Official Gradio demo for MatAnyone 2 and MatAnyone.
🔥 MatAnyone series provide practical human video matting framework supporting target assignment.
🧐 We use MatAnyone 2 as the default model. You can also choose MatAnyone in "Model Selection".
🎪 Try to drop your video/image, assign the target masks with a few clicks, and get the the matting results!

Note: Due to the online GPU memory constraints, any input with too big resolution will be resized to 1080p.
🚀 If you encounter any issue (e.g., frozen video output) or wish to run on higher resolution inputs, please consider duplicating this space or launching the demo locally following the GitHub instructions.

If our projects are helpful, please help to 🌟 the Github Repo for MatAnyone 2 and MatAnyone. Thanks!

📑 Citation
If our work is useful for your research, please consider citing:

@InProceedings{yang2026matanyone2,
      title     = {{MatAnyone 2}: Scaling Video Matting via a Learned Quality Evaluator},
      author    = {Yang, Peiqing and Zhou, Shangchen and Hao, Kai and Tao, Qingyi},
      booktitle = {CVPR},
      year      = {2026}
}

@InProceedings{yang2025matanyone,
     title     = {{MatAnyone}: Stable Video Matting with Consistent Memory Propagation},
     author    = {Yang, Peiqing and Zhou, Shangchen and Zhao, Jixin and Tao, Qingyi and Loy, Chen Change},
     booktitle = {CVPR},
     year      = {2025}
}

📝 License
This project is licensed under S-Lab License 1.0. Redistribution and use for non-commercial purposes should follow this license.
📧 Contact
If you have any questions, please feel free to reach me out at peiqingyang99@outlook.com.
👏 Acknowledgement
This project is built upon Cutie, with the interactive demo adapted from ProPainter, leveraging segmentation capabilities from Segment Anything. Thanks for their awesome works!