环境
- 阿里云PAI-DSW
- ubuntu20.04
- pytorch:1.12
- gpu-cu113
1 | git clone https://github.com/OpenTalker/SadTalker.git |
python inference.py
–driven_audio ../ds1.wav
–source_image ../2.jpg
–enhancer gfpgan
–preprocess full
–still
python inference.py –driven_audio test/ds1.wav –source_image test/1.jpg –enhancer gfpgan –cpu
3D 版
1 | git clone https://github.com/OpenTalker/SadTalker.git |