Weizhi-Zhong / IP_LAP

CVPR2023 talking face implementation for Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

train video render

ZJ-CAI opened this issue · comments

commented

你好,我想训练一个只适用于某特定人物的模型,请问训练video render时数据集的时长以及多样性是否有要求?

Hi, thanks for your interest.
Since I didn't train the network for a person-specific task, I cannot answer this question.
Maybe you can try it or finetune the pre-trained model with the person-specific dataset.

Hi, thanks for your interest. Since I didn't train the network for a person-specific task, I cannot answer this question. Maybe you can try it or finetune the pre-trained model with the person-specific dataset.
hello bro did you do for specific person ?