame_number : int) -> None:
+def update_reference_frame_number(reference_frame_number : int = 0) -> None:
 	state_manager.set_item('reference_frame_number', reference_frame_number)
 
 
+def clear_reference_frame_number() -> None:
+	state_manager.set_item('reference_frame_number', 0)
+
+
 def clear_and_update_reference_position_gallery() -> gradio.Gallery:
-	clear_reference_faces()
 	clear_static_faces()
 	return update_reference_position_gallery()
 
 
-def update_reference_position_gallery() -> gradio.Gallery:
+def update_reference_position_gallery(frame_number : int = 0) -> gradio.Gallery:
 	gallery_vision_frames = []
 	if is_image(state_manager.get_item('target_path')):
-		temp_vision_frame = read_static_image(state_manager.get_item('target_path'))
-		gallery_vision_frames = extract_gallery_frames(temp_vision_frame)
+		target_vision_frame = read_static_image(state_manager.get_item('target_path'))
+		gallery_vision_frames = extract_gallery_frames(target_vision_frame)
 	if is_video(state_manager.get_item('target_path')):
-		temp_vision_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
-		gallery_vision_frames = extract_gallery_frames(temp_vision_frame)
+		target_vision_frame = read_video_frame(state_manager.get_item('target_path'), frame_number)
+		gallery_vision_frames = extract_gallery_frames(target_vision_frame)
 	if gallery_vision_frames:
 		return gradio.Gallery(value = gallery_vision_frames)
 	return gradio.Gallery(value = None)
 
 
-def extract_gallery_frames(temp_vision_frame : VisionFrame) -> List[VisionFrame]:
+def extract_gallery_frames(target_vision_frame : VisionFrame) -> List[VisionFrame]:
 	gallery_vision_frames = []
-	faces = sort_and_filter_faces(get_many_faces([ temp_vision_frame ]))
+	faces = get_many_faces([ target_vision_frame ])
+	faces = sort_and_filter_faces(faces)
 
 	for face in faces:
 		start_x, start_y, end_x, end_y = map(int, face.bounding_box)
@@ -216,7 +224,8 @@ def extract_gallery_frames(temp_vision_frame : VisionFrame) -> List[VisionFrame]
 		start_y = max(0, start_y - padding_y)
 		end_x = max(0, end_x + padding_x)
 		end_y = max(0, end_y + padding_y)
-		crop_vision_frame = temp_vision_frame[start_y:end_y, start_x:end_x]
-		crop_vision_frame = normalize_frame_color(crop_vision_frame)
+		crop_vision_frame = target_vision_frame[start_y:end_y, start_x:end_x]
+		crop_vision_frame = fit_cover_frame(crop_vision_frame, (128, 128))
+		crop_vision_frame = cv2.cvtColor(crop_vision_frame, cv2.COLOR_BGR2RGB)
 		gallery_vision_frames.append(crop_vision_frame)
 	return gallery_vision_frames

facefusion/uis/components/face_swapper_options.py

@@ -3,19 +3,21 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import get_first
+from facefusion.common_helper import calculate_float_step, get_first
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FaceSwapperModel
+from facefusion.processors.types import FaceSwapperModel, FaceSwapperWeight
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_SWAPPER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_SWAPPER_PIXEL_BOOST_DROPDOWN : Optional[gradio.Dropdown] = None
+FACE_SWAPPER_WEIGHT_SLIDER : Optional[gradio.Slider] = None
 
 
 def render() -> None:
 	global FACE_SWAPPER_MODEL_DROPDOWN
 	global FACE_SWAPPER_PIXEL_BOOST_DROPDOWN
+	global FACE_SWAPPER_WEIGHT_SLIDER
 
