SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908588744638464 |
|---|---|
| author | Chen, Junsong Zhao, Yuyang Yu, Jincheng Chu, Ruihang Chen, Junyu Yang, Shuai Wang, Xianbang Pan, Yicheng Zhou, Daquan Ling, Huan Liu, Haozhe Yi, Hongwei Zhang, Hao Li, Muyang Chen, Yukang Cai, Han Fidler, Sanja Luo, Ping Han, Song Xie, Enze |
| author_facet | Chen, Junsong Zhao, Yuyang Yu, Jincheng Chu, Ruihang Chen, Junyu Yang, Shuai Wang, Xianbang Pan, Yicheng Zhou, Daquan Ling, Huan Liu, Haozhe Yi, Hongwei Zhang, Hao Li, Muyang Chen, Yukang Cai, Han Fidler, Sanja Luo, Ping Han, Song Xie, Enze |
| contents | We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24695 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer Chen, Junsong Zhao, Yuyang Yu, Jincheng Chu, Ruihang Chen, Junyu Yang, Shuai Wang, Xianbang Pan, Yicheng Zhou, Daquan Ling, Huan Liu, Haozhe Yi, Hongwei Zhang, Hao Li, Muyang Chen, Yukang Cai, Han Fidler, Sanja Luo, Ping Han, Song Xie, Enze Computer Vision and Pattern Recognition Artificial Intelligence We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation. |
| title | SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.24695 |