README.md

---
license: cc-by-nc-4.0
library_name: diffusers
tags:
- text-to-video
- diffusion distillation
---

# CausVid Model Card


![image/png](https://cdn-uploads.huggingface.co/production/uploads/63363b864067f020756275b7/S1o5lYfdueP7J02rIuZF3.png)

> [**From Slow Bidirectional to Fast Autoregressive Video Diffusion Models**](https://arxiv.org/abs/2412.07772),            
> Tianwei Yin*, Qiang Zhang*, Richard Zhang, William T. Freeman, Frédo Durand, Eli Shechtman, Xun Huang (* equal contribution)        


## Environment Setup 

```bash
git clone https://github.com/tianweiy/CausVid  && cd CausVid
conda create -n causvid python=3.10 -y
conda activate causvid
pip install torch torchvision 
pip install -r requirements.txt 
python setup.py develop
```

Also download the Wan base models from [here](https://github.com/Wan-Video/Wan2.1) and save it to wan_models/Wan2.1-T2V-1.3B/

## Inference Example 

First download the checkpoints: [Autoregressive Model](https://huggingface.co/tianweiy/CausVid/tree/main/autoregressive_checkpoint), [Bidirectional Model 1](https://huggingface.co/tianweiy/CausVid/tree/main/bidirectional_checkpoint1) or [Bidirectional Model 2](https://huggingface.co/tianweiy/CausVid/tree/main/bidirectional_checkpoint2) (performs slightly better). 

### Autoregressive 3-step 5-second Video Generation  

```bash 
python minimal_inference/autoregressive_inference.py --config_path configs/wan_causal_dmd.yaml --checkpoint_folder XXX  --output_folder XXX   --prompt_file_path XXX 
```

### Autoregressive 3-step long Video Generation

```bash 
python minimal_inference/longvideo_autoregressive_inference.py --config_path configs/wan_causal_dmd.yaml --checkpoint_folder XXX  --output_folder XXX   --prompt_file_path XXX   --num_rollout XXX 
```

### Bidirectional 3-step 5-second Video Generation

```bash 
python minimal_inference/bidirectional_inference.py --config_path configs/wan_bidirectional_dmd_from_scratch.yaml --checkpoint_folder XXX  --output_folder XXX   --prompt_file_path XXX 
```

For more information, please refer to the [code repository](https://github.com/tianweiy/DMD2)


## License

CausVid is released under [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en).


## Citation 

If you find CausVid useful or relevant to your research, please kindly cite our papers:

```bib
@inproceedings{yin2025causvid,
    title={From Slow Bidirectional to Fast Autoregressive Video Diffusion Models},
    author={Yin, Tianwei and Zhang, Qiang and Zhang, Richard and Freeman, William T and Durand, Fredo and Shechtman, Eli and Huang, Xun},
    booktitle={CVPR},
    year={2025}
}

@inproceedings{yin2024improved,
    title={Improved Distribution Matching Distillation for Fast Image Synthesis},
    author={Yin, Tianwei and Gharbi, Micha{\"e}l and Park, Taesung and Zhang, Richard and Shechtman, Eli and Durand, Fredo and Freeman, William T},
    booktitle={NeurIPS},
    year={2024}
}

@inproceedings{yin2024onestep,
    title={One-step Diffusion with Distribution Matching Distillation},
    author={Yin, Tianwei and Gharbi, Micha{\"e}l and Zhang, Richard and Shechtman, Eli and Durand, Fr{\'e}do and Freeman, William T and Park, Taesung},
    booktitle={CVPR},
    year={2024}
}
```