 	has_face_swapper = 'face_swapper' in state_manager.get_item('processors')
 	FACE_SWAPPER_MODEL_DROPDOWN = gradio.Dropdown(
@@ -30,25 +32,35 @@ def render() -> None:
 		value = state_manager.get_item('face_swapper_pixel_boost'),
 		visible = has_face_swapper
 	)
+	FACE_SWAPPER_WEIGHT_SLIDER = gradio.Slider(
+		label = wording.get('uis.face_swapper_weight_slider'),
+		value = state_manager.get_item('face_swapper_weight'),
+		minimum = processors_choices.face_swapper_weight_range[0],
+		maximum = processors_choices.face_swapper_weight_range[-1],
+		step = calculate_float_step(processors_choices.face_swapper_weight_range),
+		visible = has_face_swapper and has_face_swapper_weight()
+	)
 	register_ui_component('face_swapper_model_dropdown', FACE_SWAPPER_MODEL_DROPDOWN)
 	register_ui_component('face_swapper_pixel_boost_dropdown', FACE_SWAPPER_PIXEL_BOOST_DROPDOWN)
+	register_ui_component('face_swapper_weight_slider', FACE_SWAPPER_WEIGHT_SLIDER)
 
 
 def listen() -> None:
-	FACE_SWAPPER_MODEL_DROPDOWN.change(update_face_swapper_model, inputs = FACE_SWAPPER_MODEL_DROPDOWN, outputs = [ FACE_SWAPPER_MODEL_DROPDOWN, FACE_SWAPPER_PIXEL_BOOST_DROPDOWN ])
+	FACE_SWAPPER_MODEL_DROPDOWN.change(update_face_swapper_model, inputs = FACE_SWAPPER_MODEL_DROPDOWN, outputs = [ FACE_SWAPPER_MODEL_DROPDOWN, FACE_SWAPPER_PIXEL_BOOST_DROPDOWN, FACE_SWAPPER_WEIGHT_SLIDER ])
 	FACE_SWAPPER_PIXEL_BOOST_DROPDOWN.change(update_face_swapper_pixel_boost, inputs = FACE_SWAPPER_PIXEL_BOOST_DROPDOWN)
+	FACE_SWAPPER_WEIGHT_SLIDER.change(update_face_swapper_weight, inputs = FACE_SWAPPER_WEIGHT_SLIDER)
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ FACE_SWAPPER_MODEL_DROPDOWN, FACE_SWAPPER_PIXEL_BOOST_DROPDOWN ])
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ FACE_SWAPPER_MODEL_DROPDOWN, FACE_SWAPPER_PIXEL_BOOST_DROPDOWN, FACE_SWAPPER_WEIGHT_SLIDER ])
 
 
-def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Dropdown]:
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Dropdown, gradio.Slider]:
 	has_face_swapper = 'face_swapper' in processors
-	return gradio.Dropdown(visible = has_face_swapper), gradio.Dropdown(visible = has_face_swapper)
+	return gradio.Dropdown(visible = has_face_swapper), gradio.Dropdown(visible = has_face_swapper), gradio.Slider(visible = has_face_swapper)
 
 
-def update_face_swapper_model(face_swapper_model : FaceSwapperModel) -> Tuple[gradio.Dropdown, gradio.Dropdown]:
+def update_face_swapper_model(face_swapper_model : FaceSwapperModel) -> Tuple[gradio.Dropdown, gradio.Dropdown, gradio.Slider]:
 	face_swapper_module = load_processor_module('face_swapper')
 	face_swapper_module.clear_inference_pool()
 	state_manager.set_item('face_swapper_model', face_swapper_model)
@@ -56,9 +68,17 @@ def update_face_swapper_model(face_swapper_model : FaceSwapperModel) -> Tuple[gr
 	if face_swapper_module.pre_check():
 		face_swapper_pixel_boost_choices = processors_choices.face_swapper_set.get(state_manager.get_item('face_swapper_model'))
 		state_manager.set_item('face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices))
-		return gradio.Dropdown(value = state_manager.get_item('face_swapper_model')), gradio.Dropdown(value = state_manager.get_item('face_swapper_pixel_boost'), choices = face_swapper_pixel_boost_choices)
-	return gradio.Dropdown(), gradio.Dropdown()
+		return gradio.Dropdown(value = state_manager.get_item('face_swapper_model')), gradio.Dropdown(value = state_manager.get_item('face_swapper_pixel_boost'), choices = face_swapper_pixel_boost_choices), gradio.Slider(visible = has_face_swapper_weight())
+	return gradio.Dropdown(), gradio.Dropdown(), gradio.Slider()
 
