3.6.0 (#1062 )

* mark as next * add fran model * add support for corridor key (#1060) * introduce despill color * simplify the apply dispill color * finalize naming for both fill and despill * follow vision_frame convension * patch fran model * adjust fran urls * Feat/dynamic env setup (#1061) * dynamic environment setup * dynamic environment setup * fix fran model * prevent directml using incompatible corridor_key model * fix environment setup for windows * switch to corridor_key_1024 and corridor_key_2048 * switch to corridor_key_1024 and corridor_key_2048 * mark it as 3.6.0 * rename environment to conda * rename environment to conda * fix testing for face analyser * some background remove cosmetics * some background remove cosmetics * some background remove cosmetics * update preview --------- Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
update licenses
2026-07-28 12:59:03 +02:00 · 2026-03-16 15:08:43 +01:00 · 2026-03-09 21:24:53 +01:00 · 2026-03-08 11:00:45 +01:00 · 2026-02-18 09:18:03 +01:00 · 2026-02-11 09:35:08 +01:00
74 changed files with 777 additions and 459 deletions
@@ -67,7 +67,8 @@ processors =
 age_modifier_model =
 age_modifier_direction =
 background_remover_model =
-background_remover_color =
+background_remover_fill_color =
+background_remover_despill_color =
 deep_swapper_model =
 deep_swapper_morph =
 expression_restorer_model =
@@ -4,7 +4,8 @@ import os

 os.environ['OMP_NUM_THREADS'] = '1'

-from facefusion import core
+from facefusion import conda, core

 if __name__ == '__main__':
+	conda.setup()
 	core.cli()
@@ -7,6 +7,84 @@ from facefusion.types import ApplyStateItem, Args
 from facefusion.vision import detect_video_fps


+def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
+	apply_state_item('command', args.get('command'))
+	apply_state_item('temp_path', args.get('temp_path'))
+	apply_state_item('jobs_path', args.get('jobs_path'))
+	apply_state_item('source_paths', args.get('source_paths'))
+	apply_state_item('target_path', args.get('target_path'))
+	apply_state_item('output_path', args.get('output_path'))
+	apply_state_item('source_pattern', args.get('source_pattern'))
+	apply_state_item('target_pattern', args.get('target_pattern'))
+	apply_state_item('output_pattern', args.get('output_pattern'))
+	apply_state_item('face_detector_model', args.get('face_detector_model'))
+	apply_state_item('face_detector_size', args.get('face_detector_size'))
+	apply_state_item('face_detector_margin', normalize_space(args.get('face_detector_margin')))
+	apply_state_item('face_detector_angles', args.get('face_detector_angles'))
+	apply_state_item('face_detector_score', args.get('face_detector_score'))
+	apply_state_item('face_landmarker_model', args.get('face_landmarker_model'))
+	apply_state_item('face_landmarker_score', args.get('face_landmarker_score'))
+	apply_state_item('face_selector_mode', args.get('face_selector_mode'))
+	apply_state_item('face_selector_order', args.get('face_selector_order'))
+	apply_state_item('face_selector_age_start', args.get('face_selector_age_start'))
+	apply_state_item('face_selector_age_end', args.get('face_selector_age_end'))
+	apply_state_item('face_selector_gender', args.get('face_selector_gender'))
+	apply_state_item('face_selector_race', args.get('face_selector_race'))
+	apply_state_item('reference_face_position', args.get('reference_face_position'))
+	apply_state_item('reference_face_distance', args.get('reference_face_distance'))
+	apply_state_item('reference_frame_number', args.get('reference_frame_number'))
+	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_space(args.get('face_mask_padding')))
+	apply_state_item('voice_extractor_model', args.get('voice_extractor_model'))
+	apply_state_item('trim_frame_start', args.get('trim_frame_start'))
+	apply_state_item('trim_frame_end', args.get('trim_frame_end'))
+	apply_state_item('temp_frame_format', args.get('temp_frame_format'))
+	apply_state_item('keep_temp', args.get('keep_temp'))
+	apply_state_item('output_image_quality', args.get('output_image_quality'))
+	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'))
+	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)
+
+	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)
+
+	apply_state_item('open_browser', args.get('open_browser'))
+	apply_state_item('ui_layouts', args.get('ui_layouts'))
+	apply_state_item('ui_workflow', args.get('ui_workflow'))
+	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('download_providers', args.get('download_providers'))
+	apply_state_item('download_scope', args.get('download_scope'))
+	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'))
+	apply_state_item('video_memory_strategy', args.get('video_memory_strategy'))
+	apply_state_item('system_memory_limit', args.get('system_memory_limit'))
+	apply_state_item('log_level', args.get('log_level'))
+	apply_state_item('halt_on_error', args.get('halt_on_error'))
+	apply_state_item('job_id', args.get('job_id'))
+	apply_state_item('job_status', args.get('job_status'))
+	apply_state_item('step_index', args.get('step_index'))
+
+
 def reduce_step_args(args : Args) -> Args:
 	step_args =\
 	{
@@ -37,95 +115,3 @@ def collect_job_args() -> Args:
 		key: state_manager.get_item(key) for key in job_store.get_job_keys() #type:ignore[arg-type]
 	}
 	return job_args
-
-
-def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
-	# general
-	apply_state_item('command', args.get('command'))
-	# paths
-	apply_state_item('temp_path', args.get('temp_path'))
-	apply_state_item('jobs_path', args.get('jobs_path'))
-	apply_state_item('source_paths', args.get('source_paths'))
-	apply_state_item('target_path', args.get('target_path'))
-	apply_state_item('output_path', args.get('output_path'))
-	# patterns
-	apply_state_item('source_pattern', args.get('source_pattern'))
-	apply_state_item('target_pattern', args.get('target_pattern'))
-	apply_state_item('output_pattern', args.get('output_pattern'))
-	# face detector
-	apply_state_item('face_detector_model', args.get('face_detector_model'))
-	apply_state_item('face_detector_size', args.get('face_detector_size'))
-	apply_state_item('face_detector_margin', normalize_space(args.get('face_detector_margin')))
-	apply_state_item('face_detector_angles', args.get('face_detector_angles'))
-	apply_state_item('face_detector_score', args.get('face_detector_score'))
-	# face landmarker
-	apply_state_item('face_landmarker_model', args.get('face_landmarker_model'))
-	apply_state_item('face_landmarker_score', args.get('face_landmarker_score'))
-	# face selector
-	apply_state_item('face_selector_mode', args.get('face_selector_mode'))
-	apply_state_item('face_selector_order', args.get('face_selector_order'))
-	apply_state_item('face_selector_age_start', args.get('face_selector_age_start'))
-	apply_state_item('face_selector_age_end', args.get('face_selector_age_end'))
-	apply_state_item('face_selector_gender', args.get('face_selector_gender'))
-	apply_state_item('face_selector_race', args.get('face_selector_race'))
-	apply_state_item('reference_face_position', args.get('reference_face_position'))
-	apply_state_item('reference_face_distance', args.get('reference_face_distance'))
-	apply_state_item('reference_frame_number', args.get('reference_frame_number'))
-	# face masker
-	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_space(args.get('face_mask_padding')))
-	# 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'))
-	apply_state_item('temp_frame_format', args.get('temp_frame_format'))
-	apply_state_item('keep_temp', args.get('keep_temp'))
-	# output creation
-	apply_state_item('output_image_quality', args.get('output_image_quality'))
-	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'))
-	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)
-	# processors
-	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)
-	# uis
-	apply_state_item('open_browser', args.get('open_browser'))
-	apply_state_item('ui_layouts', args.get('ui_layouts'))
-	apply_state_item('ui_workflow', args.get('ui_workflow'))
-	# execution
-	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'))
-	# 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'))
-	apply_state_item('step_index', args.get('step_index'))
@@ -89,7 +89,7 @@ def cycle(cycle_count : int) -> BenchmarkCycleSet:

 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)
+	return os.path.join(tempfile.gettempdir(), hashlib.sha1(target_path.encode()).hexdigest() + target_file_extension)


 def render() -> None:
@@ -43,9 +43,9 @@ 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)
+		cv2.utils.logging.setLogLevel(0)
 		camera_capture = get_local_camera_capture(camera_id)
-		cv2.setLogLevel(3)
+		cv2.utils.logging.setLogLevel(3)

 		if camera_capture and camera_capture.isOpened():
 			local_camera_ids.append(camera_id)
@@ -1,5 +1,5 @@
 import logging
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_float_range, create_int_range
 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
@@ -12,15 +12,15 @@ face_detector_set : FaceDetectorSet =\
 	'yolo_face': [ '640x640' ],
 	'yunet': [ '640x640' ]
 }
-face_detector_models : List[FaceDetectorModel] = list(face_detector_set.keys())
-face_landmarker_models : List[FaceLandmarkerModel] = [ 'many', '2dfan4', 'peppa_wutz' ]
-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] = [ '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', 'area', 'region' ]
+face_detector_models : List[FaceDetectorModel] = list(get_args(FaceDetectorModel))
+face_landmarker_models : List[FaceLandmarkerModel] = list(get_args(FaceLandmarkerModel))
+face_selector_modes : List[FaceSelectorMode] = list(get_args(FaceSelectorMode))
+face_selector_orders : List[FaceSelectorOrder] = list(get_args(FaceSelectorOrder))
+face_selector_genders : List[Gender] = list(get_args(Gender))
+face_selector_races : List[Race] = list(get_args(Race))
+face_occluder_models : List[FaceOccluderModel] = list(get_args(FaceOccluderModel))
+face_parser_models : List[FaceParserModel] = list(get_args(FaceParserModel))
+face_mask_types : List[FaceMaskType] = list(get_args(FaceMaskType))
 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 ],
@@ -40,10 +40,10 @@ 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())
+face_mask_areas : List[FaceMaskArea] = list(get_args(FaceMaskArea))
+face_mask_regions : List[FaceMaskRegion] = list(get_args(FaceMaskRegion))

-voice_extractor_models : List[VoiceExtractorModel] = [ 'kim_vocal_1', 'kim_vocal_2', 'uvr_mdxnet' ]
+voice_extractor_models : List[VoiceExtractorModel] = list(get_args(VoiceExtractorModel))

 audio_type_set : AudioTypeSet =\
 {
@@ -74,21 +74,21 @@ video_type_set : VideoTypeSet =\
 	'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' ]
+audio_formats : List[AudioFormat] = list(get_args(AudioFormat))
+image_formats : List[ImageFormat] = list(get_args(ImageFormat))
+video_formats : List[VideoFormat] = list(get_args(VideoFormat))
+temp_frame_formats : List[TempFrameFormat] = list(get_args(TempFrameFormat))

+output_audio_encoders : List[AudioEncoder] = list(get_args(AudioEncoder))
+output_video_encoders : List[VideoEncoder] = list(get_args(VideoEncoder))
 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' ]
+	'audio': output_audio_encoders,
+	'video': output_video_encoders
 }
-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' ]
+output_video_presets : List[VideoPreset] = list(get_args(VideoPreset))

-benchmark_modes : List[BenchmarkMode] = [ 'warm', 'cold' ]
+benchmark_modes : List[BenchmarkMode] = list(get_args(BenchmarkMode))
 benchmark_set : BenchmarkSet =\
 {
 	'240p': '.assets/examples/target-240p.mp4',
@@ -99,20 +99,21 @@ benchmark_set : BenchmarkSet =\
 	'1440p': '.assets/examples/target-1440p.mp4',
 	'2160p': '.assets/examples/target-2160p.mp4'
 }
-benchmark_resolutions : List[BenchmarkResolution] = list(benchmark_set.keys())
+benchmark_resolutions : List[BenchmarkResolution] = list(get_args(BenchmarkResolution))

 execution_provider_set : ExecutionProviderSet =\
 {
 	'cuda': 'CUDAExecutionProvider',
 	'tensorrt': 'TensorrtExecutionProvider',
-	'directml': 'DmlExecutionProvider',
 	'rocm': 'ROCMExecutionProvider',
 	'migraphx': 'MIGraphXExecutionProvider',
-	'openvino': 'OpenVINOExecutionProvider',
 	'coreml': 'CoreMLExecutionProvider',
+	'openvino': 'OpenVINOExecutionProvider',
+	'qnn': 'QNNExecutionProvider',
+	'directml': 'DmlExecutionProvider',
 	'cpu': 'CPUExecutionProvider'
 }
-execution_providers : List[ExecutionProvider] = list(execution_provider_set.keys())
+execution_providers : List[ExecutionProvider] = list(get_args(ExecutionProvider))
 download_provider_set : DownloadProviderSet =\
 {
 	'github':
@@ -133,10 +134,10 @@ download_provider_set : DownloadProviderSet =\
 		'path': '/facefusion/{base_name}/resolve/main/{file_name}'
 	}
 }
-download_providers : List[DownloadProvider] = list(download_provider_set.keys())
-download_scopes : List[DownloadScope] = [ 'lite', 'full' ]
+download_providers : List[DownloadProvider] = list(get_args(DownloadProvider))
+download_scopes : List[DownloadScope] = list(get_args(DownloadScope))

