MAGI-1

MAGI-1 is the world's first large autoregressive video generation model open-sourced by Sand AI. It adopts autoregressive architecture, generates smooth and natural videos by predicting video sequences block by block, and supports unlimited scaling and one-shot-to-the-end long video generation. The native resolution of the model can be up to 1440x2568, and the generated video has smooth movements and realistic details, and has the ability of controlled generation, which can realize smooth scene transitions and fine-grained control through chunking cues. MAGI-1 Features High-performance video generation: MAGI-1 can generate high-quality video clips in a short period of time, such as generating a 5-second video in just 3 seconds, generating...

Another heavyweight open source player has emerged in the video generation space. On April 21, 2025, Sand AI, the startup of Marr Prize and Tsinghua Special Prize winner Cao Yue, launched its own big model for video generation -- MAGI-1. This is a world model that generates videos by autoregressive prediction of video block sequences, with natural and smooth generation effects, and multiple versions available for download. According to the official introduction, the video generated by MAGI-1 has the following characteristics: 1, high smoothness, no lag, can be unlimited renewal. It can be a mirror to the end to generate a continuous long visual...