Unified Character Video Editing for Live Streaming
Zhiyuan Li1,3 路 Chi-Man Pun1,馃摢 路 Peng-Tao Jiang2,馃摢 路 Bo Li2 路 Xiaodong Cun3,馃毄
1 University of Macau 2 vivo BlueImage Lab 3 GVC Lab, Great Bay University
馃摢 Corresponding authors 馃毄 Project lead
馃搵 TODO
- If you find EditaLive useful or interesting, please give us a Star 馃専. Your support encourages us to keep improving the project.
- We are doing our best to organize and polish the code for public release 馃弮馃挩. Thank you for your interest and patience 馃檹.
- Release
training code. - Release
inference code,config, andpretrained weights. - Release
paper.
鈿栵笍 Disclaimer
- This project is released for academic research only.
- Users must not use this repository to generate harmful, defamatory, or illegal content.
- The authors bear no responsibility for any misuse or legal consequences arising from the use of this tool.
- By using this code, you agree that you are solely responsible for any content generated.
馃殌 Release Status
The code, pretrained weights, and detailed installation and inference instructions are being prepared for public release. Please watch this repository for updates.
鈿欙笍 Framework
鉂わ笍 Acknowledgement
This repository is mainly built upon Wan-Animate, VideoX-Fun, LightX2V, and FastVideo, thanks to their invaluable contributions.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support