linux centos SadTalker使用指南,超级详细
1.主要按照官方文档操作即可
1.1首先安装安装 anaconda
1.1.1下载anaconda
官网地址:Free Download | Anaconda
wget https://repo.anaconda.com/archive/Anaconda3-2023.03-1-Linux-x86_64.sh
1.1.2安装
sh Anaconda3-2023.03-1-Linux-x86_64.sh
直接默认安装即可
安装后一定要重新打开shell窗口
1.2安装python(不需要)
擦考链接::Python安装 linux_linux安装python_码农弓长先生的博客-CSDN博客
1.3安装git
yum -y install git
1.4下载源码
git clone https://github.com/OpenTalker/SadTalker
1.5参考SanTalker继续安装
git clone https://github.com/Winfredy/SadTalker.git
cd SadTalker
conda create -n sadtalker python=3.8
conda activate sadtalker
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
conda install ffmpeg
pip install --use-pep517 -r requirements.txt
### tts is optional for gradio demo.
### pip install TTS
2.如果没有显卡,则只用cpu
vim /opt/anaconda3/envs/sadtalker/lib/python3.8/site-packages/facexlib/alignment/__init__.py
目录和使用的python环境有关,如果创建环境用的python是3.10
则需要修改的文件是
vim /opt/anaconda3/lib/python3.10/site-packages/facexlib/alignment/__init__.py
#其中 ',"cpu"'为添加的内容
model.load_state_dict(torch.load(model_path,"cpu")['state_dict'], strict=True)
3.具体使用教程示例
python inference.py --driven_audio /opt/source-code/SadTalker/examples/driven_audio/bus_chinese.wav --source_image /opt/source-code/SadTalker/examples/source_image/full_body_1.png --enhancer gfpgan --preprocess full --still
默认生成的文件在results目录下
4.常见报错解决方案
4.1
libGL.so.1: cannot open shared object file: No such file or directory
pip install opencv-python-headless
参考:【解决方法】libGL.so.1: cannot open shared object file: No such file or directory_MrNeoJeep的博客-CSDN博客
5.coda下载慢解决方案
conda 速度慢 解决方案_conda下载慢_一颗小树x的博客-CSDN博客
6.pip安装慢解决方案
一次使用: pip install you_package_name -i https://pypi.tuna.tsinghua.edu.cn/simple(清华源)
一劳永逸 :pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple(清华源)
libX11.so.6: cannot open shared object file: No such file or directory
posted @ 2023-07-26 17:48 cn三少<script></script> 阅读(779) 评论(0) 推荐(0) 编辑