SadTalker
SadTalker copied to clipboard
OpenTalker
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Traceback (most recent call last): File "E:\SadTalker-main\venv\lib\site-packages\gradio\routes.py", line 401, in run_predict output = await app.get_blocks().process_api( File "E:\SadTalker-main\venv\lib\site-packages\gradio\blocks.py", line 1302, in process_api result = await self.call_function( File "E:\SadTalker-main\venv\lib\site-packages\gradio\blocks.py", line 1025, in...
您好~感谢开源 使用sd webui安装sadTalker后，按照说明文件在其模块设置中选择“full”的处理方式，最后生成的视频是0字节，如果选择“crop”的话，生成的视频没有声音，请问是怎么回事，该如何解决呢？
已解决，谢谢！
[aac @ 000002742c270480] Qavg: 56305.840 The generated video is named ./results/c7bc0a51-fca0-452f-b3f6-5123e3addca0/tmps1bsrfmp##audio 2-0-100_enhanced.mp4 The generated video is named tmps1bsrfmp##audio 2-0-100 in ./results/c7bc0a51-fca0-452f-b3f6-5123e3addca0 Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call...
Kindly requesting an extension for the oobabooga webui for video and photo functionality to be added to: https://github.com/oobabooga/text-generation-webui Would be amazing if you can make an extension for the use...
Gpu memory is 6G,Looks like it's not enough。so Can I use the CPU when the GPU memory is low？
Hey @vinthony ! 👋 This pull request makes it possible to run your model inside a Docker environment with an open-source tool called [Cog](https://github.com/replicate/cog). Then the model can be run...
stderr: ERROR: Could not find a version that satisfies the requirement tb-nightly (from basicsr) (from versions: none) ERROR: No matching distribution found for tb-nightly
Commit hash: Installing requirements for SadTalker WebUI (may take longer time in first time) Traceback (most recent call last): File "Launcher.py", line 203, in prepare_environment() File "Launcher.py", line 189, in...
My command is：  An error appeared:  Other remarks: 1. The size of my reference video and my source image are not the same. Do they have to be...
Metadata
Owner
Metadata
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation