MAGI-1: Autoregressive Video Generation at Scale
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908370562187264 |
|---|---|
| author | ai, Sand. Teng, Hansi Jia, Hongyu Sun, Lei Li, Lingzhi Li, Maolin Tang, Mingqiu Han, Shuai Zhang, Tianning Zhang, W. Q. Luo, Weifeng Kang, Xiaoyang Sun, Yuchen Cao, Yue Huang, Yunpeng Lin, Yutong Fang, Yuxin Tao, Zewei Zhang, Zheng Wang, Zhongshu Liu, Zixun Shi, Dai Su, Guoli Sun, Hanwen Pan, Hong Wang, Jie Sheng, Jiexin Cui, Min Hu, Min Yan, Ming Yin, Shucheng Zhang, Siran Liu, Tingting Yin, Xianping Yang, Xiaoyu Song, Xin Hu, Xuan Zhang, Yankai Li, Yuqiao |
| author_facet | ai, Sand. Teng, Hansi Jia, Hongyu Sun, Lei Li, Lingzhi Li, Maolin Tang, Mingqiu Han, Shuai Zhang, Tianning Zhang, W. Q. Luo, Weifeng Kang, Xiaoyang Sun, Yuchen Cao, Yue Huang, Yunpeng Lin, Yutong Fang, Yuxin Tao, Zewei Zhang, Zheng Wang, Zhongshu Liu, Zixun Shi, Dai Su, Guoli Sun, Hanwen Pan, Hong Wang, Jie Sheng, Jiexin Cui, Min Hu, Min Yan, Ming Yin, Shucheng Zhang, Siran Liu, Tingting Yin, Xianping Yang, Xiaoyu Song, Xin Hu, Xuan Zhang, Yankai Li, Yuqiao |
| contents | We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_13211 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MAGI-1: Autoregressive Video Generation at Scale ai, Sand. Teng, Hansi Jia, Hongyu Sun, Lei Li, Lingzhi Li, Maolin Tang, Mingqiu Han, Shuai Zhang, Tianning Zhang, W. Q. Luo, Weifeng Kang, Xiaoyang Sun, Yuchen Cao, Yue Huang, Yunpeng Lin, Yutong Fang, Yuxin Tao, Zewei Zhang, Zheng Wang, Zhongshu Liu, Zixun Shi, Dai Su, Guoli Sun, Hanwen Pan, Hong Wang, Jie Sheng, Jiexin Cui, Min Hu, Min Yan, Ming Yin, Shucheng Zhang, Siran Liu, Tingting Yin, Xianping Yang, Xiaoyu Song, Xin Hu, Xuan Zhang, Yankai Li, Yuqiao Computer Vision and Pattern Recognition Artificial Intelligence We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai. |
| title | MAGI-1: Autoregressive Video Generation at Scale |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.13211 |