https://github.com/magic-research/magic-avatar
MagicAvatar: Multimodal Avatar Generation and Animation
https://github.com/magic-research/magic-avatar
Last synced: 8 days ago
JSON representation
MagicAvatar: Multimodal Avatar Generation and Animation
- Host: GitHub
- URL: https://github.com/magic-research/magic-avatar
- Owner: magic-research
- License: bsd-3-clause
- Created: 2023-08-18T12:52:53.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-08-29T04:42:20.000Z (almost 2 years ago)
- Last Synced: 2025-03-03T00:15:26.046Z (4 months ago)
- Homepage: https://magic-avatar.github.io/
- Size: 5.86 KB
- Stars: 622
- Watchers: 64
- Forks: 34
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-diffusion-categorized - [Code
README
MagicAvatar: Multimodal Avatar Generation and Animation
Jianfeng Zhang*
·
Hanshu Yan*
·
Zhongcong Xu*
·
Jiashi Feng
·
Jun Hao Liew†
ByteDance Inc.
![]()
![]()
![]()
*Introducing MagicAvatar, a multi-modal framework capable of converting various input modalities — text, video, and audio — into motion signals that subsequently generate/ animate an avatar.*
*For more general video editing applications, please also check our latest work MagicEdit!*
## Citing
If you find our work useful, please consider citing:
```BibTeX
@inproceedings{zhang2023magicavatar,
author = {Zhang, Jianfeng and Yan, Hanshu and Xu, Zhongcong and Feng, Jiashi and Liew, Jun Hao},
title = {MagicAvatar: Multi-modal Avatar Generation and Animation},
booktitle = {arXiv},
year = {2023}
}@inproceedings{liew2023magicedit,
author = {Liew, Jun Hao and Yan, Hanshu and Zhang, Jianfeng and Xu, Zhongcong and Feng, Jiashi},
title = {MagicEdit: High-Fidelity and Temporally Coherent Video Editing},
booktitle = {arXiv},
year = {2023}
}
```