FoundationVision/InfinityStar

Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

📖 Introduction

We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long-duration video synthesis via straightforward temporal autoregression. Through extensive experiments, InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10$\times$ faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial-level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation.

📌 Note

This repo is used for hosting InfinityStar's checkpoints. For more details, please refer to  

📖 Citation

If our work assists your research, feel free to give us a star ⭐ or cite us using:

@article{InfinityStar,
  title={InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation},
  author={Jinlai Liu and jian Han and Bin Yan and Hui Wu and Fengda Zhu and Xing Wang and Yi Jiang and Bingyue Peng and Zehuan Yuan},
  journal={Advances in neural information processing systems},
  year={2025},
}