Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915673856278528 |
|---|---|
| author | Ye, Fanjiang Zhao, Zepeng Mu, Yi Shen, Jucheng Li, Renjie Wang, Kaijian Agarwal, Saurabh Lee, Myungjin Cao, Triston Akella, Aditya Krishnamurthy, Arvind Ng, T. S. Eugene Tu, Zhengzhong Wang, Yuke |
| author_facet | Ye, Fanjiang Zhao, Zepeng Mu, Yi Shen, Jucheng Li, Renjie Wang, Kaijian Agarwal, Saurabh Lee, Myungjin Cao, Triston Akella, Aditya Krishnamurthy, Arvind Ng, T. S. Eugene Tu, Zhengzhong Wang, Yuke |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17756 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling Ye, Fanjiang Zhao, Zepeng Mu, Yi Shen, Jucheng Li, Renjie Wang, Kaijian Agarwal, Saurabh Lee, Myungjin Cao, Triston Akella, Aditya Krishnamurthy, Arvind Ng, T. S. Eugene Tu, Zhengzhong Wang, Yuke Machine Learning Systems and Control 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. |
| title | SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2508.17756 |