 
 def update_face_swapper_pixel_boost(face_swapper_pixel_boost : str) -> None:
 	state_manager.set_item('face_swapper_pixel_boost', face_swapper_pixel_boost)
+
+
+def update_face_swapper_weight(face_swapper_weight : FaceSwapperWeight) -> None:
+	state_manager.set_item('face_swapper_weight', face_swapper_weight)
+
+
+def has_face_swapper_weight() -> bool:
+	return state_manager.get_item('face_swapper_model') in [ 'ghost_1_256', 'ghost_2_256', 'ghost_3_256', 'hififace_unofficial_256', 'hyperswap_1a_256', 'hyperswap_1b_256', 'hyperswap_1c_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_unofficial_512' ]

facefusion/uis/components/frame_colorizer_options.py

@@ -3,10 +3,10 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
+from facefusion.common_helper import calculate_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FrameColorizerModel
+from facefusion.processors.types import FrameColorizerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FRAME_COLORIZER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -35,7 +35,7 @@ def render() -> None:
 	FRAME_COLORIZER_BLEND_SLIDER = gradio.Slider(
 		label = wording.get('uis.frame_colorizer_blend_slider'),
 		value = state_manager.get_item('frame_colorizer_blend'),
-		step = calc_int_step(processors_choices.frame_colorizer_blend_range),
+		step = calculate_int_step(processors_choices.frame_colorizer_blend_range),
 		minimum = processors_choices.frame_colorizer_blend_range[0],
 		maximum = processors_choices.frame_colorizer_blend_range[-1],
 		visible = has_frame_colorizer

facefusion/uis/components/frame_enhancer_options.py

@@ -3,10 +3,10 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
+from facefusion.common_helper import calculate_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FrameEnhancerModel
+from facefusion.processors.types import FrameEnhancerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FRAME_ENHANCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -27,7 +27,7 @@ def render() -> None:
 	FRAME_ENHANCER_BLEND_SLIDER = gradio.Slider(
 		label = wording.get('uis.frame_enhancer_blend_slider'),
 		value = state_manager.get_item('frame_enhancer_blend'),
-		step = calc_int_step(processors_choices.frame_enhancer_blend_range),
+		step = calculate_int_step(processors_choices.frame_enhancer_blend_range),
 		minimum = processors_choices.frame_enhancer_blend_range[0],
 		maximum = processors_choices.frame_enhancer_blend_range[-1],
 		visible = has_frame_enhancer

facefusion/uis/components/instant_runner.py

@@ -9,7 +9,7 @@ from facefusion.core import process_step
 from facefusion.filesystem import is_directory, is_image, is_video
 from facefusion.jobs import job_helper, job_manager, job_runner, job_store
 from facefusion.temp_helper import clear_temp_directory
-from facefusion.typing import Args, UiWorkflow
+from facefusion.types import Args, UiWorkflow
 from facefusion.uis.core import get_ui_component
 from facefusion.uis.ui_helper import suggest_output_path
 
@@ -54,7 +54,7 @@ def listen() -> None:
 	if output_image and output_video:
 		INSTANT_RUNNER_START_BUTTON.click(start, outputs = [ INSTANT_RUNNER_START_BUTTON, INSTANT_RUNNER_STOP_BUTTON ])
 		INSTANT_RUNNER_START_BUTTON.click(run, outputs = [ INSTANT_RUNNER_START_BUTTON, INSTANT_RUNNER_STOP_BUTTON, output_image, output_video ])
-		INSTANT_RUNNER_STOP_BUTTON.click(stop, outputs = [ INSTANT_RUNNER_START_BUTTON, INSTANT_RUNNER_STOP_BUTTON ])
+		INSTANT_RUNNER_STOP_BUTTON.click(stop, outputs = [ INSTANT_RUNNER_START_BUTTON, INSTANT_RUNNER_STOP_BUTTON, output_image, output_video ])
 		INSTANT_RUNNER_CLEAR_BUTTON.click(clear, outputs = [ output_image, output_video ])
 	if ui_workflow_dropdown:
 		ui_workflow_dropdown.change(remote_update, inputs = ui_workflow_dropdown, outputs = INSTANT_RUNNER_WRAPPER)
@@ -92,14 +92,14 @@ def create_and_run_job(step_args : Args) -> bool:
 	job_id = job_helper.suggest_job_id('ui')
 
