赞
踩
。。。。。。。。。。。。。。。。
pip源,设置:
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
开始安装执行SadTalker安装命令:
- cd SadTalker
-
- conda create -n sadtalker python=3.8
-
- conda activate sadtalker
-
- pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
-
- conda install ffmpeg
-
- pip install -r requirements.txt
python inference.py --driven_audio E:\work\sadTalker\SadTalker\examples\driven_audio\chinese_news.wav --source_image E:\work\sadTalker\SadTalker\examples\source_image\art_2.png --result_dir E:\work\sadTalker\SadTalker\examples\ref_video --still --preprocess full --enhancer gfpgan
python inference.py
--driven_audio E:\work\sadTalker\SadTalker\examples\driven_audio\chinese_news.wav
--source_image E:\work\sadTalker\SadTalker\examples\source_image\art_2.png
--result_dir E:\work\sadTalker\SadTalker\examples\ref_video
--still
--preprocess full
--enhancer gfpgan
1、音频位置
2、图片位置
3、生成结果(视频)位置
4...各种效果
有问题,可能是没有配置正确。
把【项目包】里面的:gfpgan\weights\GFPGANv1.4.pth
剪切到
【虚拟环境】的 Lib\site-packages\gfpgan\weights 目录下
报错:(sadtalker) E:\work\sadTalker\SadTalker>python inference.py --driven_audio E:\work\sadTalker\SadTalker\examples\driven_audio\chinese_news.wav --source_image E:\work\sadTalker\SadTalker\examples\source_image\133.png --result_dir E:\work\sadT
alker\SadTalker\examples\ref_video --still --preprocess full --enhancer gfpgan
using safetensor as default
3DMM Extraction for source image
Traceback (most recent call last):
File "inference.py", line 144, in <module>
main(args)
File "inference.py", line 46, in main
first_coeff_path, crop_pic_path, crop_info = preprocess_model.generate(pic_path, first_frame_dir, args.preprocess,\
File "E:\work\sadTalker\SadTalker\src\utils\preprocess.py", line 103, in generate
x_full_frames, crop, quad = self.propress.crop(x_full_frames, still=True if 'ext' in crop_or_resize.lower() else False, xsize=512)
File "E:\work\sadTalker\SadTalker\src\utils\croper.py", line 131, in crop
raise 'can not detect the landmark from source image'
TypeError: exceptions must derive from BaseException
似乎是在处理图像预处理时出现了问题,导致无法从源图像中检测到地标(landmark)
针对这个问题,建议你检查以下几点:
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。