SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
- Published
- Source
- arXiv
- Paper number
- 699
- Field
- Computer Vision
- arXiv ID
- 2607.21553
Key points
- It mixes linear attention and softmax attention in a 3-to-1 ratio so that it can achieve both speed and quality.
- The AttnRes technique improves information quality in deep layers by about 12 percent.
- A single H100 GPU can generate a 720p video in 13 seconds, which is 120 times faster than Wan 2.2.
- It directly learns the optimal balance point by showing that 25 percent softmax attention is the best trade-off between quality and efficiency.
- Kernel optimization through Sol-Engine delivers an additional 3.58 times speedup.
Paper links
External research summaries. These are not HDATF publications or measured product results.