 	for key in job_store.get_job_keys():
-		state_manager.sync_item(key) #type:ignore
+		state_manager.sync_item(key) #type:ignore[arg-type]
 
 	return job_manager.create_job(job_id) and job_manager.add_step(job_id, step_args) and job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step)
 
 
-def stop() -> Tuple[gradio.Button, gradio.Button]:
+def stop() -> Tuple[gradio.Button, gradio.Button, gradio.Image, gradio.Video]:
 	process_manager.stop()
-	return gradio.Button(visible = True), gradio.Button(visible = False)
+	return gradio.Button(visible = True), gradio.Button(visible = False), gradio.Image(value = None), gradio.Video(value = None)
 
 
 def clear() -> Tuple[gradio.Image, gradio.Video]:

facefusion/uis/components/job_list.py

@@ -6,7 +6,7 @@ import facefusion.choices
 from facefusion import state_manager, wording
 from facefusion.common_helper import get_first
 from facefusion.jobs import job_list, job_manager
-from facefusion.typing import JobStatus
+from facefusion.types import JobStatus
 from facefusion.uis.core import get_ui_component
 
 JOB_LIST_JOBS_DATAFRAME : Optional[gradio.Dataframe] = None

facefusion/uis/components/job_list_options.py

@@ -6,7 +6,7 @@ import facefusion.choices
 from facefusion import state_manager, wording
 from facefusion.common_helper import get_first
 from facefusion.jobs import job_manager
-from facefusion.typing import JobStatus
+from facefusion.types import JobStatus
 from facefusion.uis.core import register_ui_component
 
 JOB_LIST_JOB_STATUS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None

facefusion/uis/components/job_manager.py

@@ -7,10 +7,10 @@ from facefusion.args import collect_step_args
 from facefusion.common_helper import get_first, get_last
 from facefusion.filesystem import is_directory
 from facefusion.jobs import job_manager
-from facefusion.typing import UiWorkflow
+from facefusion.types import UiWorkflow
 from facefusion.uis import choices as uis_choices
 from facefusion.uis.core import get_ui_component
-from facefusion.uis.typing import JobManagerAction
+from facefusion.uis.types import JobManagerAction
 from facefusion.uis.ui_helper import convert_int_none, convert_str_none, suggest_output_path
 
