Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curationl

Xin Yan, Yuxuan Cai, Qiuyue Wang, Yuan Zhou, Wenhao Huang, Huan Yang,

Quick Start

Full code is released. We will update this markdown in several days...

Citation

@article{yan2024long,
  title={Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation},
  author={Yan, Xin and Cai, Yuxuan and Wang, Qiuyue and Zhou, Yuan and Huang, Wenhao and Yang, Huan},
  journal={arXiv preprint arXiv:2412.01316},
  year={2024}
}

Acknowledgment

We extend our heartfelt appreciation for the great contribution to the open-source community:

• Allegro: A powerful text-to-video and text-image-to-video model that generates high-quality videos.
• Open-Sora-Plan: A project aims to create a simple and scalable repo, to reproduce Sora.
• EMA-VFI: A video frame interpolation model.
• DiT: Scalable Diffusion Models with Transformers.
• T5: A powerful text encoder.