KwaiVGI / LivePortrait

Bring portraits to life!
https://liveportrait.github.io
Other
12.09k stars 1.27k forks source link

Training of the second stage #350

Open JZArray opened 1 month ago

JZArray commented 1 month ago

Hello, a quick question, I am trying to train this model from scratch, and it seems the first-stage training is ok, and I have gotten a promising result. While training the second stage, results are always noised, so I want to ask how to train the second one? Should a pretrained model from the first stage be frozen, and only the stitching module is going to be trained? Whether only using stitching loss to supervise stitching module is enough, or losses used in the first stage should be also used?

Apokar commented 1 month ago

Hi,May i ask how did you train this model. Did you write the training code and collect train-data yourself?

JZArray commented 1 month ago

Hi,May i ask how did you train this model. Did you write the training code and collect train-data yourself?

Yes, we have implemented training codes and collected datasets by ourselves.

NithinJangid commented 3 weeks ago

Hi @JZArray, can you share the training code and sample dataset that needs for training

henbucuoshanghai commented 5 days ago

implemented training codes,great