-video_memory_strategies : List[VideoMemoryStrategy] = [ 'strict', 'moderate', 'tolerant' ]
+video_memory_strategies : List[VideoMemoryStrategy] = list(get_args(VideoMemoryStrategy))

 log_level_set : LogLevelSet =\
 {
@@ -145,10 +146,10 @@ log_level_set : LogLevelSet =\
 	'info': logging.INFO,
 	'debug': logging.DEBUG
 }
-log_levels : List[LogLevel] = list(log_level_set.keys())
+log_levels : List[LogLevel] = list(get_args(LogLevel))

-ui_workflows : List[UiWorkflow] = [ 'instant_runner', 'job_runner', 'job_manager' ]
-job_statuses : List[JobStatus] = [ 'drafted', 'queued', 'completed', 'failed' ]
+ui_workflows : List[UiWorkflow] = list(get_args(UiWorkflow))
+job_statuses : List[JobStatus] = list(get_args(JobStatus))

 benchmark_cycle_count_range : Sequence[int] = create_int_range(1, 10, 1)
 execution_thread_count_range : Sequence[int] = create_int_range(1, 32, 1)
@@ -0,0 +1,41 @@
+import os
+import sys
+from typing import List
+
+from facefusion.common_helper import is_linux, is_windows
+
+
+def setup() -> None:
+	conda_prefix = os.getenv('CONDA_PREFIX')
+	conda_ready = os.getenv('CONDA_READY')
+
+	if conda_prefix and not conda_ready:
+		if is_linux():
+			python_id = 'python' + str(sys.version_info.major) + '.' + str(sys.version_info.minor)
+			library_paths : List[str] =\
+			[
+				os.path.join(conda_prefix, 'lib'),
+				os.path.join(conda_prefix, 'lib', python_id, 'site-packages', 'tensorrt_libs')
+			]
+			library_paths = list(filter(os.path.exists, library_paths))
+
+			if library_paths:
+				if os.getenv('LD_LIBRARY_PATH'):
+					library_paths.append(os.getenv('LD_LIBRARY_PATH'))
+				os.environ['LD_LIBRARY_PATH'] = os.pathsep.join(library_paths)
+				os.environ['CONDA_READY'] = '1'
+				os.execv(sys.executable, [ sys.executable ] + sys.argv)
+
+		if is_windows():
+			library_paths =\
+			[
+				os.path.join(conda_prefix, 'Lib'),
+				os.path.join(conda_prefix, 'Lib', 'site-packages', 'tensorrt_libs')
+			]
+			library_paths = list(filter(os.path.exists, library_paths))
+
+			if library_paths:
+				if os.getenv('PATH'):
+					library_paths.append(os.getenv('PATH'))
+				os.environ['PATH'] = os.pathsep.join(library_paths)
+				os.environ['CONDA_READY'] = '1'
@@ -9,7 +9,7 @@ from facefusion.types import Command
 def run(commands : List[Command]) -> List[Command]:
 	user_agent = metadata.get('name') + '/' + metadata.get('version')

-	return [ shutil.which('curl'), '--user-agent', user_agent, '--insecure', '--location', '--silent' ] + commands
+	return [ shutil.which('curl'), '--user-agent', user_agent, '--location', '--silent' ] + commands


 def chain(*commands : List[Command]) -> List[Command]:
@@ -1,15 +1,17 @@
+import os
 import shutil
 import subprocess
 import xml.etree.ElementTree as ElementTree
 from functools import lru_cache
 from typing import List, Optional

-from onnxruntime import get_available_providers, set_default_logger_severity
+import onnxruntime

 import facefusion.choices
-from facefusion.types import ExecutionDevice, ExecutionProvider, InferenceSessionProvider, ValueAndUnit
+from facefusion.filesystem import create_directory, is_directory
+from facefusion.types import ExecutionDevice, ExecutionProvider, InferenceOptionSet, InferenceProvider, ValueAndUnit

-set_default_logger_severity(3)
+onnxruntime.set_default_logger_severity(3)


 def has_execution_provider(execution_provider : ExecutionProvider) -> bool:
@@ -17,7 +19,7 @@ def has_execution_provider(execution_provider : ExecutionProvider) -> bool:


 def get_available_execution_providers() -> List[ExecutionProvider]:
-	inference_session_providers = get_available_providers()
+	inference_session_providers = onnxruntime.get_available_providers()
 	available_execution_providers : List[ExecutionProvider] = []

 	for execution_provider, execution_provider_value in facefusion.choices.execution_provider_set.items():
@@ -28,54 +30,86 @@ def get_available_execution_providers() -> List[ExecutionProvider]:
 	return available_execution_providers


-def create_inference_session_providers(execution_device_id : int, execution_providers : List[ExecutionProvider]) -> List[InferenceSessionProvider]:
-	inference_session_providers : List[InferenceSessionProvider] = []
+def create_inference_providers(execution_device_id : int, execution_providers : List[ExecutionProvider]) -> List[InferenceProvider]:
+	inference_providers : List[InferenceProvider] = []
+	cache_path = resolve_cache_path()

 	for execution_provider in execution_providers:
 		if execution_provider == 'cuda':
-			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id,
 				'cudnn_conv_algo_search': resolve_cudnn_conv_algo_search()
 			}))
+
 		if execution_provider == 'tensorrt':
-			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_option_set : InferenceOptionSet =\
 			{
-				'device_id': execution_device_id,
-				'trt_engine_cache_enable': True,
-				'trt_engine_cache_path': '.caches',
-				'trt_timing_cache_enable': True,
-				'trt_timing_cache_path': '.caches',
-				'trt_builder_optimization_level': 5
-			}))
+				'device_id': execution_device_id
+			}
+			if is_directory(cache_path) or create_directory(cache_path):
+				inference_option_set.update(
+				{
+					'trt_engine_cache_enable': True,
+					'trt_engine_cache_path': cache_path,
+					'trt_timing_cache_enable': True,
+					'trt_timing_cache_path': cache_path,
+					'trt_builder_optimization_level': 4
+				})
+			inference_providers.append((facefusion.choices.execution_provider_set.get(execution_provider), inference_option_set))
+
 		if execution_provider in [ 'directml', 'rocm' ]:
-			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_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),
+			inference_option_set =\
 			{
-				'device_id': execution_device_id,
-				'migraphx_model_cache_dir': '.caches'
-			}))
+				'device_id': execution_device_id
+			}
+			if is_directory(cache_path) or create_directory(cache_path):
+				inference_option_set.update(
+				{
+					'migraphx_model_cache_dir': cache_path
+				})
+			inference_providers.append((facefusion.choices.execution_provider_set.get(execution_provider), inference_option_set))
+
+		if execution_provider == 'coreml':
+			inference_option_set =\
+			{
+				'SpecializationStrategy': 'FastPrediction'
+			}
+			if is_directory(cache_path) or create_directory(cache_path):
+				inference_option_set.update(
+				{
+					'ModelCacheDirectory': cache_path
+				})
+			inference_providers.append((facefusion.choices.execution_provider_set.get(execution_provider), inference_option_set))
+
 		if execution_provider == 'openvino':
-			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			inference_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_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+
+		if execution_provider == 'qnn':
+			inference_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
-				'SpecializationStrategy': 'FastPrediction',
-				'ModelCacheDirectory': '.caches'
+				'device_id': execution_device_id,
+				'backend_type': 'htp'
 			}))

 	if 'cpu' in execution_providers:
-		inference_session_providers.append(facefusion.choices.execution_provider_set.get('cpu'))
+		inference_providers.append(facefusion.choices.execution_provider_set.get('cpu'))

-	return inference_session_providers
+	return inference_providers
+
+
+def resolve_cache_path() -> str:
+	return os.path.join('.caches', onnxruntime.get_version_string())


 def resolve_cudnn_conv_algo_search() -> str:
@@ -20,7 +20,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			'__metadata__':
 			{
 				'vendor': 'dchen236',
-				'license': 'Non-Commercial',
+				'license': 'CC-BY-4.0',
 				'year': 2021
 			},
 			'hashes':
@@ -381,11 +381,11 @@ def detect_with_yunet(vision_frame : VisionFrame, face_detector_size : str) -> T
 			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
+				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]:
@@ -81,7 +81,7 @@ def warp_face_by_face_landmark_5(temp_vision_frame : VisionFrame, face_landmark_


 def warp_face_by_bounding_box(temp_vision_frame : VisionFrame, bounding_box : BoundingBox, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
-	source_points = numpy.array([ [ bounding_box[0], bounding_box[1] ], [bounding_box[2], bounding_box[1] ], [ bounding_box[0], bounding_box[3] ] ]).astype(numpy.float32)
+	source_points = numpy.array([ [ bounding_box[0], bounding_box[1] ], [ bounding_box[2], bounding_box[1] ], [ bounding_box[0], bounding_box[3] ] ]).astype(numpy.float32)
 	target_points = numpy.array([ [ 0, 0 ], [ crop_size[0], 0 ], [ 0, crop_size[1] ] ]).astype(numpy.float32)
 	affine_matrix = cv2.getAffineTransform(source_points, target_points)
 	if bounding_box[2] - bounding_box[0] > crop_size[0] or bounding_box[3] - bounding_box[1] > crop_size[1]:
@@ -247,7 +247,7 @@ def get_nms_threshold(face_detector_model : FaceDetectorModel, face_detector_ang


 def merge_matrix(temp_matrices : List[Matrix]) -> Matrix:
-	matrix = numpy.vstack([temp_matrices[0], [0, 0, 1]])
+	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 ] ])
@@ -233,7 +233,7 @@ def create_area_mask(crop_vision_frame : VisionFrame, face_landmark_68 : FaceLan

 	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]
+	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

@@ -114,6 +114,7 @@ def extract_frames(target_path : str, temp_video_resolution : Resolution, temp_v
 		ffmpeg_builder.set_input(target_path),
 		ffmpeg_builder.set_media_resolution(pack_resolution(temp_video_resolution)),
 		ffmpeg_builder.set_frame_quality(0),
+		ffmpeg_builder.enforce_pixel_format('rgb24'),
 		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)
@@ -243,7 +244,8 @@ def merge_video(target_path : str, temp_video_fps : Fps, output_video_resolution


 def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
-	concat_video_path = tempfile.mktemp()
+	file_descriptor, concat_video_path = tempfile.mkstemp()
+	os.close(file_descriptor)

 	with open(concat_video_path, 'w') as concat_video_file:
 		for temp_output_path in temp_output_paths:
@@ -48,7 +48,7 @@ def set_input(input_path : str) -> List[Command]:


 def set_input_fps(input_fps : Fps) -> List[Command]:
-	return [ '-r', str(input_fps)]
+	return [ '-r', str(input_fps) ]


 def set_output(output_path : str) -> List[Command]:
@@ -79,6 +79,10 @@ def unsafe_concat() -> List[Command]:
 	return [ '-f', 'concat', '-safe', '0' ]


+def enforce_pixel_format(pixel_format : str) -> List[Command]:
+	return [ '-pix_fmt', pixel_format ]
+
+
 def set_pixel_format(video_encoder : VideoEncoder) -> List[Command]:
 	if video_encoder == 'rawvideo':
 		return [ '-pix_fmt', 'rgb24' ]
@@ -8,7 +8,7 @@ from onnxruntime import InferenceSession
 from facefusion import logger, process_manager, state_manager, translator
 from facefusion.app_context import detect_app_context
 from facefusion.common_helper import is_windows
-from facefusion.execution import create_inference_session_providers, has_execution_provider
+from facefusion.execution import create_inference_providers, has_execution_provider
 from facefusion.exit_helper import fatal_exit
 from facefusion.filesystem import get_file_name, is_file
 from facefusion.time_helper import calculate_end_time
@@ -72,8 +72,8 @@ def create_inference_session(model_path : str, execution_device_id : int, execut
 	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)
+		inference_providers = create_inference_providers(execution_device_id, execution_providers)
+		inference_session = InferenceSession(model_path, providers = inference_providers)
 		logger.debug(translator.get('loading_model_succeeded').format(model_name = model_file_name, seconds = calculate_end_time(start_time)), __name__)
 		return inference_session

