metadata
license: apache-2.0
pipeline_tag: text-to-video
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation
This repository contains the weights for DomainShuttle, an open-domain subject-driven text-to-video (S2V) generation method presented in DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation.
DomainShuttle achieves both high subject fidelity and generative flexibility across diverse open-domain video personalization scenarios by decoupling reference and video features.
- Project Page: DomainShuttle Project Page
- Code: GitHub Repository
Citation
If you find our work useful in your research, please consider citing:
@article{chen2026domainshuttle,
title={DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation},
author={Chen, Nan and Cai, Yiyang Caps and Xie, Rongchang and Pan, Junwen and Chen, Cheng and Jia, Weinan and Chen, Zhuowei and Zhou, Wen and Sun, Zhenbang and Luo, Wenhan},
journal={arXiv preprint arXiv:2606.26058},
year={2026}
}