[2512.13592] Image Diffusion Preview with Consistency Solver

Computer Science > Machine Learning arXiv:2512.13592 (cs) [Submitted on 15 Dec 2025 (v1), last revised 7 Apr 2026 (this version, v2)] Title:Image Diffusion Preview with Consistency Solver 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 View a PDF of the paper titled Image Diffusion Preview with Consistency Solver, by Fu-Yun Wang and 10 other authors View PDF HTML (experimental) 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 ...