@@ -10,7 +10,7 @@ from types import FrameType
 from facefusion import metadata
 from facefusion.common_helper import is_linux, is_windows

-LOCALS =\
+LOCALES =\
 {
 	'install_dependency': 'install the {dependency} package',
 	'force_reinstall': 'force reinstall of packages',
@@ -19,24 +19,25 @@ LOCALS =\
 }
 ONNXRUNTIME_SET =\
 {
-	'default': ('onnxruntime', '1.23.2')
+	'default': ('onnxruntime', '1.24.1')
 }
 if is_windows() or is_linux():
-	ONNXRUNTIME_SET['cuda'] = ('onnxruntime-gpu', '1.23.2')
-	ONNXRUNTIME_SET['openvino'] = ('onnxruntime-openvino', '1.23.0')
+	ONNXRUNTIME_SET['cuda'] = ('onnxruntime-gpu', '1.24.3')
+	ONNXRUNTIME_SET['openvino'] = ('onnxruntime-openvino', '1.24.1')
 if is_windows():
-	ONNXRUNTIME_SET['directml'] = ('onnxruntime-directml', '1.23.0')
+	ONNXRUNTIME_SET['directml'] = ('onnxruntime-directml', '1.24.3')
+	ONNXRUNTIME_SET['qnn'] = ('onnxruntime-qnn', '1.24.3')
 if is_linux():
-	ONNXRUNTIME_SET['migraphx'] = ('onnxruntime-migraphx', '1.23.0')
-	ONNXRUNTIME_SET['rocm'] = ('onnxruntime_rocm', '1.22.1', '7.0.2') #type:ignore[assignment]
+	ONNXRUNTIME_SET['migraphx'] = ('onnxruntime-migraphx', '1.24.2')
+	ONNXRUNTIME_SET['rocm'] = ('onnxruntime-rocm', '1.22.2.post1')


 def cli() -> None:
 	signal.signal(signal.SIGINT, signal_exit)
 	program = ArgumentParser(formatter_class = partial(HelpFormatter, max_help_position = 50))
-	program.add_argument('--onnxruntime', help = LOCALS.get('install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIME_SET.keys(), required = True)
-	program.add_argument('--force-reinstall', help = LOCALS.get('force_reinstall'), action = 'store_true')
-	program.add_argument('--skip-conda', help = LOCALS.get('skip_conda'), action = 'store_true')
+	program.add_argument('--onnxruntime', help = LOCALES.get('install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIME_SET.keys(), required = True)
+	program.add_argument('--force-reinstall', help = LOCALES.get('force_reinstall'), action = 'store_true')
+	program.add_argument('--skip-conda', help = LOCALES.get('skip_conda'), action = 'store_true')
 	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
 	run(program)

@@ -48,15 +49,16 @@ def signal_exit(signum : int, frame : FrameType) -> None:
 def run(program : ArgumentParser) -> None:
 	args = program.parse_args()
 	has_conda = 'CONDA_PREFIX' in os.environ
+
+	if not args.skip_conda and not has_conda:
+		sys.stdout.write(LOCALES.get('conda_not_activated') + os.linesep)
+		sys.exit(1)
+
 	commands = [ shutil.which('pip'), 'install' ]

 	if args.force_reinstall:
 		commands.append('--force-reinstall')

-	if not args.skip_conda and not has_conda:
-		sys.stdout.write(LOCALS.get('conda_not_activated') + os.linesep)
-		sys.exit(1)
-
 	with open('requirements.txt') as file:

 		for line in file.readlines():
@@ -64,46 +66,9 @@ def run(program : ArgumentParser) -> None:
 			if not __line__.startswith('onnxruntime'):
 				commands.append(__line__)

-	if args.onnxruntime == 'rocm':
-		onnxruntime_name, onnxruntime_version, rocm_version = ONNXRUNTIME_SET.get(args.onnxruntime) #type:ignore[misc]
-		python_id = 'cp' + str(sys.version_info.major) + str(sys.version_info.minor)
+	onnxruntime_name, onnxruntime_version = ONNXRUNTIME_SET.get(args.onnxruntime)
+	commands.append(onnxruntime_name + '==' + onnxruntime_version)

-		if python_id in [ 'cp310', 'cp312' ]:
-			wheel_name = onnxruntime_name + '-' + onnxruntime_version + '-' + python_id + '-' + python_id + '-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl'
-			wheel_url = 'https://repo.radeon.com/rocm/manylinux/rocm-rel-' + rocm_version + '/' + wheel_name
-			commands.append(wheel_url)
-	else:
-		onnxruntime_name, onnxruntime_version = ONNXRUNTIME_SET.get(args.onnxruntime)
-		commands.append(onnxruntime_name + '==' + onnxruntime_version)
+	subprocess.call([ shutil.which('pip'), 'uninstall', 'onnxruntime', onnxruntime_name, '-y', '-q' ])

 	subprocess.call(commands)
-
-	if args.onnxruntime == 'cuda' and has_conda:
-		library_paths = []
-
-		if is_linux():
-			if os.getenv('LD_LIBRARY_PATH'):
-				library_paths = os.getenv('LD_LIBRARY_PATH').split(os.pathsep)
-
-			python_id = 'python' + str(sys.version_info.major) + '.' + str(sys.version_info.minor)
-			library_paths.extend(
-			[
-				os.path.join(os.getenv('CONDA_PREFIX'), 'lib'),
-				os.path.join(os.getenv('CONDA_PREFIX'), 'lib', python_id, 'site-packages', 'tensorrt_libs')
-			])
-			library_paths = list(dict.fromkeys([ library_path for library_path in library_paths if os.path.exists(library_path) ]))
-
-			subprocess.call([ shutil.which('conda'), 'env', 'config', 'vars', 'set', 'LD_LIBRARY_PATH=' + os.pathsep.join(library_paths) ])
-
-		if is_windows():
-			if os.getenv('PATH'):
-				library_paths = os.getenv('PATH').split(os.pathsep)
-
-			library_paths.extend(
-			[
-				os.path.join(os.getenv('CONDA_PREFIX'), 'Lib'),
-				os.path.join(os.getenv('CONDA_PREFIX'), 'Lib', 'site-packages', 'tensorrt_libs')
-			])
-			library_paths = list(dict.fromkeys([ library_path for library_path in library_paths if os.path.exists(library_path) ]))
-
-			subprocess.call([ shutil.which('conda'), 'env', 'config', 'vars', 'set', 'PATH=' + os.pathsep.join(library_paths) ])
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -189,7 +189,7 @@ LOCALS : Locals =\
 		},
 		'about':
 		{
-			'fund': 'fund training server',
+			'fund': 'fund ai workstation',
 			'subscribe': 'become a member',
 			'join': 'join our community'
 		},
@@ -4,7 +4,7 @@ METADATA =\
 {
 	'name': 'FaceFusion',
 	'description': 'Industry leading face manipulation platform',
-	'version': '3.5.2',
+	'version': '3.6.0',
 	'license': 'OpenRAIL-AS',
 	'author': 'Henry Ruhs',
 	'url': 'https://facefusion.io'
@@ -19,9 +19,9 @@ def normalize_space(spaces : Optional[List[int]]) -> Optional[Padding]:
 	if spaces and len(spaces) == 1:
 		return tuple([spaces[0]] * 4) #type:ignore[return-value]
 	if spaces and len(spaces) == 2:
-		return tuple([spaces[0], spaces[1], spaces[0], spaces[1]]) #type:ignore[return-value]
+		return tuple([ spaces[0], spaces[1], spaces[0], spaces[1] ]) #type:ignore[return-value]
 	if spaces and len(spaces) == 3:
-		return tuple([spaces[0], spaces[1], spaces[2], spaces[1]]) #type:ignore[return-value]
+		return tuple([ spaces[0], spaces[1], spaces[2], spaces[1] ]) #type:ignore[return-value]
 	if spaces and len(spaces) == 4:
 		return tuple(spaces) #type:ignore[return-value]
 	return None
@@ -1,8 +1,8 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_int_range
 from facefusion.processors.modules.age_modifier.types import AgeModifierModel

-age_modifier_models : List[AgeModifierModel] = [ 'styleganex_age' ]
+age_modifier_models : List[AgeModifierModel] = list(get_args(AgeModifierModel))

 age_modifier_direction_range : Sequence[int] = create_int_range(-100, 100, 1)
@@ -29,6 +29,41 @@ from facefusion.vision import match_frame_color, read_static_image, read_static_
 def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 	return\
 	{
+		'fran':
+		{
+			'__metadata__':
+			{
+				'vendor': 'ry-lu',
+				'license': 'mit',
+				'year': 2024
+			},
+			'hashes':
+			{
+				'age_modifier':
+				{
+					'url': resolve_download_url('models-3.6.0', 'fran.hash'),
+					'path': resolve_relative_path('../.assets/models/fran.hash')
+				}
+			},
+			'sources':
+			{
+				'age_modifier':
+				{
+					'url': resolve_download_url('models-3.6.0', 'fran.onnx'),
+					'path': resolve_relative_path('../.assets/models/fran.onnx')
+				}
+			},
+			'templates':
+			{
+				'target': 'ffhq_512',
+			},
+			'sizes':
+			{
+				'target': (1024, 1024),
+			},
+			'mean': [ 0.0, 0.0, 0.0 ],
+			'standard_deviation': [ 1.0, 1.0, 1.0 ]
+		},
 		'styleganex_age':
 		{
 			'__metadata__':
@@ -62,7 +97,9 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			{
 				'target': (256, 256),
 				'target_with_background': (384, 384)
-			}
+			},
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		}
 	}

@@ -87,7 +124,7 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--age-modifier-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'age_modifier_model', 'styleganex_age'), choices = age_modifier_choices.age_modifier_models)
+		group_processors.add_argument('--age-modifier-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'age_modifier_model', 'fran'), choices = age_modifier_choices.age_modifier_models)
 		group_processors.add_argument('--age-modifier-direction', help = translator.get('help.direction', __package__), type = int, default = config.get_int_value('processors', 'age_modifier_direction', '0'), choices = age_modifier_choices.age_modifier_direction_range, metavar = create_int_metavar(age_modifier_choices.age_modifier_direction_range))
 		facefusion.jobs.job_store.register_step_keys([ 'age_modifier_model', 'age_modifier_direction' ])

@@ -137,32 +174,57 @@ def modify_age(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFra
 	model_sizes = get_model_options().get('sizes')
 	face_landmark_5 = target_face.landmark_set.get('5/68').copy()
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_templates.get('target'), model_sizes.get('target'))
-	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_box_mask(extend_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(crop_vision_frame)
-		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)
+	if state_manager.get_item('age_modifier_model') == 'fran':
+		box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+		crop_masks =\
+		[
+			box_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)
-	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)
-	extend_affine_matrix *= (model_sizes.get('target')[0] * 4) / model_sizes.get('target_with_background')[0]
-	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
-	crop_mask = cv2.resize(crop_mask, (model_sizes.get('target')[0] * 4, model_sizes.get('target')[1] * 4))
-	paste_vision_frame = paste_back(temp_vision_frame, extend_vision_frame, crop_mask, extend_affine_matrix)
-	return paste_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)
+
+		crop_vision_frame = prepare_vision_frame(crop_vision_frame)
+		target_age = numpy.mean(target_face.age)
+		age_modifier_direction = numpy.array([ target_age, target_age + state_manager.get_item('age_modifier_direction') ], dtype = numpy.float32) / 100
+		age_modifier_direction = age_modifier_direction.clip(0, 1)
+		crop_vision_frame = forward(crop_vision_frame, crop_vision_frame, age_modifier_direction)
+		crop_vision_frame = normalize_vision_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)
+		return paste_vision_frame
+
+	if state_manager.get_item('age_modifier_model') == 'styleganex_age':
+		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_box_mask(extend_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(crop_vision_frame)
+			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)
+		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)
+		extend_affine_matrix *= (model_sizes.get('target')[0] * 4) / model_sizes.get('target_with_background')[0]
+		crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
+		crop_mask = cv2.resize(crop_mask, (model_sizes.get('target')[0] * 4, model_sizes.get('target')[1] * 4))
+		paste_vision_frame = paste_back(temp_vision_frame, extend_vision_frame, crop_mask, extend_affine_matrix)
+		return paste_vision_frame
+
+	return temp_vision_frame


 def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame, age_modifier_direction : AgeModifierDirection) -> VisionFrame:
@@ -187,12 +249,24 @@ def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame,


 def prepare_vision_frame(vision_frame : VisionFrame) -> VisionFrame:
+	model_mean = get_model_options().get('mean')
+	model_standard_deviation = get_model_options().get('standard_deviation')
 	vision_frame = vision_frame[:, :, ::-1] / 255.0
-	vision_frame = (vision_frame - 0.5) / 0.5
+	vision_frame = (vision_frame - model_mean) / model_standard_deviation
 	vision_frame = numpy.expand_dims(vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
 	return vision_frame


