{"ID":2852338,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18775","arxiv_id":"2510.18775","title":"UltraGen: High-Resolution Video Generation with Hierarchical Attention","abstract":"Recent advances in video generation have made it possible to produce visually compelling videos, with wide-ranging applications in content creation, entertainment, and virtual reality. However, most existing diffusion transformer based video generation models are limited to low-resolution outputs (\u003c=720P) due to the quadratic computational complexity of the attention mechanism with respect to the output width and height. This computational bottleneck makes native high-resolution video generation (1080P/2K/4K) impractical for both training and inference. To address this challenge, we present UltraGen, a novel video generation framework that enables i) efficient and ii) end-to-end native high-resolution video synthesis. Specifically, UltraGen features a hierarchical dual-branch attention architecture based on global-local attention decomposition, which decouples full attention into a local attention branch for high-fidelity regional content and a global attention branch for overall semantic consistency. We further propose a spatially compressed global modeling strategy to efficiently learn global dependencies, and a hierarchical cross-window local attention mechanism to reduce computational costs while enhancing information flow across different local windows. Extensive experiments demonstrate that UltraGen can effectively scale pre-trained low-resolution video models to 1080P and even 4K resolution for the first time, outperforming existing state-of-the-art methods and super-resolution based two-stage pipelines in both qualitative and quantitative evaluations.","short_abstract":"Recent advances in video generation have made it possible to produce visually compelling videos, with wide-ranging applications in content creation, entertainment, and virtual reality. However, most existing diffusion transformer based video generation models are limited to low-resolution outputs (\u003c=720P) due to the qu...","url_abs":"https://arxiv.org/abs/2510.18775","url_pdf":"https://arxiv.org/pdf/2510.18775v1","authors":"[\"Teng Hu\",\"Jiangning Zhang\",\"Zihan Su\",\"Ran Yi\"]","published":"2025-10-21T16:23:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}