SadTalker
SadTalker copied to clipboard
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Which value of pose_style to choose can ensure that the neck does not twist
I make generate for jpg and mp3 with 9 minutes length it gives error and failed so what is the max mp3 time that can be generated in hugging face?
希望能够提供arm64的docker镜像,同时更新相应依赖的版本,有很多依赖没有指定版本,随着时间迁移,导致安装出现依赖版本冲突。
作者您好!您的工作做的非常精彩,但是该项目中仅包含测试部分,不知道您是否方便开源模型的训练部分?非常期待您的回复
ref_pose的视频有什么要求吗?full下最终生成的视频头部下方会有模糊的现象,是提供的pose视频不对吗?
Traceback (most recent call last): File "G:\Programme\STABLE DIFFUSION\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict output = await app.get_blocks().process_api( File "G:\Programme\STABLE DIFFUSION\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api result = await self.call_function( File "G:\Programme\STABLE DIFFUSION\venv\lib\site-packages\gradio\blocks.py",...
I know I can write --disable-safe-unpickle in the webui_user.bat But why do I need to do that? Why does it need me to compromise the security of it? Wasn't this...
https://github.com/oobabooga/text-generation-webui/discussions/1449
我用的mac,芯片是Intel的,虚拟环境用的pyenv 根据安装步骤已安装完成。 我本地原来安装了ffmpeg,然后根据文档使用pip 也安装了ffmpeg 但是我运行脚本的时候报错: ![image](https://user-images.githubusercontent.com/12129950/234471346-a010be92-f18f-4a1d-bd32-1d0bd1db08c7.png)
Just like that, I'm not able to create a video output bigger than 256x256, I'll like to have a bigger output with more details.