+def normalize_vision_frame(vision_frame : VisionFrame) -> VisionFrame:
+	model_mean = get_model_options().get('mean')
+	model_standard_deviation = get_model_options().get('standard_deviation')
+	vision_frame = vision_frame.transpose(1, 2, 0)
+	vision_frame = vision_frame * model_standard_deviation + model_mean
+	vision_frame = vision_frame.clip(0, 1)
+	vision_frame = vision_frame[:, :, ::-1] * 255
+	return vision_frame
+
+
 def normalize_extend_frame(extend_vision_frame : VisionFrame) -> VisionFrame:
 	model_sizes = get_model_options().get('sizes')
 	extend_vision_frame = numpy.clip(extend_vision_frame, -1, 1)
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -12,6 +12,6 @@ AgeModifierInputs = TypedDict('AgeModifierInputs',
 	'temp_vision_mask' : Mask
 })

-AgeModifierModel = Literal['styleganex_age']
+AgeModifierModel = Literal['fran', 'styleganex_age']

 AgeModifierDirection : TypeAlias = NDArray[Any]
@@ -1,8 +1,8 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_int_range
 from facefusion.processors.modules.background_remover.types import BackgroundRemoverModel

-background_remover_models : List[BackgroundRemoverModel] = [ 'ben_2', 'birefnet_general', 'birefnet_portrait', 'isnet_general', 'modnet', 'ormbg', 'rmbg_1.4', 'rmbg_2.0', 'silueta', 'u2net_cloth', 'u2net_general', 'u2net_human', 'u2netp' ]
+background_remover_models : List[BackgroundRemoverModel] = list(get_args(BackgroundRemoverModel))

 background_remover_color_range : Sequence[int] = create_int_range(0, 255, 1)
@@ -8,7 +8,7 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 from facefusion import config, content_analyser, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import is_macos
+from facefusion.common_helper import is_macos, is_windows
 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
@@ -51,6 +51,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/ben_2.onnx')
 				}
 			},
+			'type': 'ben',
 			'size': (1024, 1024),
 			'mean': [ 0.0, 0.0, 0.0 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -79,6 +80,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/birefnet_general.onnx')
 				}
 			},
+			'type': 'birefnet',
 			'size': (1024, 1024),
 			'mean': [ 0.0, 0.0, 0.0 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -107,10 +109,69 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/birefnet_portrait.onnx')
 				}
 			},
+			'type': 'birefnet',
 			'size': (1024, 1024),
 			'mean': [ 0.0, 0.0, 0.0 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
 		},
+		'corridor_key_1024':
+		{
+			'__metadata__':
+			{
+				'vendor': 'nikopueringer',
+				'license': 'Non-Commercial',
+				'year': 2025
+			},
+			'hashes':
+			{
+				'background_remover':
+				{
+					'url': resolve_download_url('models-3.6.0', 'corridor_key_1024.hash'),
+					'path': resolve_relative_path('../.assets/models/corridor_key_1024.hash')
+				}
+			},
+			'sources':
+			{
+				'background_remover':
+				{
+					'url': resolve_download_url('models-3.6.0', 'corridor_key_1024.onnx'),
+					'path': resolve_relative_path('../.assets/models/corridor_key_1024.onnx')
+				}
+			},
+			'type': 'corridor_key',
+			'size': (1024, 1024),
+			'mean': [ 0.485, 0.456, 0.406 ],
+			'standard_deviation': [ 0.229, 0.224, 0.225 ]
+		},
+		'corridor_key_2048':
+		{
+			'__metadata__':
+			{
+				'vendor': 'nikopueringer',
+				'license': 'Non-Commercial',
+				'year': 2025
+			},
+			'hashes':
+			{
+				'background_remover':
+				{
+					'url': resolve_download_url('models-3.6.0', 'corridor_key_2048.hash'),
+					'path': resolve_relative_path('../.assets/models/corridor_key_2048.hash')
+				}
+			},
+			'sources':
+			{
+				'background_remover':
+				{
+					'url': resolve_download_url('models-3.6.0', 'corridor_key_2048.onnx'),
+					'path': resolve_relative_path('../.assets/models/corridor_key_2048.onnx')
+				}
+			},
+			'type': 'corridor_key',
+			'size': (2048, 2048),
+			'mean': [ 0.485, 0.456, 0.406 ],
+			'standard_deviation': [ 0.229, 0.224, 0.225 ]
+		},
 		'isnet_general':
 		{
 			'__metadata__':
@@ -135,6 +196,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/isnet_general.onnx')
 				}
 			},
+			'type': 'isnet',
 			'size': (1024, 1024),
 			'mean': [ 0.5, 0.5, 0.5 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -163,6 +225,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/modnet.onnx')
 				}
 			},
+			'type': 'modnet',
 			'size': (512, 512),
 			'mean': [ 0.5, 0.5, 0.5 ],
 			'standard_deviation': [ 0.5, 0.5, 0.5 ]
@@ -191,6 +254,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/ormbg.onnx')
 				}
 			},
+			'type': 'ormbg',
 			'size': (1024, 1024),
 			'mean': [ 0.0, 0.0, 0.0 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -219,6 +283,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/rmbg_1.4.onnx')
 				}
 			},
+			'type': 'rmbg',
 			'size': (1024, 1024),
 			'mean': [ 0.5, 0.5, 0.5 ],
 			'standard_deviation': [ 1.0, 1.0, 1.0 ]
@@ -247,6 +312,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/rmbg_2.0.onnx')
 				}
 			},
+			'type': 'rmbg',
 			'size': (1024, 1024),
 			'mean': [ 0.485, 0.456, 0.406 ],
 			'standard_deviation': [ 0.229, 0.224, 0.225 ]
@@ -275,6 +341,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/silueta.onnx')
 				}
 			},
+			'type': 'silueta',
 			'size': (320, 320),
 			'mean': [ 0.485, 0.456, 0.406 ],
 			'standard_deviation': [ 0.229, 0.224, 0.225 ]
@@ -303,6 +370,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/u2net_cloth.onnx')
 				}
 			},
+			'type': 'u2net_cloth',
 			'size': (768, 768),
 			'mean': [ 0.485, 0.456, 0.406 ],
 			'standard_deviation': [ 0.229, 0.224, 0.225 ]
@@ -331,6 +399,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/u2net_general.onnx')
 				}
 			},
+			'type': 'u2net',
 			'size': (320, 320),
 			'mean': [ 0.485, 0.456, 0.406 ],
 			'standard_deviation': [ 0.229, 0.224, 0.225 ]
@@ -359,6 +428,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/u2net_human.onnx')
 				}
 			},
+			'type': 'u2net',
 			'size': (320, 320),
 			'mean': [ 0.485, 0.456, 0.406 ],
 			'standard_deviation': [ 0.229, 0.224, 0.225 ]
@@ -387,6 +457,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/u2netp.onnx')
 				}
 			},
+			'type': 'u2netp',
 			'size': (320, 320),
 			'mean': [ 0.485, 0.456, 0.406 ],
 			'standard_deviation': [ 0.229, 0.224, 0.225 ]
@@ -407,7 +478,9 @@ def clear_inference_pool() -> None:


 def resolve_execution_providers() -> List[ExecutionProvider]:
-	if is_macos() and has_execution_provider('coreml'):
+	model_type = get_model_options().get('type')
+
+	if is_macos() and has_execution_provider('coreml') or is_windows() and has_execution_provider('directml') and model_type == 'corridor_key':
 		return [ 'cpu' ]
 	return state_manager.get_item('execution_providers')

@@ -420,14 +493,16 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--background-remover-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'background_remover_model', 'rmbg_2.0'), choices = background_remover_choices.background_remover_models)
-		group_processors.add_argument('--background-remover-color', help = translator.get('help.color', __package__), type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range), default = config.get_int_list('processors', 'background_remover_color', '0 0 0 0'), nargs = '+')
-		facefusion.jobs.job_store.register_step_keys([ 'background_remover_model', 'background_remover_color' ])
+		group_processors.add_argument('--background-remover-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'background_remover_model', 'modnet'), choices = background_remover_choices.background_remover_models)
+		group_processors.add_argument('--background-remover-fill-color', help = translator.get('help.fill_color', __package__), type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range), default = config.get_int_list('processors', 'background_remover_fill_color', '0 0 0 0'), nargs = '+')
+		group_processors.add_argument('--background-remover-despill-color', help = translator.get('help.despill_color', __package__), type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range), default = config.get_int_list('processors', 'background_remover_despill_color', '0 0 0 0'), nargs = '+')
+		facefusion.jobs.job_store.register_step_keys([ 'background_remover_model', 'background_remover_fill_color', 'background_remover_despill_color' ])


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('background_remover_model', args.get('background_remover_model'))
-	apply_state_item('background_remover_color', normalize_color(args.get('background_remover_color')))
+	apply_state_item('background_remover_fill_color', normalize_color(args.get('background_remover_fill_color')))
+	apply_state_item('background_remover_despill_color', normalize_color(args.get('background_remover_despill_color')))


 def pre_check() -> bool:
@@ -461,16 +536,26 @@ def post_process() -> None:


 def remove_background(temp_vision_frame : VisionFrame) -> Tuple[VisionFrame, Mask]:
-	temp_vision_mask = forward(prepare_temp_frame(temp_vision_frame))
-	temp_vision_mask = normalize_vision_mask(temp_vision_mask)
-	temp_vision_mask = cv2.resize(temp_vision_mask, temp_vision_frame.shape[:2][::-1])
-	temp_vision_frame = apply_background_color(temp_vision_frame, temp_vision_mask)
-	return temp_vision_frame, temp_vision_mask
+	model_type = get_model_options().get('type')
+
+	if model_type == 'corridor_key':
+		remove_vision_mask, remove_vision_frame = forward_corridor_key(prepare_temp_frame(temp_vision_frame))
+		remove_vision_frame = numpy.squeeze(remove_vision_frame).transpose(1, 2, 0)
+		remove_vision_frame = numpy.clip(remove_vision_frame * 255, 0, 255).astype(numpy.uint8)
+		temp_vision_frame = cv2.resize(remove_vision_frame[:, :, ::-1], temp_vision_frame.shape[:2][::-1])
+	else:
+		remove_vision_mask = forward(prepare_temp_frame(temp_vision_frame))
+
+	remove_vision_mask = normalize_vision_mask(remove_vision_mask)
+	remove_vision_mask = cv2.resize(remove_vision_mask, temp_vision_frame.shape[:2][::-1])
+	temp_vision_frame = apply_despill_color(temp_vision_frame)
+	temp_vision_frame = apply_fill_color(temp_vision_frame, remove_vision_mask)
+	return temp_vision_frame, remove_vision_mask


 def forward(temp_vision_frame : VisionFrame) -> VisionFrame:
 	background_remover = get_inference_pool().get('background_remover')
-	model_name = state_manager.get_item('background_remover_model')
+	model_type = get_model_options().get('type')

 	with thread_semaphore():
 		remove_vision_frame = background_remover.run(None,
@@ -478,20 +563,42 @@ def forward(temp_vision_frame : VisionFrame) -> VisionFrame:
 			'input': temp_vision_frame
 		})[0]

