Search

News
Publications

Light Dark Automatic

Text-to-Video

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720×1280 resolution and minute-length …

Junsong Chen, Yuyang Zhao, Jincheng YU, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie

PDF Cite Code Project Demo

© 2026 NVIDIA. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.

Cite