---
license: mit
datasets:
- NumlockUknowSth/Cine250K
language:
- en
pipeline_tag: text-to-video
tags:
- multi-shot
---

<div align="center">
  
<h1>CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models</h1>

[![](https://img.shields.io/static/v1?label=CineTrans&message=Project&color=purple)](https://uknowsth.github.io/CineTrans/)   [![](https://img.shields.io/static/v1?label=Paper&message=Arxiv&color=red&logo=arxiv)](https://arxiv.org/abs/2508.11484)   [![](https://img.shields.io/static/v1?label=Code&message=Github&color=blue&logo=github)](https://github.com/Vchitect/CineTrans)   [![](https://img.shields.io/static/v1?label=Dataset&message=HuggingFace&color=yellow&logo=huggingface)](https://huggingface.co/datasets/NumlockUknowSth/Cine250K)   

                    
<p><a href="https://scholar.google.com/citations?hl=zh-CN&user=TbZZSVgAAAAJ">Xiaoxue Wu</a><sup>1,2*</sup>,
<a href="https://scholar.google.com/citations?user=0gY2o7MAAAAJ&amp;hl=zh-CN" target="_blank">Bingjie Gao</a><sup>2,3</sup>,
<a href="https://scholar.google.com.hk/citations?user=gFtI-8QAAAAJ&amp;hl=zh-CN">Yu Qiao</a><sup>2&dagger;</sup>,
<a href="https://wyhsirius.github.io/">Yaohui Wang</a><sup>2&dagger;</sup>,
<a href="https://scholar.google.com/citations?user=3fWSC8YAAAAJ">Xinyuan Chen</a><sup>2&dagger;</sup></p>


<span class="author-block"><sup>1</sup>Fudan University</span>
<span class="author-block"><sup>2</sup>Shanghai Artificial Intelligence Laboratory</span>
<span class="author-block"><sup>3</sup>Shanghai Jiao Tong University</span>


<span class="author-block"><sup>*</sup>Work done during internship at Shanghai AI Laboratory</span> <span class="author-block"><sup>&dagger;</sup>Corresponding author</span>

</div>


## 📥 Installation
1. Clone the Repository
```
git clone https://github.com/UknowSth/CineTrans.git
cd CineTrans
```
2. Set up Environment
```
conda create -n cinetrans python==3.11.9
conda activate cinetrans

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

## 🤗 Checkpoint  
### CineTrans-Unet
Download the required [model weights](https://huggingface.co/NumlockUknowSth/CineTrans-Unet/tree/main) and place them in the `ckpt/` directory.
```
ckpt/
│── stable-diffusion-v1-4/
│   ├── scheduler/
│   ├── text_encoder/
│   ├── tokenizer/  
│   │── unet/
│   └── vae_temporal_decoder/
│── checkpoint.pt
│── longclip-L.pt
```

For more inference details, please refer to the [GitHub repository](https://github.com/Vchitect/CineTrans).

---

## 📑 BiTeX  
If you find [CineTrans](https://github.com/Vchitect/CineTrans.git) useful for your research and applications, please cite using this BibTeX:
```
@misc{wu2025cinetranslearninggeneratevideos,
      title={CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models}, 
      author={Xiaoxue Wu and Bingjie Gao and Yu Qiao and Yaohui Wang and Xinyuan Chen},
      year={2025},
      eprint={2508.11484},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.11484}, 
}
```