Show 1 Sr1

🚀 show-1-sr1

Show-1-sr1 is an efficient text-to-video model that combines the strengths of pixel-based and latent-based VDMs to generate high-quality videos with good video-text alignment.

Pixel-based VDMs can generate motion accurately aligned with the textual prompt but typically demand expensive computational costs in terms of time and GPU memory, especially when generating high-resolution videos. Latent-based VDMs are more resource-efficient because they work in a reduced-dimension latent space. But it is challenging for such small latent space (e.g., 64×40 for 256×160 videos) to cover rich yet necessary visual semantic details as described by the textual prompt.

To marry the strength and alleviate the weakness of pixel-based and latent-based VDMs, we introduce Show-1, an efficient text-to-video model that generates videos of not only decent video-text alignment but also high visual quality.

📚 Documentation

Model Details

This is the super-resolution model of Show-1 that upscales videos from a 64x40 resolution to 256x160. The model is finetuned from DeepFloyd/IF-II-M-v1.0 on the WebVid-10M dataset.

🚀 Quick Start

Installation

Clone the GitHub repository and install the requirements:

git clone https://github.com/showlab/Show-1.git
pip install -r requirements.txt

Usage Examples

Basic Usage

Run the following command to generate a video from a text prompt. By default, this will automatically download all the model weights from huggingface.

python run_inference.py

Advanced Usage

You can also download the weights manually and change the pretrained_model_path in run_inference.py to run the inference.

git lfs install

# base
git clone https://huggingface.co/showlab/show-1-base
# interp
git clone https://huggingface.co/showlab/show-1-interpolation
# sr1
git clone https://huggingface.co/showlab/show-1-sr1
# sr2
git clone https://huggingface.co/showlab/show-1-sr2

📄 License

This project is licensed under the Creative Commons Attribution Non Commercial 4.0 license.

📚 Citation

If you make use of our work, please cite our paper.

@misc{zhang2023show1,
    title={Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation}, 
    author={David Junhao Zhang and Jay Zhangjie Wu and Jia-Wei Liu and Rui Zhao and Lingmin Ran and Yuchao Gu and Difei Gao and Mike Zheng Shou},
    year={2023},
    eprint={2309.15818},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

📞 Model Card Contact

This model card is maintained by David Junhao Zhang and Jay Zhangjie Wu. For any questions, please feel free to contact us or open an issue in the repository.