ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions

 β€‚  β€‚  β€‚  

Xiaoxue Wu1,2*, Xinyuan Chen2†, Yaohui Wang2†, Yu Qiao2†,

1Fudan University 2Shanghai Artificial Intelligence Laboratory

*Work done during internship at Shanghai AI Laboratory †Corresponding author

πŸ“₯ Installation

  1. Clone the Repository
git clone https://github.com/UknowSth/ShotDirector.git
cd ShotDirector
  1. Set up Environment
conda create -n shotdirector python==3.11.9
conda activate shotdirector

pip install torch==2.5.1 torchvision==0.20.1 --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt

πŸ€— Checkpoint

CineTrans-DiT

Download the weights of Wan2.1-T2V-1.3B and the weights required for Shotdirector. Place them in the .ckpt/ folder as shown in the following diagram.

ckpt/
│── Wan2.1/Wan2.1-T2V-1.3B/
β”‚   β”œβ”€β”€ config.json
β”‚   β”œβ”€β”€ diffusion_pytorch_model.safetensors
β”‚   β”œβ”€β”€ google/  
β”‚   │── models_t5_umt5-xxl-enc-bf16.pth
β”‚   └── Wan2.1_VAE.pth
│── encoder.pt
│── model.pt
│── trans.pt

For more inference details, please refer to our GitHub repository.

πŸ“‘ BiTeX

If you find ShotDirector useful for your research and applications, please cite using this BibTeX:

@misc{wu2025shotdirectordirectoriallycontrollablemultishot,
      title={ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions}, 
      author={Xiaoxue Wu and Xinyuan Chen and Yaohui Wang and Yu Qiao},
      year={2025},
      eprint={2512.10286},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.10286}, 
}
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 NumlockUknowSth/ShotDirector