 JOB_MANAGER_WRAPPER : Optional[gradio.Column] = None
@@ -89,6 +89,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 
 	if is_directory(step_args.get('output_path')):
 		step_args['output_path'] = suggest_output_path(step_args.get('output_path'), state_manager.get_item('target_path'))
+
 	if job_action == 'job-create':
 		if created_job_id and job_manager.create_job(created_job_id):
 			updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
@@ -97,6 +98,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 			return gradio.Dropdown(value = 'job-add-step'), gradio.Textbox(visible = False), gradio.Dropdown(value = created_job_id, choices = updated_job_ids, visible = True), gradio.Dropdown()
 		else:
 			logger.error(wording.get('job_not_created').format(job_id = created_job_id), __name__)
+
 	if job_action == 'job-submit':
 		if selected_job_id and job_manager.submit_job(selected_job_id):
 			updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
@@ -105,6 +107,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 			return gradio.Dropdown(), gradio.Textbox(), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids, visible = True), gradio.Dropdown()
 		else:
 			logger.error(wording.get('job_not_submitted').format(job_id = selected_job_id), __name__)
+
 	if job_action == 'job-delete':
 		if selected_job_id and job_manager.delete_job(selected_job_id):
 			updated_job_ids = job_manager.find_job_ids('drafted') + job_manager.find_job_ids('queued') + job_manager.find_job_ids('failed') + job_manager.find_job_ids('completed') or [ 'none' ]
@@ -113,6 +116,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 			return gradio.Dropdown(), gradio.Textbox(), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids, visible = True), gradio.Dropdown()
 		else:
 			logger.error(wording.get('job_not_deleted').format(job_id = selected_job_id), __name__)
+
 	if job_action == 'job-add-step':
 		if selected_job_id and job_manager.add_step(selected_job_id, step_args):
 			state_manager.set_item('output_path', output_path)
@@ -121,6 +125,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 		else:
 			state_manager.set_item('output_path', output_path)
 			logger.error(wording.get('job_step_not_added').format(job_id = selected_job_id), __name__)
+
 	if job_action == 'job-remix-step':
 		if selected_job_id and job_manager.has_step(selected_job_id, selected_step_index) and job_manager.remix_step(selected_job_id, selected_step_index, step_args):
 			updated_step_choices = get_step_choices(selected_job_id) or [ 'none' ] #type:ignore[list-item]
@@ -131,6 +136,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 		else:
 			state_manager.set_item('output_path', output_path)
 			logger.error(wording.get('job_remix_step_not_added').format(job_id = selected_job_id, step_index = selected_step_index), __name__)
+
 	if job_action == 'job-insert-step':
 		if selected_job_id and job_manager.has_step(selected_job_id, selected_step_index) and job_manager.insert_step(selected_job_id, selected_step_index, step_args):
 			updated_step_choices = get_step_choices(selected_job_id) or [ 'none' ] #type:ignore[list-item]
@@ -141,6 +147,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 		else:
 			state_manager.set_item('output_path', output_path)
 			logger.error(wording.get('job_step_not_inserted').format(job_id = selected_job_id, step_index = selected_step_index), __name__)
+
 	if job_action == 'job-remove-step':
 		if selected_job_id and job_manager.has_step(selected_job_id, selected_step_index) and job_manager.remove_step(selected_job_id, selected_step_index):
 			updated_step_choices = get_step_choices(selected_job_id) or [ 'none' ] #type:ignore[list-item]
@@ -160,16 +167,19 @@ def get_step_choices(job_id : str) -> List[int]:
 def update(job_action : JobManagerAction, selected_job_id : str) -> Tuple[gradio.Textbox, gradio.Dropdown, gradio.Dropdown]:
 	if job_action == 'job-create':
 		return gradio.Textbox(value = None, visible = True), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False)
+
 	if job_action == 'job-delete':
 		updated_job_ids = job_manager.find_job_ids('drafted') + job_manager.find_job_ids('queued') + job_manager.find_job_ids('failed') + job_manager.find_job_ids('completed') or [ 'none' ]
 		updated_job_id = selected_job_id if selected_job_id in updated_job_ids else get_last(updated_job_ids)
 
 		return gradio.Textbox(visible = False), gradio.Dropdown(value = updated_job_id, choices = updated_job_ids, visible = True), gradio.Dropdown(visible = False)
+
 	if job_action in [ 'job-submit', 'job-add-step' ]:
 		updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
 		updated_job_id = selected_job_id if selected_job_id in updated_job_ids else get_last(updated_job_ids)
 
 		return gradio.Textbox(visible = False), gradio.Dropdown(value = updated_job_id, choices = updated_job_ids, visible = True), gradio.Dropdown(visible = False)
+
 	if job_action in [ 'job-remix-step', 'job-insert-step', 'job-remove-step' ]:
 		updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
 		updated_job_id = selected_job_id if selected_job_id in updated_job_ids else get_last(updated_job_ids)

facefusion/uis/components/job_runner.py

@@ -7,10 +7,10 @@ from facefusion import logger, process_manager, state_manager, wording
 from facefusion.common_helper import get_first, get_last
 from facefusion.core import process_step
 from facefusion.jobs import job_manager, job_runner, job_store
-from facefusion.typing import UiWorkflow
+from facefusion.types import UiWorkflow
 from facefusion.uis import choices as uis_choices
 from facefusion.uis.core import get_ui_component
-from facefusion.uis.typing import JobRunnerAction
+from facefusion.uis.types import JobRunnerAction
 from facefusion.uis.ui_helper import convert_str_none
 