-		if model_name == 'u2net_cloth':
+		if model_type == 'u2net_cloth':
 			remove_vision_frame = numpy.argmax(remove_vision_frame, axis = 1)

 	return remove_vision_frame


+def forward_corridor_key(temp_vision_frame : VisionFrame) -> Tuple[Mask, VisionFrame]:
+	background_remover = get_inference_pool().get('background_remover')
+
+	with thread_semaphore():
+		remove_vision_mask, remove_vision_frame = background_remover.run(None,
+		{
+			'input': temp_vision_frame
+		})
+
+	return remove_vision_mask, remove_vision_frame
+
+
 def prepare_temp_frame(temp_vision_frame : VisionFrame) -> VisionFrame:
+	model_type = get_model_options().get('type')
 	model_size = get_model_options().get('size')
 	model_mean = get_model_options().get('mean')
 	model_standard_deviation = get_model_options().get('standard_deviation')

+	if model_type == 'corridor_key':
+		coarse_color = temp_vision_frame[:, :, ::-1].astype(numpy.float32) / 255.0
+		coarse_bias = coarse_color[:, :, 1] - numpy.maximum(coarse_color[:, :, 0], coarse_color[:, :, 2])
+		coarse_vision_mask = cv2.resize(1.0 - numpy.clip(coarse_bias * 2.0, 0, 1), model_size)[:, :, numpy.newaxis]
+
 	temp_vision_frame = cv2.resize(temp_vision_frame, model_size)
 	temp_vision_frame = temp_vision_frame[:, :, ::-1] / 255.0
 	temp_vision_frame = (temp_vision_frame - model_mean) / model_standard_deviation
+
+	if model_type == 'corridor_key':
+		temp_vision_frame = numpy.concatenate([ temp_vision_frame, coarse_vision_mask ], axis = 2)
+
 	temp_vision_frame = temp_vision_frame.transpose(2, 0, 1)
 	temp_vision_frame = numpy.expand_dims(temp_vision_frame, axis = 0).astype(numpy.float32)
 	return temp_vision_frame
@@ -503,16 +610,32 @@ def normalize_vision_mask(temp_vision_mask : Mask) -> Mask:
 	return temp_vision_mask


-def apply_background_color(temp_vision_frame : VisionFrame, temp_vision_mask : Mask) -> VisionFrame:
-	background_remover_color = state_manager.get_item('background_remover_color')
+def apply_fill_color(temp_vision_frame : VisionFrame, temp_vision_mask : Mask) -> VisionFrame:
+	background_remover_fill_color = state_manager.get_item('background_remover_fill_color')
 	temp_vision_mask = temp_vision_mask.astype(numpy.float32) / 255
 	temp_vision_mask = numpy.expand_dims(temp_vision_mask, axis = 2)
-	temp_vision_mask = (1 - temp_vision_mask) * background_remover_color[-1] / 255
-	color_frame = numpy.zeros_like(temp_vision_frame)
-	color_frame[:, :, 0] = background_remover_color[2]
-	color_frame[:, :, 1] = background_remover_color[1]
-	color_frame[:, :, 2] = background_remover_color[0]
-	temp_vision_frame = temp_vision_frame * (1 - temp_vision_mask) + color_frame * temp_vision_mask
+	temp_vision_mask = (1 - temp_vision_mask) * background_remover_fill_color[-1] / 255
+	fill_vision_frame = numpy.zeros_like(temp_vision_frame)
+	fill_vision_frame[:, :, 0] = background_remover_fill_color[2]
+	fill_vision_frame[:, :, 1] = background_remover_fill_color[1]
+	fill_vision_frame[:, :, 2] = background_remover_fill_color[0]
+	temp_vision_frame = temp_vision_frame * (1 - temp_vision_mask) + fill_vision_frame * temp_vision_mask
+	temp_vision_frame = temp_vision_frame.astype(numpy.uint8)
+	return temp_vision_frame
+
+
+def apply_despill_color(temp_vision_frame : VisionFrame) -> VisionFrame:
+	background_remover_despill_color = state_manager.get_item('background_remover_despill_color')
+	temp_vision_frame = temp_vision_frame.astype(numpy.float32)
+	color_alpha = background_remover_despill_color[3] / 255.0
+	despill_vision_frame = numpy.zeros_like(temp_vision_frame)
+	despill_vision_frame[:, :, 0] = background_remover_despill_color[2]
+	despill_vision_frame[:, :, 1] = background_remover_despill_color[1]
+	despill_vision_frame[:, :, 2] = background_remover_despill_color[0]
+	color_weight = despill_vision_frame / numpy.maximum(numpy.max(background_remover_despill_color[:3]), 1)
+	color_limit = numpy.roll(temp_vision_frame, 1, 2) + numpy.roll(temp_vision_frame, -1, 2)
+	limit_vision_frame = numpy.minimum(temp_vision_frame, color_limit * 0.5)
+	temp_vision_frame = temp_vision_frame + (limit_vision_frame - temp_vision_frame) * color_alpha * color_weight
 	temp_vision_frame = temp_vision_frame.astype(numpy.uint8)
 	return temp_vision_frame

@@ -0,0 +1,26 @@
+from facefusion.types import Locales
+
+LOCALES : Locales =\
+{
+	'en':
+	{
+		'help':
+		{
+			'model': 'choose the model responsible for removing the background',
+			'fill_color': 'apply red, green, blue and alpha values to the background',
+			'despill_color': 'remove red, green, blue and alpha values from the foreground'
+		},
+		'uis':
+		{
+			'model_dropdown': 'BACKGROUND REMOVER MODEL',
+			'fill_color_red_number': 'FILL COLOR RED',
+			'fill_color_green_number': 'FILL COLOR GREEN',
+			'fill_color_blue_number': 'FILL COLOR BLUE',
+			'fill_color_alpha_number': 'FILL COLOR ALPHA',
+			'despill_color_red_number': 'DESPILL COLOR RED',
+			'despill_color_green_number': 'DESPILL COLOR GREEN',
+			'despill_color_blue_number': 'DESPILL COLOR BLUE',
+			'despill_color_alpha_number': 'DESPILL COLOR ALPHA'
+		}
+	}
+}
@@ -1,21 +0,0 @@
-from facefusion.types import Locals
-
-LOCALS : Locals =\
-{
-	'en':
-	{
-		'help':
-		{
-			'model': 'choose the model responsible for removing the background',
-			'color': 'apply red, green blue and alpha values to the background'
-		},
-		'uis':
-		{
-			'model_dropdown': 'BACKGROUND REMOVER MODEL',
-			'color_red_number': 'BACKGROUND COLOR RED',
-			'color_green_number': 'BACKGROUND COLOR GREEN',
-			'color_blue_number': 'BACKGROUND COLOR BLUE',
-			'color_alpha_number': 'BACKGROUND COLOR ALPHA'
-		}
-	}
-}
@@ -9,4 +9,4 @@ BackgroundRemoverInputs = TypedDict('BackgroundRemoverInputs',
 	'temp_vision_mask' : Mask
 })

-BackgroundRemoverModel = Literal['ben_2', 'birefnet_general', 'birefnet_portrait', 'isnet_general', 'modnet', 'ormbg', 'rmbg_1.4', 'rmbg_2.0', 'silueta', 'u2net_cloth', 'u2net_general', 'u2net_human', 'u2netp']
+BackgroundRemoverModel = Literal['ben_2', 'birefnet_general', 'birefnet_portrait', 'corridor_key_1024', 'corridor_key_2048', 'isnet_general', 'modnet', 'ormbg', 'rmbg_1.4', 'rmbg_2.0', 'silueta', 'u2net_cloth', 'u2net_general', 'u2net_human', 'u2netp']
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,10 +1,10 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_int_range
 from facefusion.processors.modules.expression_restorer.types import ExpressionRestorerArea, ExpressionRestorerModel

-expression_restorer_models : List[ExpressionRestorerModel] = [ 'live_portrait' ]
+expression_restorer_models : List[ExpressionRestorerModel] = list(get_args(ExpressionRestorerModel))

-expression_restorer_areas : List[ExpressionRestorerArea] = [ 'upper-face', 'lower-face' ]
+expression_restorer_areas : List[ExpressionRestorerArea] = list(get_args(ExpressionRestorerArea))

 expression_restorer_factor_range : Sequence[int] = create_int_range(0, 100, 1)
@@ -192,12 +192,12 @@ def restrict_expression_areas(temp_expression : LivePortraitExpression, target_e
 	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]]
+		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[:, [ 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]]
+	target_expression[:, [ 0, 4, 5, 8, 9 ]] = temp_expression[:, [ 0, 4, 5, 8, 9 ]]
 	return target_expression


@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,5 +1,5 @@
-from typing import List
+from typing import List, get_args

 from facefusion.processors.modules.face_debugger.types import FaceDebuggerItem

-face_debugger_items : List[FaceDebuggerItem] = [ 'bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask' ]
+face_debugger_items : List[FaceDebuggerItem] = list(get_args(FaceDebuggerItem))
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,9 +1,9 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_float_range
 from facefusion.processors.modules.face_editor.types import FaceEditorModel

-face_editor_models : List[FaceEditorModel] = [ 'live_portrait' ]
+face_editor_models : List[FaceEditorModel] = list(get_args(FaceEditorModel))

 face_editor_eyebrow_direction_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
 face_editor_eye_gaze_horizontal_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,9 +1,9 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_float_range, create_int_range
 from facefusion.processors.modules.face_enhancer.types import FaceEnhancerModel

-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_enhancer_models : List[FaceEnhancerModel] = list(get_args(FaceEnhancerModel))

 face_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)

@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,8 +1,9 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_float_range
 from facefusion.processors.modules.face_swapper.types import FaceSwapperModel, FaceSwapperSet, FaceSwapperWeight

+
 face_swapper_set : FaceSwapperSet =\
 {
 	'blendswap_256': [ '256x256', '384x384', '512x512', '768x768', '1024x1024' ],
@@ -20,6 +21,6 @@ face_swapper_set : FaceSwapperSet =\
 	'uniface_256': [ '256x256', '512x512', '768x768', '1024x1024' ]
 }

-face_swapper_models : List[FaceSwapperModel] = list(face_swapper_set.keys())
+face_swapper_models : List[FaceSwapperModel] = list(get_args(FaceSwapperModel))

 face_swapper_weight_range : Sequence[FaceSwapperWeight] = create_float_range(0.0, 1.0, 0.05)
@@ -540,8 +540,8 @@ def pre_process(mode : ProcessMode) -> bool:
 		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)
+	source_vision_frames = read_static_images(source_image_paths)
+	source_faces = get_many_faces(source_vision_frames)

 	if not get_one_face(source_faces):
 		logger.error(translator.get('no_source_face_detected') + translator.get('exclamation_mark'), __name__)
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,9 +1,9 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_int_range
 from facefusion.processors.modules.frame_colorizer.types import FrameColorizerModel

-frame_colorizer_models : List[FrameColorizerModel] = [ 'ddcolor', 'ddcolor_artistic', 'deoldify', 'deoldify_artistic', 'deoldify_stable' ]
+frame_colorizer_models : List[FrameColorizerModel] = list(get_args(FrameColorizerModel))

 frame_colorizer_sizes : List[str] = [ '192x192', '256x256', '384x384', '512x512' ]

@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,8 +1,8 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_int_range
 from facefusion.processors.modules.frame_enhancer.types import FrameEnhancerModel

-frame_enhancer_models : List[FrameEnhancerModel] = [ 'clear_reality_x4', 'face_dat_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', 'tghq_face_x8', 'ultra_sharp_x4', 'ultra_sharp_2_x4' ]
+frame_enhancer_models : List[FrameEnhancerModel] = list(get_args(FrameEnhancerModel))

 frame_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
@@ -56,7 +56,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			'__metadata__':
 			{
 				'vendor': 'Helaman',
-				'license': 'Non-Commercial',
+				'license': 'CC-BY-4.0',
 				'year': 2023
 			},
 			'hashes':
@@ -83,7 +83,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			'__metadata__':
 			{
 				'vendor': 'Phhofm',
-				'license': 'Non-Commercial',
+				'license': 'CC-BY-4.0',
 				'year': 2023
 			},
 			'hashes':
@@ -299,7 +299,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 			'__metadata__':
 			{
 				'vendor': 'Helaman',
-				'license': 'Non-Commercial',
+				'license': 'CC-BY-4.0',
 				'year': 2024
 			},
 			'hashes':
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -1,8 +1,8 @@
-from typing import List, Sequence
+from typing import List, Sequence, get_args

 from facefusion.common_helper import create_float_range
 from facefusion.processors.modules.lip_syncer.types import LipSyncerModel

