YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

Qinghe Wang1 Xiaoyu Shi2βœ‰ Baolu Li1 Weikang Bian3 Quande Liu2 Huchuan Lu1
Xintao Wang2 Pengfei Wan2 Kun Gai2 Xu Jia1βœ‰

1Dalian University of Technology    2Kling Team, Kuaishou Technology
3The Chinese University of Hong Kong    βœ‰Corresponding author

   

Please refer to the Github README for usage.

πŸ“Œ TL;DR

MultiShotMaster is a controllable multi-shot narrative video generation framework that supports 1) text-driven inter-shot consistency, 2) variable shot counts and shot durations, 3) customized subject with motion control, and 4) background-driven customized scene.

🌟 Citation

Please leave us a star 🌟 and cite our paper if you find our work helpful.

@article{wang2025multishotmaster,
  title={MultiShotMaster: A Controllable Multi-Shot Video Generation Framework},
  author={Wang, Qinghe and Shi, Xiaoyu and Li, Baolu and Bian, Weikang and Liu, Quande and Lu, Huchuan and Wang, Xintao and Wan, Pengfei and Gai, Kun and Jia, Xu},
  journal={arXiv preprint arXiv:2512.03041},
  year={2025}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Paper for KlingTeam/MultiShotMaster