SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified architecture. Designed to generate high-quality video up to 720p on a single GPU, SANA-Video 2.0 matches full-softmax video DiTs in quality while retaining the favorable long-sequence scaling of linear attention. To avoid quadratic attention throughout, Hybrid Linear-Softmax Attention combines gated linear attention for O(N)-dominated mixing with periodic gated-softmax anchors at a 3:1 ratio, restoring the full-rank token interactions that pure linear attention lacks. To propagate these refreshed representations across depth, Block Attention Residuals (AttnRes) route complet...
| Authors | Junsong Chen, Jincheng Yu, Yitong Li et al. |
|---|---|
| Primary category | cs.CV |
| Published | 23 July 2026 |
| Last updated at source | 23 July 2026 |
Connected in the knowledge graph
- Efficient-Large-Model/SANA-Video_2.0_5B_720p_4stepModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.