-lip_syncer_models : List[LipSyncerModel] = [ 'edtalk_256', 'wav2lip_96', 'wav2lip_gan_96' ]
+lip_syncer_models : List[LipSyncerModel] = list(get_args(LipSyncerModel))

 lip_syncer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
@@ -1,6 +1,6 @@
-from facefusion.types import Locals
+from facefusion.types import Locales

-LOCALS : Locals =\
+LOCALES : Locales =\
 {
 	'en':
 	{
@@ -10,7 +10,7 @@ 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
-from facefusion.sanitizer import sanitize_int_range
+from facefusion.sanitizer import sanitize_int_range, sanitize_job_id


 def create_help_formatter_small(prog : str) -> HelpFormatter:
@@ -188,7 +188,7 @@ def create_processors_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	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 = translator.get('help.processors').format(choices = ', '.join(available_processors)), default = config.get_str_list('processors', 'processors', 'face_swapper'), nargs = '+')
+	group_processors.add_argument('--processors', help = translator.get('help.processors').format(choices = ', '.join(available_processors)), default = config.get_str_list('processors', 'processors', 'face_swapper'), choices = available_processors, nargs = '+', metavar = 'PROCESSORS')
 	job_store.register_step_keys([ 'processors' ])
 	for processor_module in get_processors_modules(available_processors):
 		processor_module.register_args(program)
@@ -200,7 +200,7 @@ def create_uis_program() -> ArgumentParser:
 	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 = translator.get('help.open_browser'), action = 'store_true', default = config.get_bool_value('uis', 'open_browser'))
-	group_uis.add_argument('--ui-layouts', help = translator.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-layouts', help = translator.get('help.ui_layouts').format(choices = ', '.join(available_ui_layouts)), default = config.get_str_list('uis', 'ui_layouts', 'default'), choices = available_ui_layouts, nargs = '+', metavar = 'UI_LAYOUTS')
 	group_uis.add_argument('--ui-workflow', help = translator.get('help.ui_workflow'), default = config.get_str_value('uis', 'ui_workflow', 'instant_runner'), choices = facefusion.choices.ui_workflows)
 	return program

@@ -268,7 +268,7 @@ def create_halt_on_error_program() -> ArgumentParser:

 def create_job_id_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	program.add_argument('job_id', help = translator.get('help.job_id'))
+	program.add_argument('job_id', help = translator.get('help.job_id'), type = sanitize_job_id)
 	return program


@@ -297,13 +297,11 @@ def create_program() -> ArgumentParser:
 	program._positionals.title = 'commands'
 	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 = translator.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 = translator.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 = translator.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 = translator.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 = translator.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 = translator.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 = translator.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 = translator.get('help.job_submit'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
@@ -314,7 +312,6 @@ def create_program() -> ArgumentParser:
 	sub_program.add_parser('job-remix-step', help = translator.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 = translator.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 = translator.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 = translator.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 = translator.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 = translator.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)
@@ -1,6 +1,15 @@
+import hashlib
 from typing import Sequence


+def sanitize_job_id(job_id : str) -> str:
+	__job_id__ = job_id.replace('-', '')
+
+	if __job_id__.isalnum():
+		return job_id
+	return hashlib.sha1(job_id.encode()).hexdigest()
+
+
 def sanitize_int_range(value : int, int_range : Sequence[int]) -> int:
 	if value in int_range:
 		return value
@@ -26,17 +26,17 @@ def multi_process_capture(camera_capture : cv2.VideoCapture, camera_fps : Fps) -
 			futures = []

 			while camera_capture and camera_capture.isOpened():
-				_, capture_frame = camera_capture.read()
-				if analyse_stream(capture_frame, camera_fps):
+				_, capture_vision_frame = camera_capture.read()
+				if analyse_stream(capture_vision_frame, camera_fps):
 					camera_capture.release()

-				if numpy.any(capture_frame):
-					future = executor.submit(process_stream_frame, capture_frame)
+				if numpy.any(capture_vision_frame):
+					future = executor.submit(process_stream_frame, capture_vision_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)
+					capture_vision_frame = future_done.result()
+					capture_deque.append(capture_vision_frame)
 					futures.remove(future_done)

 				while capture_deque:
@@ -1,29 +1,29 @@
 import importlib
 from typing import Optional

-from facefusion.types import Language, LocalPoolSet, Locals
+from facefusion.types import Language, LocalePoolSet, Locales

-LOCAL_POOL_SET : LocalPoolSet = {}
+LOCALE_POOL_SET : LocalePoolSet = {}
 CURRENT_LANGUAGE : Language = 'en'


 def __autoload__(module_name : str) -> None:
 	try:
-		__locals__ = importlib.import_module(module_name + '.locals')
-		load(__locals__.LOCALS, module_name)
+		__locales__ = importlib.import_module(module_name + '.locales')
+		load(__locales__.LOCALES, module_name)
 	except ImportError:
 		pass


-def load(__locals__ : Locals, module_name : str) -> None:
-	LOCAL_POOL_SET[module_name] = __locals__
+def load(__locales__ : Locales, module_name : str) -> None:
+	LOCALE_POOL_SET[module_name] = __locales__


 def get(notation : str, module_name : str = 'facefusion') -> Optional[str]:
-	if module_name not in LOCAL_POOL_SET:
+	if module_name not in LOCALE_POOL_SET:
 		__autoload__(module_name)

-	current = LOCAL_POOL_SET.get(module_name).get(CURRENT_LANGUAGE)
+	current = LOCALE_POOL_SET.get(module_name).get(CURRENT_LANGUAGE)

 	for fragment in notation.split('.'):
 		if fragment in current:
@@ -51,8 +51,8 @@ FaceStore = TypedDict('FaceStore',
 })

 Language = Literal['en']
-Locals : TypeAlias = Dict[Language, Dict[str, Any]]
-LocalPoolSet : TypeAlias = Dict[str, Locals]
+Locales : TypeAlias = Dict[Language, Dict[str, Any]]
+LocalePoolSet : TypeAlias = Dict[str, Locales]

 VideoCaptureSet : TypeAlias = Dict[str, cv2.VideoCapture]
 VideoWriterSet : TypeAlias = Dict[str, cv2.VideoWriter]
@@ -167,10 +167,11 @@ 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']
+ExecutionProvider = Literal['cuda', 'tensorrt', 'rocm', 'migraphx', 'coreml', 'openvino', 'qnn', 'directml', 'cpu']
+ExecutionProviderValue = Literal['CPUExecutionProvider', 'CoreMLExecutionProvider', 'CUDAExecutionProvider', 'DmlExecutionProvider', 'OpenVINOExecutionProvider', 'MIGraphXExecutionProvider', 'QNNExecutionProvider', 'ROCMExecutionProvider', 'TensorrtExecutionProvider']
 ExecutionProviderSet : TypeAlias = Dict[ExecutionProvider, ExecutionProviderValue]
-InferenceSessionProvider : TypeAlias = Any
+InferenceProvider : TypeAlias = Any
+InferenceOptionSet : TypeAlias = Dict[str, Any]
 ValueAndUnit = TypedDict('ValueAndUnit',
 {
 	'value' : int,
@@ -14,7 +14,7 @@ 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' ]

-background_remover_colors : Dict[str, Color] =\
+background_remover_fill_colors : Dict[str, Color] =\
 {
 	'red' : (255, 0, 0, 255),
 	'green' : (0, 255, 0, 255),
@@ -11,82 +11,132 @@ from facefusion.sanitizer import sanitize_int_range
 from facefusion.uis.core import get_ui_component, register_ui_component

 BACKGROUND_REMOVER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
-BACKGROUND_REMOVER_COLOR_WRAPPER : Optional[gradio.Group] = None
-BACKGROUND_REMOVER_COLOR_RED_NUMBER : Optional[gradio.Number] = None
-BACKGROUND_REMOVER_COLOR_GREEN_NUMBER : Optional[gradio.Number] = None
-BACKGROUND_REMOVER_COLOR_BLUE_NUMBER : Optional[gradio.Number] = None
-BACKGROUND_REMOVER_COLOR_ALPHA_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_FILL_COLOR_WRAPPER : Optional[gradio.Group] = None
+BACKGROUND_REMOVER_FILL_COLOR_RED_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_FILL_COLOR_GREEN_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_FILL_COLOR_BLUE_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_FILL_COLOR_ALPHA_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_DESPILL_COLOR_WRAPPER : Optional[gradio.Group] = None
+BACKGROUND_REMOVER_DESPILL_COLOR_RED_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_DESPILL_COLOR_GREEN_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_DESPILL_COLOR_BLUE_NUMBER : Optional[gradio.Number] = None
+BACKGROUND_REMOVER_DESPILL_COLOR_ALPHA_NUMBER : Optional[gradio.Number] = None


 def render() -> None:
 	global BACKGROUND_REMOVER_MODEL_DROPDOWN
-	global BACKGROUND_REMOVER_COLOR_WRAPPER
-	global BACKGROUND_REMOVER_COLOR_RED_NUMBER
-	global BACKGROUND_REMOVER_COLOR_GREEN_NUMBER
-	global BACKGROUND_REMOVER_COLOR_BLUE_NUMBER
-	global BACKGROUND_REMOVER_COLOR_ALPHA_NUMBER
+	global BACKGROUND_REMOVER_FILL_COLOR_WRAPPER
+	global BACKGROUND_REMOVER_FILL_COLOR_RED_NUMBER
+	global BACKGROUND_REMOVER_FILL_COLOR_GREEN_NUMBER
+	global BACKGROUND_REMOVER_FILL_COLOR_BLUE_NUMBER
+	global BACKGROUND_REMOVER_FILL_COLOR_ALPHA_NUMBER
+	global BACKGROUND_REMOVER_DESPILL_COLOR_WRAPPER
+	global BACKGROUND_REMOVER_DESPILL_COLOR_RED_NUMBER
+	global BACKGROUND_REMOVER_DESPILL_COLOR_GREEN_NUMBER
+	global BACKGROUND_REMOVER_DESPILL_COLOR_BLUE_NUMBER
+	global BACKGROUND_REMOVER_DESPILL_COLOR_ALPHA_NUMBER

