InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
This addresses the problem of efficient, high-quality video generation for applications requiring industrial-level 720p output, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of high-resolution image and dynamic video synthesis by introducing InfinityStar, a unified spacetime autoregressive framework that jointly captures spatial and temporal dependencies. The result is a model that scores 83.74 on VBench, outperforming all autoregressive models and some diffusion competitors, while generating 720p videos approximately 10x faster than leading diffusion-based methods.
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 interactive video synthesis via straightforward temporal autoregression. Extensive experiments demonstrate that InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing some diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10x 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.