Giters

thu-ml / controlvideo

Official implementation for "ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ID Consistency

Carlyx opened this issue · comments

commented

Hi, awesome work!

In fact, I use a dancing video as input, and try to change hair by "+ with red hair".
However, I just get a different result in regard to identity and background (style).
Do you have any suggestion for this result?

300.mp4
commented

Hi, you can change pose control to Canny or HED boundary. These two controls contain detailed information of the source video and thus can preserve the source video content faithfully. You can also try to train the model on the source video using more steps, which allows a trade-off between faithfulness and editability.