 	has_background_remover = 'background_remover' in state_manager.get_item('processors')
-	background_remover_color = state_manager.get_item('background_remover_color')
+	background_remover_fill_color = state_manager.get_item('background_remover_fill_color')
+	background_remover_despill_color = state_manager.get_item('background_remover_despill_color')
 	BACKGROUND_REMOVER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = translator.get('uis.model_dropdown', 'facefusion.processors.modules.background_remover'),
 		choices = background_remover_choices.background_remover_models,
 		value = state_manager.get_item('background_remover_model'),
 		visible = has_background_remover
 	)
-	with gradio.Group(visible = has_background_remover) as BACKGROUND_REMOVER_COLOR_WRAPPER:
+	with gradio.Group(visible = has_background_remover) as BACKGROUND_REMOVER_FILL_COLOR_WRAPPER:
 		with gradio.Row():
-			BACKGROUND_REMOVER_COLOR_RED_NUMBER = gradio.Number(
-				label = translator.get('uis.color_red_number', 'facefusion.processors.modules.background_remover'),
-				value = background_remover_color[0],
+			BACKGROUND_REMOVER_FILL_COLOR_RED_NUMBER = gradio.Number(
+				label = translator.get('uis.fill_color_red_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_fill_color[0],
 				minimum = background_remover_choices.background_remover_color_range[0],
 				maximum = background_remover_choices.background_remover_color_range[-1],
 				step = calculate_int_step(background_remover_choices.background_remover_color_range)
 			)
-			BACKGROUND_REMOVER_COLOR_GREEN_NUMBER = gradio.Number(
-				label = translator.get('uis.color_green_number', 'facefusion.processors.modules.background_remover'),
-				value = background_remover_color[1],
+			BACKGROUND_REMOVER_FILL_COLOR_GREEN_NUMBER = gradio.Number(
+				label = translator.get('uis.fill_color_green_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_fill_color[1],
 				minimum = background_remover_choices.background_remover_color_range[0],
 				maximum = background_remover_choices.background_remover_color_range[-1],
 				step = calculate_int_step(background_remover_choices.background_remover_color_range)
 			)
 		with gradio.Row():
-			BACKGROUND_REMOVER_COLOR_BLUE_NUMBER = gradio.Number(
-				label = translator.get('uis.color_blue_number', 'facefusion.processors.modules.background_remover'),
-				value = background_remover_color[2],
+			BACKGROUND_REMOVER_FILL_COLOR_BLUE_NUMBER = gradio.Number(
+				label = translator.get('uis.fill_color_blue_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_fill_color[2],
 				minimum = background_remover_choices.background_remover_color_range[0],
 				maximum = background_remover_choices.background_remover_color_range[-1],
 				step = calculate_int_step(background_remover_choices.background_remover_color_range)
 			)
-			BACKGROUND_REMOVER_COLOR_ALPHA_NUMBER = gradio.Number(
-				label = translator.get('uis.color_alpha_number', 'facefusion.processors.modules.background_remover'),
-				value = background_remover_color[3],
+			BACKGROUND_REMOVER_FILL_COLOR_ALPHA_NUMBER = gradio.Number(
+				label = translator.get('uis.fill_color_alpha_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_fill_color[3],
+				minimum = background_remover_choices.background_remover_color_range[0],
+				maximum = background_remover_choices.background_remover_color_range[-1],
+				step = calculate_int_step(background_remover_choices.background_remover_color_range)
+			)
+	with gradio.Group(visible = has_background_remover) as BACKGROUND_REMOVER_DESPILL_COLOR_WRAPPER:
+		with gradio.Row():
+			BACKGROUND_REMOVER_DESPILL_COLOR_RED_NUMBER = gradio.Number(
+				label = translator.get('uis.despill_color_red_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_despill_color[0],
+				minimum = background_remover_choices.background_remover_color_range[0],
+				maximum = background_remover_choices.background_remover_color_range[-1],
+				step = calculate_int_step(background_remover_choices.background_remover_color_range)
+			)
+			BACKGROUND_REMOVER_DESPILL_COLOR_GREEN_NUMBER = gradio.Number(
+				label = translator.get('uis.despill_color_green_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_despill_color[1],
+				minimum = background_remover_choices.background_remover_color_range[0],
+				maximum = background_remover_choices.background_remover_color_range[-1],
+				step = calculate_int_step(background_remover_choices.background_remover_color_range)
+			)
+		with gradio.Row():
+			BACKGROUND_REMOVER_DESPILL_COLOR_BLUE_NUMBER = gradio.Number(
+				label = translator.get('uis.despill_color_blue_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_despill_color[2],
+				minimum = background_remover_choices.background_remover_color_range[0],
+				maximum = background_remover_choices.background_remover_color_range[-1],
+				step = calculate_int_step(background_remover_choices.background_remover_color_range)
+			)
+			BACKGROUND_REMOVER_DESPILL_COLOR_ALPHA_NUMBER = gradio.Number(
+				label = translator.get('uis.despill_color_alpha_number', 'facefusion.processors.modules.background_remover'),
+				value = background_remover_despill_color[3],
 				minimum = background_remover_choices.background_remover_color_range[0],
 				maximum = background_remover_choices.background_remover_color_range[-1],
 				step = calculate_int_step(background_remover_choices.background_remover_color_range)
 			)
 	register_ui_component('background_remover_model_dropdown', BACKGROUND_REMOVER_MODEL_DROPDOWN)
-	register_ui_component('background_remover_color_red_number', BACKGROUND_REMOVER_COLOR_RED_NUMBER)
-	register_ui_component('background_remover_color_green_number', BACKGROUND_REMOVER_COLOR_GREEN_NUMBER)
-	register_ui_component('background_remover_color_blue_number', BACKGROUND_REMOVER_COLOR_BLUE_NUMBER)
-	register_ui_component('background_remover_color_alpha_number', BACKGROUND_REMOVER_COLOR_ALPHA_NUMBER)
+	register_ui_component('background_remover_fill_color_red_number', BACKGROUND_REMOVER_FILL_COLOR_RED_NUMBER)
+	register_ui_component('background_remover_fill_color_green_number', BACKGROUND_REMOVER_FILL_COLOR_GREEN_NUMBER)
+	register_ui_component('background_remover_fill_color_blue_number', BACKGROUND_REMOVER_FILL_COLOR_BLUE_NUMBER)
+	register_ui_component('background_remover_fill_color_alpha_number', BACKGROUND_REMOVER_FILL_COLOR_ALPHA_NUMBER)
+	register_ui_component('background_remover_despill_color_red_number', BACKGROUND_REMOVER_DESPILL_COLOR_RED_NUMBER)
+	register_ui_component('background_remover_despill_color_green_number', BACKGROUND_REMOVER_DESPILL_COLOR_GREEN_NUMBER)
+	register_ui_component('background_remover_despill_color_blue_number', BACKGROUND_REMOVER_DESPILL_COLOR_BLUE_NUMBER)
+	register_ui_component('background_remover_despill_color_alpha_number', BACKGROUND_REMOVER_DESPILL_COLOR_ALPHA_NUMBER)


 def listen() -> None:
 	BACKGROUND_REMOVER_MODEL_DROPDOWN.change(update_background_remover_model, inputs = BACKGROUND_REMOVER_MODEL_DROPDOWN, outputs = BACKGROUND_REMOVER_MODEL_DROPDOWN)
-	background_remover_color_inputs = [ BACKGROUND_REMOVER_COLOR_RED_NUMBER, BACKGROUND_REMOVER_COLOR_GREEN_NUMBER, BACKGROUND_REMOVER_COLOR_BLUE_NUMBER, BACKGROUND_REMOVER_COLOR_ALPHA_NUMBER ]
+	background_remover_fill_color_inputs = [ BACKGROUND_REMOVER_FILL_COLOR_RED_NUMBER, BACKGROUND_REMOVER_FILL_COLOR_GREEN_NUMBER, BACKGROUND_REMOVER_FILL_COLOR_BLUE_NUMBER, BACKGROUND_REMOVER_FILL_COLOR_ALPHA_NUMBER ]
+	background_remover_despill_color_inputs = [ BACKGROUND_REMOVER_DESPILL_COLOR_RED_NUMBER, BACKGROUND_REMOVER_DESPILL_COLOR_GREEN_NUMBER, BACKGROUND_REMOVER_DESPILL_COLOR_BLUE_NUMBER, BACKGROUND_REMOVER_DESPILL_COLOR_ALPHA_NUMBER ]

-	for background_remover_color_input in background_remover_color_inputs:
-		background_remover_color_input.change(update_background_remover_color, inputs = background_remover_color_inputs)
+	for background_remover_fill_color_input in background_remover_fill_color_inputs:
+		background_remover_fill_color_input.change(update_background_remover_fill_color, inputs = background_remover_fill_color_inputs)
+
+	for background_remover_despill_color_input in background_remover_despill_color_inputs:
+		background_remover_despill_color_input.change(update_background_remover_despill_color, inputs = background_remover_despill_color_inputs)

 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [BACKGROUND_REMOVER_MODEL_DROPDOWN, BACKGROUND_REMOVER_COLOR_WRAPPER])
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ BACKGROUND_REMOVER_MODEL_DROPDOWN, BACKGROUND_REMOVER_FILL_COLOR_WRAPPER, BACKGROUND_REMOVER_DESPILL_COLOR_WRAPPER ])


-def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Group]:
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Group, gradio.Group]:
 	has_background_remover = 'background_remover' in processors
-	return gradio.Dropdown(visible = has_background_remover), gradio.Group(visible = has_background_remover)
+	return gradio.Dropdown(visible = has_background_remover), gradio.Group(visible = has_background_remover), gradio.Group(visible = has_background_remover)


 def update_background_remover_model(background_remover_model : BackgroundRemoverModel) -> gradio.Dropdown:
@@ -99,9 +149,17 @@ def update_background_remover_model(background_remover_model : BackgroundRemover
 	return gradio.Dropdown()


-def update_background_remover_color(red : int, green : int, blue : int, alpha : int) -> None:
+def update_background_remover_fill_color(red : int, green : int, blue : int, alpha : int) -> None:
 	red = sanitize_int_range(red, background_remover_choices.background_remover_color_range)
 	green = sanitize_int_range(green, background_remover_choices.background_remover_color_range)
 	blue = sanitize_int_range(blue, background_remover_choices.background_remover_color_range)
 	alpha = sanitize_int_range(alpha, background_remover_choices.background_remover_color_range)
-	state_manager.set_item('background_remover_color', (red, green, blue, alpha))
+	state_manager.set_item('background_remover_fill_color', (red, green, blue, alpha))
+
+
+def update_background_remover_despill_color(red : int, green : int, blue : int, alpha : int) -> None:
+	red = sanitize_int_range(red, background_remover_choices.background_remover_color_range)
+	green = sanitize_int_range(green, background_remover_choices.background_remover_color_range)
+	blue = sanitize_int_range(blue, background_remover_choices.background_remover_color_range)
+	alpha = sanitize_int_range(alpha, background_remover_choices.background_remover_color_range)
+	state_manager.set_item('background_remover_despill_color', (red, green, blue, alpha))
@@ -132,7 +132,7 @@ def listen() -> None:
 		'target_video'
 	]):
 		for method in [ 'change', 'clear' ]:
-			getattr(ui_component, method)(remote_update, outputs = [OUTPUT_IMAGE_QUALITY_SLIDER, OUTPUT_IMAGE_SCALE_SLIDER, OUTPUT_AUDIO_ENCODER_DROPDOWN, OUTPUT_AUDIO_QUALITY_SLIDER, OUTPUT_AUDIO_VOLUME_SLIDER, OUTPUT_VIDEO_ENCODER_DROPDOWN, OUTPUT_VIDEO_PRESET_DROPDOWN, OUTPUT_VIDEO_QUALITY_SLIDER, OUTPUT_VIDEO_SCALE_SLIDER, OUTPUT_VIDEO_FPS_SLIDER])
+			getattr(ui_component, method)(remote_update, outputs = [ OUTPUT_IMAGE_QUALITY_SLIDER, OUTPUT_IMAGE_SCALE_SLIDER, OUTPUT_AUDIO_ENCODER_DROPDOWN, OUTPUT_AUDIO_QUALITY_SLIDER, OUTPUT_AUDIO_VOLUME_SLIDER, OUTPUT_VIDEO_ENCODER_DROPDOWN, OUTPUT_VIDEO_PRESET_DROPDOWN, OUTPUT_VIDEO_QUALITY_SLIDER, OUTPUT_VIDEO_SCALE_SLIDER, OUTPUT_VIDEO_FPS_SLIDER ])


 def remote_update() -> Tuple[gradio.Slider, gradio.Slider, gradio.Dropdown, gradio.Slider, gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Slider, gradio.Slider]:
@@ -90,10 +90,14 @@ def listen() -> None:

 	for ui_component in get_ui_components(
 	[
-		'background_remover_color_red_number',
-		'background_remover_color_green_number',
-		'background_remover_color_blue_number',
-		'background_remover_color_alpha_number',
+		'background_remover_fill_color_red_number',
+		'background_remover_fill_color_green_number',
+		'background_remover_fill_color_blue_number',
+		'background_remover_fill_color_alpha_number',
+		'background_remover_despill_color_red_number',
+		'background_remover_despill_color_green_number',
+		'background_remover_despill_color_blue_number',
+		'background_remover_despill_color_alpha_number',
 		'face_debugger_items_checkbox_group',
 		'frame_colorizer_size_dropdown',
 		'face_mask_types_checkbox_group',
@@ -296,7 +300,7 @@ def extract_crop_frame(vision_frame : VisionFrame, face : Face) -> Optional[Visi


 def prepare_output_frame(target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame, temp_vision_mask : Mask) -> VisionFrame:
-	temp_vision_mask = temp_vision_mask.clip(state_manager.get_item('background_remover_color')[-1], 255)
+	temp_vision_mask = temp_vision_mask.clip(state_manager.get_item('background_remover_fill_color')[-1], 255)
 	temp_vision_frame = merge_vision_mask(temp_vision_frame, temp_vision_mask)
 	temp_vision_frame = cv2.resize(temp_vision_frame, target_vision_frame.shape[1::-1])
 	return temp_vision_frame
@@ -10,7 +10,7 @@ from facefusion.streamer import multi_process_capture, open_stream
 from facefusion.types import Fps, VisionFrame, WebcamMode
 from facefusion.uis.core import get_ui_component
 from facefusion.uis.types import File
-from facefusion.vision import unpack_resolution
+from facefusion.vision import fit_cover_frame, unpack_resolution

