{"ID":2878443,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17756","arxiv_id":"2508.17756","title":"SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling","abstract":"Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However, generating ultra-high-resolution videos on existing standard-resolution (e.g., 720p) platforms remains challenging due to the excessive re-training requirements and prohibitively high computational and memory costs. To this end, we introduce SUPERGEN, an efficient tile-based framework for ultra-high-resolution video generation. SUPERGEN features a novel training-free algorithmic innovation with tiling to successfully support a wide range of resolutions without additional training efforts while significantly reducing both memory footprint and computational complexity. Moreover, SUPERGEN incorporates a tile-tailored, adaptive, region-aware caching strategy that accelerates video generation by exploiting redundancy across denoising steps and spatial regions. SUPERGEN also integrates cache-guided, communication-minimized tile parallelism for enhanced throughput and minimized latency. Evaluations show that SUPERGEN maximizes performance gains while achieving high output quality across various benchmarks.","short_abstract":"Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However, generating ultra-high-resolution videos on existing standard-resolution (e.g., 720p) plat...","url_abs":"https://arxiv.org/abs/2508.17756","url_pdf":"https://arxiv.org/pdf/2508.17756v2","authors":"[\"Fanjiang Ye\",\"Zepeng Zhao\",\"Yi Mu\",\"Jucheng Shen\",\"Renjie Li\",\"Kaijian Wang\",\"Saurabh Agarwal\",\"Myungjin Lee\",\"Triston Cao\",\"Aditya Akella\",\"Arvind Krishnamurthy\",\"T. S. Eugene Ng\",\"Zhengzhong Tu\",\"Yuke Wang\"]","published":"2025-08-25T07:49:17Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"eess.SY\"]","methods":"[\"Diffusion Model\"]","has_code":false}