Skip to content

Latest commit

 

History

History
147 lines (112 loc) · 6.58 KB

README.md

File metadata and controls

147 lines (112 loc) · 6.58 KB
Raw

SEINE

arXiv Project Page Replicate Hugging Face Spaces Hits

This repository is the official implementation of SEINE:

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (ICLR2024)

SEINE is a video diffusion model and is part of the video generation system Vchitect. You can also check our Text-to-Video (T2V) framework LaVie.

Setup

Prepare Environment

conda create -n seine python==3.9.16
conda activate seine
pip install -r requirement.txt

Download our model and T2I base model

Our model is based on Stable diffusion v1.4, you may download Stable Diffusion v1-4 to the director of pretrained . Download our model checkpoint (from google drive or hugging face) and save to the directory of pretrained

Now under ./pretrained, you should be able to see the following:

├── pretrained
│   ├── seine.pt
│   ├── stable-diffusion-v1-4
│   │   ├── ...
└── └── ├── ...
        ├── ...

Usage

Inference for I2V

Run the following command to get the I2V results:

python sample_scripts/with_mask_sample.py --config configs/sample_i2v.yaml

The generated video will be saved in ./results/i2v.

More Details

You may modify ./configs/sample_i2v.yaml to change the generation conditions. For example:

ckpt is used to specify a model checkpoint.

text_prompt is used to describe the content of the video.

input_path is used to specify the path to the image.

Inference for Transition

python sample_scripts/with_mask_sample.py --config configs/sample_transition.yaml

The generated video will be saved in ./results/transition.

Results

I2V Results

Input Image Output Video

Transition Results

Input Images Output Video

BibTeX

@inproceedings{chen2023seine,
  title={Seine: Short-to-long video diffusion model for generative transition and prediction},
  author={Chen, Xinyuan and Wang, Yaohui and Zhang, Lingjun and Zhuang, Shaobin and Ma, Xin and Yu, Jiashuo and Wang, Yali and Lin, Dahua and Qiao, Yu and Liu, Ziwei},
  booktitle={ICLR},
  year={2023}
}
@article{wang2023lavie,
  title={LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models},
  author={Wang, Yaohui and Chen, Xinyuan and Ma, Xin and Zhou, Shangchen and Huang, Ziqi and Wang, Yi and Yang, Ceyuan and He, Yinan and Yu, Jiashuo and Yang, Peiqing and others},
  journal={IJCV},
  year={2024}
}

Disclaimer

We disclaim responsibility for user-generated content. The model was not trained to realistically represent people or events, so using it to generate such content is beyond the model's capabilities. It is prohibited for pornographic, violent and bloody content generation, and to generate content that is demeaning or harmful to people or their environment, culture, religion, etc. Users are solely liable for their actions. The project contributors are not legally affiliated with, nor accountable for users' behaviors. Use the generative model responsibly, adhering to ethical and legal standards.

Contact Us

Xinyuan Chen: [email protected] Yaohui Wang: [email protected]

Acknowledgements

The code is built upon LaVie, diffusers and Stable Diffusion, we thank all the contributors for open-sourcing.

License

The code is licensed under Apache-2.0, model weights are fully open for academic research and also allow free commercial usage. To apply for a commercial license, please contact [email protected].