search

tencent-ailab / V-Express

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.
2.03k stars 250 forks source link

How to extract kps.pth? #34

Open digdigdigging opened 3 weeks ago

digdigdigging commented 3 weeks ago

How to extract kps.pth from image?

A-2-H commented 3 weeks ago

It's in the "HOW TO USE" - KPS is extracted from video files not from images - it will create file with facial animation information. Just replace the mp4 file and paths.

python scripts/extract_kps_sequence_and_audio.py \
    --video_path "./test_samples/short_case/AOC/gt.mp4" \
    --kps_sequence_save_path "./test_samples/short_case/AOC/kps.pth" \
    --audio_save_path "./test_samples/short_case/AOC/aud.mp3"
johndpope commented 2 weeks ago

close