{"ID":2829086,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.13592","arxiv_id":"2512.13592","title":"Image Diffusion Preview with Consistency Solver","abstract":"The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs for user evaluation, deferring full-step refinement until the preview is deemed satisfactory. Existing acceleration methods, including training-free solvers and post-training distillation, struggle to deliver high-quality previews or ensure consistency between previews and final outputs. We propose ConsistencySolver derived from general linear multistep methods, a lightweight, trainable high-order solver optimized via Reinforcement Learning, that enhances preview quality and consistency. Experimental results demonstrate that ConsistencySolver significantly improves generation quality and consistency in low-step scenarios, making it ideal for efficient preview-and-refine workflows. Notably, it achieves FID scores on-par with Multistep DPM-Solver using 47% fewer steps, while outperforming distillation baselines. Furthermore, user studies indicate our approach reduces overall user interaction time by nearly 50% while maintaining generation quality. Code is available at https://github.com/G-U-N/consolver.","short_abstract":"The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs for user evaluation, deferring full-step refinement until the preview is deemed s...","url_abs":"https://arxiv.org/abs/2512.13592","url_pdf":"https://arxiv.org/pdf/2512.13592v2","authors":"[\"Fu-Yun Wang\",\"Hao Zhou\",\"Liangzhe Yuan\",\"Sanghyun Woo\",\"Boqing Gong\",\"Bohyung Han\",\"Ming-Hsuan Yang\",\"Han Zhang\",\"Yukun Zhu\",\"Ting Liu\",\"Long Zhao\"]","published":"2025-12-15T17:47:49Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":605929,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2829086,"paper_url":"https://arxiv.org/abs/2512.13592","paper_title":"Image Diffusion Preview with Consistency Solver","repo_url":"https://github.com/G-U-N/consolver","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}