mirror of
https://github.com/facefusion/facefusion.git
synced 2026-08-05 16:48:36 +02:00
* mark as next * unify the dependency checks in pre_check and add ffprobe (#1181) * drop keep_temp and the common options component (#1180) Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * introduce ffprobe and ffprobe_builder (#1182) * introduce ffprobe and ffprobe_builder Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * introduce ffprobe and ffprobe_builder Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * probe video metadata via ffprobe in vision (#1184) * probe video metadata via ffprobe in vision Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * probe video metadata via ffprobe in vision Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * adopt the workflow task vocabulary from next major (#1185) Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * introduce workflow-mode and workflow-strategy like next major (#1187) Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * restrict hdr color transfer and tag the merge output as bt709 (#1188) * restrict hdr color transfer and tag the merge output as bt709 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * restrict hdr color transfer and tag the merge output as bt709 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * full video migration * compose the hdr fixture via the builder chain Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * compose the test fixtures via the builder and run_ffmpeg Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * compose every test fixture via the builder and run_ffmpeg (#1189) * compose every test fixture via the builder and run_ffmpeg Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * use loops in tests for ffmpeg stuff --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * New Video Manager (#1191) * tiny adjustment for tests * address the review on the video manager Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * introduce the stream strategy for the video workflow (#1192) * introduce the stream strategy for the video workflow Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * address the review on the stream strategy Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * annotate the changes for review Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * annotate the new tests for review Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * match the temp pixel format help to the locale style Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * question the set_input_seek naming Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * question the reader and writer keys Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * drop the review annotations from the encoder mapping tests Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * drop the review annotations from the thread count tests Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * drop the review annotations from the ui files Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * capture the open review questions as annotations Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a * drop the settled annotations from the types Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> * switch to ffmpeg.style for audio.py * remove todos that were never needed * fix for ffmpeg7 * Add frame_store module (#1194) * add frame_store module * rename and change tests * rename and update tests * route window read through frame_store (#1196) * route window read through frame_store * update proper id * restore todos * restore todos * go v4 style for workflow (#1197) * go v4 style for workflow * remove some todos * route chunk read through frame_store (#1198) * vision integration * Deleted read_video_chunk + read_static_video_chunk * margin decouple (#1199) * fix windows CI fail (#1200) * Cleanup Part1 (#1201) * remove some todos, improve video manager, simplify ffmpeg commands and more * do more * remove thread count for filters * Cleanup Part 2 (#1202) * tons of renaming * tons of renaming * multi reader approach * bring tests to an okay-ish state * bring drain back * improve read_video_frame speed * rename method * move variables * seek video reader only when trim frame start is larger 0 * make stream the default * Cleanup/part 3 (#1203) * remove todo * sort out workflow, to match upcoming v4 * remove look ahead * remove core namespace again * Revamp execution provider overrides/adjustments (#1206) * Split provider hooks into override/adjust with cached CoreML base Replace the single resolve_inference_providers processor hook with two: override_inference_providers (full replacement) and adjust_inference_providers (merge options onto the base providers built by create_inference_providers). This lets CoreML processors inherit ModelCacheDirectory + SpecializationStrategy from the base while layering ModelFormat/MLComputeUnits on top. