video-retalking

video-retalking copied to clipboard

I can do lip sync for any character. I reduced the quality to 10 MB in order to upload video. If you are interested, write to me in telegram: The_best_result...

Chechgroup

Question: How much time do you spend to treat a ONE MINUTE video?

4

I would like to compare, to see if there is any problem with my config, or if it's slow for everyone?

AIhasArrived

感觉中文支持比较差 有没有中文的模型 怎么训练模型 Uploading output_220.mp4…

Joneshan907

how to make the mouth region smaller?

1

Hi i have a video of a person with beard and far from the camera how can i make the region smaller for the lip sync, right now there is...

jryebread

参考视频是1080p,生成的视频唇部周边抖动,遇到这个问题我应该用哪个参数解决?感谢指点,谢谢啦!!!!

tommasi-a

sieve improvements

4

https://www.sievedata.com/blog/fast-high-quality-ai-lipsyncing Can the improvements made by sieve be done here?

cparello

Problem producing high resolution output

9

In order to get high resolution output in the project, it is necessary to use use_sr=True, but there should be srmodel in it, but this file is not uploaded, will...

oztrkoguz

When will the training code for the model be made public?

2

We would like to train a model for our own scenario. Could you please send us the training code? Email: [email protected]

zongxiangli

UnboundLocalError: local variable 'mask_sharp' referenced before assignment

3

video-retalking/third_part/GPEN/gpen_face_enhancer.py", line 113, in process mask_sharp = cv2.GaussianBlur(mask_sharp, (0,0), sigmaX=1, sigmaY=1, borderType = cv2.BORDER_DEFAULT) UnboundLocalError: local variable 'mask_sharp' referenced before assignment

longma-tech

The instructions in readme is a bit outdated, python 3.8, cuda 11.1 is not fit with 4090, I updated it and tested fine. Finally it works, but not as good...

0000sir