BachVid: Training-Free Video Generation with Consistent Background and Character

Arxiv 2025

Project page | arXiv

BibTeX

If you find our paper helps, please consider citing:

@misc{yan2025bachvidtrainingfreevideogeneration,
      title={BachVid: Training-Free Video Generation with Consistent Background and Character}, 
      author={Han Yan and Xibin Song and Yifu Wang and Hongdong Li and Pan Ji and Chao Ma},
      year={2025},
      eprint={2510.21696},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.21696}, 
}