MCPcopy Create free account
hub / github.com/IronSpiderMan/MuseTalkPlus / process_video

Function process_video

scripts/prepare_dataset.py:32–125  ·  view source on GitHub ↗

video_path: 视频路径 face_shift: 人脸往上偏移的像素值,如果为None则偏移到额头 return { "image_files": ['path/to/image01', 'path/to/image02'], "audio_files": ['path/to/audio01', 'path/to/audio02'], }

(video_path, face_shift=None, include_latents=False)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

process_videosFunction · 0.70

Calls 7

recreate_multiple_dirsFunction · 0.90
video2imagesFunction · 0.90
read_imagesFunction · 0.90
video2audioFunction · 0.90
analysisMethod · 0.80
face_locationMethod · 0.80
extract_featuresMethod · 0.45

Tested by

no test coverage detected