LiveSpeechPortraits icon indicating copy to clipboard operation
LiveSpeechPortraits copied to clipboard

Personalized data generation

Open arvind-kr7 opened this issue 2 years ago • 3 comments

hey, I cloned the repo. Its working fine with the pretrained model and data generated. But, I wish to train model on new face, and how to generate data for the new face. Is there any source code available?? if yes, whether it is included in this repo? If not can you please provide the same.

If anyone has worked on personalized datasets. please do comment. Your help is appreciated. Thanks

arvind-kr7 avatar Jan 03 '23 10:01 arvind-kr7

I'm looking for same thing, do you have any solution ?

qMartis avatar Feb 06 '23 14:02 qMartis

options folder ([https://github.com/YuanxunLu/LiveSpeechPortraits/tree/main/options]) contained training and testing code, but i don't know how to use this code. If anyone has knowledge of these use cases, please let me know.

samsgates avatar Feb 15 '23 12:02 samsgates

please share your train.py

komilaria avatar Aug 01 '23 01:08 komilaria