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HTQCZiYjJyUX11bDpbRSiB * fix caching for execution provider by having override and adjust ways * fix caching for execution provider by having override and adjust ways * fix lint * use proper pytest fixtures --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix update preview bug (#1205) * fix update preview bug * fix update preview bug * remove guard * add is_vision_frame * Restrict the preview frame slider and the reader seek to the last frame index (#1207) * fix index bug * fix rounding bug * avoid tobytes copy (#1208) * beautify tests * hide ffmpeg warnings * simplify process_stream_frame * Use is vision frame everywhere (#1210) * use is_vision_frame everywhere * fix hash * fix lint * fix hash creation in face store * that model does not exist * update workflow ffmpeg * guard workflow (#1211) * bump version and dependencies * Update preview * switch workflow strategy to disk|memory * update preview * update preview * fix wording * last minute change workflow position * adjust wording --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com> Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
100 lines
3.8 KiB
Python
100 lines
3.8 KiB
Python
import os
|
|
import subprocess
|
|
from collections import deque
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from typing import Deque, Iterator, List
|
|
|
|
import cv2
|
|
from tqdm import tqdm
|
|
|
|
from facefusion import ffmpeg_builder, logger, state_manager, translator
|
|
from facefusion.audio import create_empty_audio_frame
|
|
from facefusion.content_analyser import analyse_stream
|
|
from facefusion.ffmpeg import open_ffmpeg
|
|
from facefusion.filesystem import is_directory
|
|
from facefusion.processors.core import get_processors_modules
|
|
from facefusion.types import Fps, StreamMode, VisionFrame
|
|
from facefusion.vision import extract_vision_mask, is_vision_frame, read_static_images
|
|
|
|
|
|
def multi_process_capture(camera_capture : cv2.VideoCapture, camera_fps : Fps) -> Iterator[VisionFrame]:
|
|
capture_deque : Deque[VisionFrame] = deque()
|
|
source_vision_frames = read_static_images(state_manager.get_item('source_paths'))
|
|
|
|
with tqdm(desc = translator.get('streaming'), unit = 'frame', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
|
|
with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
|
|
futures = []
|
|
|
|
while camera_capture and camera_capture.isOpened():
|
|
_, capture_vision_frame = camera_capture.read()
|
|
if analyse_stream(capture_vision_frame, camera_fps):
|
|
camera_capture.release()
|
|
|
|
if is_vision_frame(capture_vision_frame):
|
|
future = executor.submit(process_stream_frame, source_vision_frames, capture_vision_frame)
|
|
futures.append(future)
|
|
|
|
for future_done in [ future for future in futures if future.done() ]:
|
|
capture_vision_frame = future_done.result()
|
|
capture_deque.append(capture_vision_frame)
|
|
futures.remove(future_done)
|
|
|
|
while capture_deque:
|
|
progress.update()
|
|
yield capture_deque.popleft()
|
|
|
|
|
|
def process_stream_frame(source_vision_frames : List[VisionFrame], target_vision_frame : VisionFrame) -> VisionFrame:
|
|
source_audio_frame = create_empty_audio_frame()
|
|
source_voice_frame = create_empty_audio_frame()
|
|
temp_vision_frame = target_vision_frame.copy()
|
|
temp_vision_mask = extract_vision_mask(temp_vision_frame)
|
|
|
|
for processor_module in get_processors_modules(state_manager.get_item('processors')):
|
|
logger.disable()
|
|
if processor_module.pre_process('stream'):
|
|
logger.enable()
|
|
temp_vision_frame, temp_vision_mask = processor_module.process_frame(
|
|
{
|
|
'source_vision_frames': source_vision_frames,
|
|
'source_audio_frame': source_audio_frame,
|
|
'source_voice_frame': source_voice_frame,
|
|
'target_vision_frames': [ target_vision_frame ],
|
|
'temp_vision_frame': temp_vision_frame,
|
|
'temp_vision_mask': temp_vision_mask
|
|
})
|
|
logger.enable()
|
|
|
|
return temp_vision_frame
|
|
|
|
|
|
def open_stream(stream_mode : StreamMode, stream_resolution : str, stream_fps : Fps) -> subprocess.Popen[bytes]:
|
|
commands = ffmpeg_builder.chain(
|
|
ffmpeg_builder.capture_video(),
|
|
ffmpeg_builder.set_media_resolution(stream_resolution),
|
|
ffmpeg_builder.set_input_fps(stream_fps)
|
|
)
|
|
|
|
if stream_mode == 'udp':
|
|
commands.extend(ffmpeg_builder.set_input('-'))
|
|
commands.extend(ffmpeg_builder.set_stream_mode('udp'))
|
|
commands.extend(ffmpeg_builder.set_stream_quality(2000))
|
|
commands.extend(ffmpeg_builder.set_output('udp://localhost:27000?pkt_size=1316'))
|
|
|
|
if stream_mode == 'v4l2':
|
|
device_directory_path = '/sys/devices/virtual/video4linux'
|
|
commands.extend(ffmpeg_builder.set_input('-'))
|
|
commands.extend(ffmpeg_builder.set_stream_mode('v4l2'))
|
|
|
|
if is_directory(device_directory_path):
|
|
device_names = os.listdir(device_directory_path)
|
|
|
|
for device_name in device_names:
|
|
device_path = '/dev/' + device_name
|
|
commands.extend(ffmpeg_builder.set_output(device_path))
|
|
|
|
else:
|
|
logger.error(translator.get('stream_not_loaded').format(stream_mode = stream_mode), __name__)
|
|
|
|
return open_ffmpeg(commands)
|