SadTalker

SadTalker copied to clipboard

extract_kp_videos.py中读取图片关键点时索引超出界限

2

第33行 keypoints.append(current_kp[-1]) 报错 list index out of range ，请问一下这是我的素材的问题吗

Gltton

图片生成的视频分辨率如何提高？怎么样设置生成的视频不是只有人头

3

hi 请问基于图片生成的视频分辨率如何提高？ 怎么样设置生成的视频不是只有人头，能够包含原图片全身型像？

magicleo

About training code

18

Great job! We want to train the network based on our own datasets, could you please tell us when you will release the training code of Audio2exp or Audio2Pose?

QUTGXX

Thanks for your great work! I found that the generated head is moving around even if I set all the pose to be same with the first frame's pose. Is...

henrycjh

audio sampling rate

1

Hello, I want to ask you about the audio sampling rate. In the example you provided, there are 16k, 24k and 48k. How much should I convert the audio sampling...

shenriver

How to run SadTalker in stable-diffusion-web-ui?

1

Thank you for your work on SadTalker! Could you please provide instructions on how to run SadTalker in stable-diffusion-web-ui?

D-Mad

装不上，总是重复安装模型，都set和设置过了。

26

raise SSLError(e, request=request) requests.exceptions.SSLError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /vinthony/SadTalker/resolve/4aedd064359e623398a2d73eb8c253ebb2bd516c/BFM_Fitting/01_MorphableModel.mat (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:997)')))

sungrande

请问一下为什么在SD生成时总提示出错？

1

C:\novelai-webui-aki-v3\extensions\SadTalker\checkpoints\auido2pose_00140-model.pth C:\novelai-webui-aki-v3\extensions\SadTalker\checkpoints\shape_predictor_68_face_landmarks.dat Traceback (most recent call last): File "C:\novelai-webui-aki-v3\py310\lib\site-packages\gradio\routes.py", line 394, in run_predict output = await app.get_blocks().process_api( File "C:\novelai-webui-aki-v3\py310\lib\site-packages\gradio\blocks.py", line 1075, in process_api result = await self.call_function( File "C:\novelai-webui-aki-v3\py310\lib\site-packages\gradio\blocks.py", line...

Clement-mo

[Remark/Question] Have the results gotten worse since v0.0.2?

2

I used SadTalker to generate shorts similar to these examples on YouTube (https://www.youtube.com/@SharpGoddess/shorts or https://www.youtube.com/shorts/qomN6_CIaFg). However, since I updated, I have not been able to achieve similar results. The videos...

Fy-

sadtalker的视频效果，说一点瑕疵，

1

经过大师的二天解惑，我终于生成了视频。惊艳，惊艳，一点不过分。 呵呵，追求完美是更高想法了： 我发现视频，会增加脸部图像的美白度，这个是优点也是缺点 优点是美颜，缺点是和身体其他部位显的就有突兀感了，有点失真。 请参考一下图片  是我设置的原因吗？

toniedeng