GitHub - dc-ai-projects/DC-VideoGen: DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

DC-VideoGen is a new post-training framework for accelerating video diffusion models. Key features:

Highlight 1: DC-AE-V - Deep Compression Video Autoencoder with Chunk-Causal Temporal Modeling

@article{chen2025dc,
  title={DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder},
  author={Chen, Junyu and He, Wenkun and Gu, Yuchao and Zhao, Yuyang and Yu, Jincheng and Chen, Junsong and Zou, Dongyun and Lin, Yujun and Zhang, Zhekai and Li, Muyang and others},
  journal={arXiv preprint arXiv:2509.25182},
  year={2025}
}