 JOB_RUNNER_WRAPPER : Optional[gradio.Column] = None
@@ -84,36 +84,41 @@ def run(job_action : JobRunnerAction, job_id : str) -> Tuple[gradio.Button, grad
 	job_id = convert_str_none(job_id)
 
 	for key in job_store.get_job_keys():
-		state_manager.sync_item(key) #type:ignore
+		state_manager.sync_item(key) #type:ignore[arg-type]
 
 	if job_action == 'job-run':
 		logger.info(wording.get('running_job').format(job_id = job_id), __name__)
 		if job_id and job_runner.run_job(job_id, process_step):
-			logger.info(wording.get('processing_job_succeed').format(job_id = job_id), __name__)
+			logger.info(wording.get('processing_job_succeeded').format(job_id = job_id), __name__)
 		else:
 			logger.info(wording.get('processing_job_failed').format(job_id = job_id), __name__)
 		updated_job_ids = job_manager.find_job_ids('queued') or [ 'none' ]
 
 		return gradio.Button(visible = True), gradio.Button(visible = False), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids)
+
 	if job_action == 'job-run-all':
 		logger.info(wording.get('running_jobs'), __name__)
-		if job_runner.run_jobs(process_step):
-			logger.info(wording.get('processing_jobs_succeed'), __name__)
+		halt_on_error = False
+		if job_runner.run_jobs(process_step, halt_on_error):
+			logger.info(wording.get('processing_jobs_succeeded'), __name__)
 		else:
 			logger.info(wording.get('processing_jobs_failed'), __name__)
+
 	if job_action == 'job-retry':
 		logger.info(wording.get('retrying_job').format(job_id = job_id), __name__)
 		if job_id and job_runner.retry_job(job_id, process_step):
-			logger.info(wording.get('processing_job_succeed').format(job_id = job_id), __name__)
+			logger.info(wording.get('processing_job_succeeded').format(job_id = job_id), __name__)
 		else:
 			logger.info(wording.get('processing_job_failed').format(job_id = job_id), __name__)
 		updated_job_ids = job_manager.find_job_ids('failed') or [ 'none' ]
 
 		return gradio.Button(visible = True), gradio.Button(visible = False), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids)
+
 	if job_action == 'job-retry-all':
 		logger.info(wording.get('retrying_jobs'), __name__)
-		if job_runner.retry_jobs(process_step):
-			logger.info(wording.get('processing_jobs_succeed'), __name__)
+		halt_on_error = False
+		if job_runner.retry_jobs(process_step, halt_on_error):
+			logger.info(wording.get('processing_jobs_succeeded'), __name__)
 		else:
 			logger.info(wording.get('processing_jobs_failed'), __name__)
 	return gradio.Button(visible = True), gradio.Button(visible = False), gradio.Dropdown()
@@ -129,6 +134,7 @@ def update_job_action(job_action : JobRunnerAction) -> gradio.Dropdown:
 		updated_job_ids = job_manager.find_job_ids('queued') or [ 'none' ]
 
 		return gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids, visible = True)
+
 	if job_action == 'job-retry':
 		updated_job_ids = job_manager.find_job_ids('failed') or [ 'none' ]
 

facefusion/uis/components/lip_syncer_options.py

@@ -1,18 +1,21 @@
-from typing import List, Optional
+from typing import List, Optional, Tuple
 
 import gradio
 
 from facefusion import state_manager, wording
+from facefusion.common_helper import calculate_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import LipSyncerModel
+from facefusion.processors.types import LipSyncerModel, LipSyncerWeight
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 LIP_SYNCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
+LIP_SYNCER_WEIGHT_SLIDER : Optional[gradio.Slider] = None
 
 
 def render() -> None:
 	global LIP_SYNCER_MODEL_DROPDOWN
+	global LIP_SYNCER_WEIGHT_SLIDER
 
