Giters

rese1f / StableVideo

[ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Home Page:https://rese1f.github.io/StableVideo/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

why does every video need to train a new model?

lucasjinreal opened this issue · comments

commented

why does every video need to train a new model?

commented

Thanks for your insterest. Our method is based on atlas. Same as Text2LIVE, train a new model for each video is necessary. It's like a NeRF but for video.