search

OpenTalker / SadTalker

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
https://sadtalker.github.io/
Other
12.04k stars 2.24k forks source link

ImportError: cannot import name 'GFPGANer' from 'gfpgan' (unknown location) #628

Open lvsh2012 opened 1 year ago

lvsh2012 commented 1 year ago

python inference.py --driven_audio test/test.wav --source_image test/zh.png --result_dir results> --still --preprocess full --enhancer gfpgan

Traceback (most recent call last): File "D:\code\python\SadTalker\inference.py", line 10, in from src.facerender.animate import AnimateFromCoeff File "D:\code\python\SadTalker\src\facerender\animate.py", line 23, in from src.utils.face_enhancer import enhancer_generator_with_len, enhancer_list File "D:\code\python\SadTalker\src\utils\face_enhancer.py", line 4, in from gfpgan import GFPGANer ImportError: cannot import name 'GFPGANer' from 'gfpgan' (unknown location)

lvsh2012 commented 1 year ago

win10 环境，使用以下命令

Install Python 3.10.6, checking "Add Python to PATH". Install git manually (OR scoop install git via scoop). Install ffmpeg, following this instruction (OR using scoop install ffmpeg via scoop). Download our SadTalker repository, for example by running git clone https://github.com/Winfredy/SadTalker.git. Download the checkpoint and gfpgan below↓. Run start.bat from Windows Explorer as normal, non-administrator, user, a gradio WebUI demo will be started.

zyj-2000 commented 10 months ago

pip install gfpgan