 	has_lip_syncer = 'lip_syncer' in state_manager.get_item('processors')
 	LIP_SYNCER_MODEL_DROPDOWN = gradio.Dropdown(
@@ -21,20 +24,30 @@ def render() -> None:
 		value = state_manager.get_item('lip_syncer_model'),
 		visible = has_lip_syncer
 	)
+	LIP_SYNCER_WEIGHT_SLIDER = gradio.Slider(
+		label = wording.get('uis.lip_syncer_weight_slider'),
+		value = state_manager.get_item('lip_syncer_weight'),
+		step = calculate_float_step(processors_choices.lip_syncer_weight_range),
+		minimum = processors_choices.lip_syncer_weight_range[0],
+		maximum = processors_choices.lip_syncer_weight_range[-1],
+		visible = has_lip_syncer
+	)
 	register_ui_component('lip_syncer_model_dropdown', LIP_SYNCER_MODEL_DROPDOWN)
+	register_ui_component('lip_syncer_weight_slider', LIP_SYNCER_WEIGHT_SLIDER)
 
 
 def listen() -> None:
 	LIP_SYNCER_MODEL_DROPDOWN.change(update_lip_syncer_model, inputs = LIP_SYNCER_MODEL_DROPDOWN, outputs = LIP_SYNCER_MODEL_DROPDOWN)
+	LIP_SYNCER_WEIGHT_SLIDER.release(update_lip_syncer_weight, inputs = LIP_SYNCER_WEIGHT_SLIDER)
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = LIP_SYNCER_MODEL_DROPDOWN)
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ LIP_SYNCER_MODEL_DROPDOWN, LIP_SYNCER_WEIGHT_SLIDER ])
 
 
-def remote_update(processors : List[str]) -> gradio.Dropdown:
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
 	has_lip_syncer = 'lip_syncer' in processors
-	return gradio.Dropdown(visible = has_lip_syncer)
+	return gradio.Dropdown(visible = has_lip_syncer), gradio.Slider(visible = has_lip_syncer)
 
 
 def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdown:
@@ -45,3 +58,7 @@ def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdow
 	if lip_syncer_module.pre_check():
 		return gradio.Dropdown(value = state_manager.get_item('lip_syncer_model'))
 	return gradio.Dropdown()
+
+
+def update_lip_syncer_weight(lip_syncer_weight : LipSyncerWeight) -> None:
+	state_manager.set_item('lip_syncer_weight', lip_syncer_weight)

facefusion/uis/components/memory.py

@@ -4,8 +4,8 @@ import gradio
 
 import facefusion.choices
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
-from facefusion.typing import VideoMemoryStrategy
+from facefusion.common_helper import calculate_int_step
+from facefusion.types import VideoMemoryStrategy
 
 VIDEO_MEMORY_STRATEGY_DROPDOWN : Optional[gradio.Dropdown] = None
 SYSTEM_MEMORY_LIMIT_SLIDER : Optional[gradio.Slider] = None
@@ -22,7 +22,7 @@ def render() -> None:
 	)
 	SYSTEM_MEMORY_LIMIT_SLIDER = gradio.Slider(
 		label = wording.get('uis.system_memory_limit_slider'),
-		step = calc_int_step(facefusion.choices.system_memory_limit_range),
+		step = calculate_int_step(facefusion.choices.system_memory_limit_range),
 		minimum = facefusion.choices.system_memory_limit_range[0],
 		maximum = facefusion.choices.system_memory_limit_range[-1],
 		value = state_manager.get_item('system_memory_limit')

facefusion/uis/components/output.py

@@ -1,4 +1,5 @@
 import tempfile
+from pathlib import Path
 from typing import Optional
 
 import gradio
@@ -17,7 +18,12 @@ def render() -> None:
 	global OUTPUT_VIDEO
 
 	if not state_manager.get_item('output_path'):
-		state_manager.set_item('output_path', tempfile.gettempdir())
+		documents_directory = Path.home().joinpath('Documents')
+
+		if documents_directory.exists():
+			state_manager.set_item('output_path', documents_directory)
+		else:
+			state_manager.set_item('output_path', tempfile.gettempdir())
 	OUTPUT_PATH_TEXTBOX = gradio.Textbox(
 		label = wording.get('uis.output_path_textbox'),
 		value = state_manager.get_item('output_path'),