 SOURCE_FILE : Optional[gradio.File] = None
 WEBCAM_IMAGE : Optional[gradio.Image] = None
@@ -90,7 +90,7 @@ def start(webcam_device_id : int, webcam_mode : WebcamMode, webcam_resolution :
 	stream = None

 	if webcam_mode in [ 'udp', 'v4l2' ]:
-		stream = open_stream(webcam_mode, webcam_resolution, webcam_fps) # type:ignore[arg-type]
+		stream = open_stream(webcam_mode, webcam_resolution, webcam_fps) #type:ignore[arg-type]
 	webcam_width, webcam_height = unpack_resolution(webcam_resolution)

 	if camera_capture and camera_capture.isOpened():
@@ -98,14 +98,15 @@ def start(webcam_device_id : int, webcam_mode : WebcamMode, webcam_resolution :
 		camera_capture.set(cv2.CAP_PROP_FRAME_HEIGHT, webcam_height)
 		camera_capture.set(cv2.CAP_PROP_FPS, webcam_fps)

-		for capture_frame in multi_process_capture(camera_capture, webcam_fps):
-			capture_frame = cv2.cvtColor(capture_frame, cv2.COLOR_BGR2RGB)
+		for capture_vision_frame in multi_process_capture(camera_capture, webcam_fps):
+			capture_vision_frame = cv2.cvtColor(capture_vision_frame, cv2.COLOR_BGR2RGB)
+			capture_vision_frame = fit_cover_frame(capture_vision_frame, (webcam_width, webcam_height))

 			if webcam_mode == 'inline':
-				yield capture_frame
-			else:
+				yield capture_vision_frame
+			if webcam_mode in [ 'udp', 'v4l2' ]:
 				try:
-					stream.stdin.write(capture_frame.tobytes())
+					stream.stdin.write(capture_vision_frame.tobytes())
 				except Exception:
 					pass

@@ -1,4 +1,5 @@
 import importlib
+import logging
 import os
 import warnings
 from types import ModuleType
@@ -72,6 +73,7 @@ def init() -> None:
 	os.environ['GRADIO_ANALYTICS_ENABLED'] = '0'
 	os.environ['GRADIO_TEMP_DIR'] = os.path.join(state_manager.get_item('temp_path'), 'gradio')

+	logging.getLogger('asyncio').setLevel(logging.CRITICAL)
 	warnings.filterwarnings('ignore', category = UserWarning, module = 'gradio')
 	gradio.processing_utils._check_allowed = uis_overrides.mock
 	gradio.processing_utils.convert_video_to_playable_mp4 = uis_overrides.convert_video_to_playable_mp4
@@ -6,10 +6,14 @@ ComponentName = Literal\
 	'age_modifier_direction_slider',
 	'age_modifier_model_dropdown',
 	'background_remover_model_dropdown',
-	'background_remover_color_red_number',
-	'background_remover_color_green_number',
-	'background_remover_color_blue_number',
-	'background_remover_color_alpha_number',
+	'background_remover_fill_color_red_number',
+	'background_remover_fill_color_green_number',
+	'background_remover_fill_color_blue_number',
+	'background_remover_fill_color_alpha_number',
+	'background_remover_despill_color_red_number',
+	'background_remover_despill_color_green_number',
+	'background_remover_despill_color_blue_number',
+	'background_remover_despill_color_alpha_number',
 	'deep_swapper_model_dropdown',
 	'deep_swapper_morph_slider',
 	'expression_restorer_factor_slider',
@@ -69,8 +69,8 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 		{
 			'__metadata__':
 			{
-				'vendor': 'Unknown',
-				'license': 'Non-Commercial',
+				'vendor': 'Anjok07',
+				'license': 'MIT',
 				'year': 2023
 			},
 			'hashes':
@@ -24,7 +24,7 @@ def process(start_time : float) -> ErrorCode:
 	process_manager.start()

 	for task in tasks:
-		error_code = task() # type:ignore[operator]
+		error_code = task() #type:ignore[operator]

 		if error_code > 0:
 			process_manager.end()
@@ -31,7 +31,7 @@ def process(start_time : float) -> ErrorCode:
 	process_manager.start()

 	for task in tasks:
-		error_code = task() # type:ignore[operator]
+		error_code = task() #type:ignore[operator]

 		if error_code > 0:
 			process_manager.end()
@@ -1,9 +1,8 @@
 gradio-rangeslider==0.0.8
 gradio==5.44.1
-numpy==2.2.6
-onnx==1.19.1
-onnxruntime==1.23.2
-opencv-python==4.12.0.88
-psutil==7.1.3
-tqdm==4.67.1
-scipy==1.16.3
+numpy==2.2.1
+onnx==1.20.1
+onnxruntime==1.24.3
+opencv-python==4.13.0.92
+tqdm==4.67.3
+scipy==1.17.1
@@ -15,7 +15,7 @@ def before_all() -> None:
 		'https://github.com/facefusion/facefusion-assets/releases/download/examples-3.0.0/source.jpg',
 		'https://github.com/facefusion/facefusion-assets/releases/download/examples-3.0.0/target-240p.mp4'
 	])
-	subprocess.run(['ffmpeg', '-i', get_test_example_file('target-240p.mp4'), '-vframes', '1', get_test_example_file('target-240p.jpg')])
+	subprocess.run([ 'ffmpeg', '-i', get_test_example_file('target-240p.mp4'), '-vframes', '1', get_test_example_file('target-240p.jpg') ])


@pytest.fixture(scope = 'function', autouse = True)
@@ -20,8 +20,8 @@ def test_create_float_range() -> None:


 def test_calc_int_step() -> None:
-	assert calculate_int_step([0, 1]) == 1
+	assert calculate_int_step([ 0, 1 ]) == 1


 def test_calc_float_step() -> None:
-	assert calculate_float_step([0.1, 0.2]) == 0.1
+	assert calculate_float_step([ 0.1, 0.2 ]) == 0.1
@@ -7,7 +7,7 @@ from facefusion.curl_builder import chain, ping, run, set_timeout
 def test_run() -> None:
 	user_agent = metadata.get('name') + '/' + metadata.get('version')

-	assert run([]) == [ which('curl'), '--user-agent', user_agent, '--insecure', '--location', '--silent' ]
+	assert run([]) == [ which('curl'), '--user-agent', user_agent, '--location', '--silent' ]


 def test_chain() -> None:
@@ -1,4 +1,4 @@
-from facefusion.execution import create_inference_session_providers, get_available_execution_providers, has_execution_provider
+from facefusion.execution import create_inference_providers, get_available_execution_providers, has_execution_provider


 def test_has_execution_provider() -> None:
@@ -10,8 +10,8 @@ def test_get_available_execution_providers() -> None:
 	assert 'cpu' in get_available_execution_providers()


-def test_create_inference_session_providers() -> None:
-	inference_session_providers =\
+def test_create_inference_providers() -> None:
+	inference_providers =\
 	[
 		('CUDAExecutionProvider',
 		{
@@ -21,4 +21,4 @@ def test_create_inference_session_providers() -> None:
 		'CPUExecutionProvider'
 	]

-	assert create_inference_session_providers(1, [ 'cpu', 'cuda' ]) == inference_session_providers
+	assert create_inference_providers(1, [ 'cpu', 'cuda' ]) == inference_providers
@@ -5,6 +5,7 @@ import pytest
 from facefusion import face_classifier, face_detector, face_landmarker, face_recognizer, state_manager
 from facefusion.download import conditional_download
 from facefusion.face_analyser import get_many_faces
+from facefusion.face_store import clear_static_faces
 from facefusion.vision import read_static_image
 from .helper import get_test_example_file, get_test_examples_directory

@@ -37,6 +38,7 @@ def before_each() -> None:
 	face_detector.clear_inference_pool()
 	face_landmarker.clear_inference_pool()
 	face_recognizer.clear_inference_pool()
+	clear_static_faces()


 def test_get_one_face_with_retinaface() -> None:
@@ -62,7 +64,7 @@ def test_get_one_face_with_retinaface() -> None:

 def test_get_one_face_with_scrfd() -> None:
 	state_manager.init_item('face_detector_model', 'scrfd')
-	state_manager.init_item('face_detector_size', '640x640')
+	state_manager.init_item('face_detector_size', '320x320')
 	state_manager.init_item('face_detector_margin', (0, 0, 0, 0))
 	face_detector.pre_check()

@@ -82,7 +84,7 @@ def test_get_one_face_with_scrfd() -> None:


 def test_get_one_face_with_yoloface() -> None:
-	state_manager.init_item('face_detector_model', 'yoloface')
+	state_manager.init_item('face_detector_model', 'yolo_face')
 	state_manager.init_item('face_detector_size', '640x640')
 	state_manager.init_item('face_detector_margin', (0, 0, 0, 0))
 	face_detector.pre_check()
@@ -1,10 +1,12 @@
+import os
 import tempfile

 from facefusion.json import read_json, write_json


 def test_read_json() -> None:
-	_, json_path = tempfile.mkstemp(suffix = '.json')
+	file_descriptor, json_path = tempfile.mkstemp(suffix = '.json')
+	os.close(file_descriptor)

 	assert not read_json(json_path)

@@ -14,6 +16,7 @@ def test_read_json() -> None:


 def test_write_json() -> None:
-	_, json_path = tempfile.mkstemp(suffix = '.json')
+	file_descriptor, json_path = tempfile.mkstemp(suffix = '.json')
+	os.close(file_descriptor)

 	assert write_json(json_path, {})
@@ -3,6 +3,6 @@ from facefusion.sanitizer import sanitize_int_range

 def test_sanitize_int_range() -> None:
 	assert sanitize_int_range(0, [ 0, 1, 2 ]) == 0
-	assert sanitize_int_range(2, [0, 1, 2]) == 2
+	assert sanitize_int_range(2, [ 0, 1, 2 ]) == 2
 	assert sanitize_int_range(-1, [ 0, 1 ]) == 0
 	assert sanitize_int_range(3, [ 0, 1 ]) == 0
@@ -1,11 +1,11 @@
 from facefusion import translator
-from facefusion.locals import LOCALS
+from facefusion.locales import LOCALES


 def test_load() -> None:
-	translator.load(LOCALS, __name__)
+	translator.load(LOCALES, __name__)

-	assert __name__ in translator.LOCAL_POOL_SET
+	assert __name__ in translator.LOCALE_POOL_SET


 def test_get() -> None:
Author	SHA1	Message	Date
Henry Ruhs GitHub harisreedhar	57fcb86b82	3.6.0 (#1062 ) * mark as next * add fran model * add support for corridor key (#1060) * introduce despill color * simplify the apply dispill color * finalize naming for both fill and despill * follow vision_frame convension * patch fran model * adjust fran urls * Feat/dynamic env setup (#1061) * dynamic environment setup * dynamic environment setup * fix fran model * prevent directml using incompatible corridor_key model * fix environment setup for windows * switch to corridor_key_1024 and corridor_key_2048 * switch to corridor_key_1024 and corridor_key_2048 * mark it as 3.6.0 * rename environment to conda * rename environment to conda * fix testing for face analyser * some background remove cosmetics * some background remove cosmetics * some background remove cosmetics * update preview --------- Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>	2026-03-16 15:08:43 +01:00
henryruhs	2cc05d4fba	update licenses	2026-03-09 21:24:53 +01:00
Henry RuhsandGitHub	a498f3d618	Patch 3.5.4 (#1055 ) * remove insecure flag from curl * eleminate repating definitons * limit processors and ui layouts by choices * follow couple of v4 standards * use more secure mkstemp * dynamic cache path for execution providers * fix benchmarker, prevent path traveling via job-id * fix order in execution provider choices * resort by prioroty * introduce support for QNN * close file description for Windows to stop crying * prevent ConnectionResetError under windows * needed for nested .caches directory as onnxruntime does not create it * different approach to silent asyncio * update dependencies * simplify the name to just inference providers * switch to trt_builder_optimization_level 4	2026-03-08 11:00:45 +01:00
Henry Ruhs GitHub Claude	c7976ec9d4	Fix list literal spacing to use [ x, y ] style (#1044 ) Enforce consistent space inside square brackets for all list literals across source and test files. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com>	2026-02-18 09:18:03 +01:00
Henry RuhsandGitHub	8801668562	3.5.3 * honor webcam resolution to avoid stripe mismatch, update dependencies * avoid version conflicts * enforce prores video extraction to 8 bit * make the installer more robust on execution switch * make the installer more robust on execution switch * improve the installer env handling * different approach to handle env	2026-02-11 09:35:08 +01:00
Henry RuhsandGitHub	a7f3de3dbc	Rename local(s) to locale(s) (#1008 )	2025-12-17 18:37:51 +01:00