基于一致性求解器的图像扩散预览
Image Diffusion Preview with Consistency Solver
把扩散采样器本身当作可训练的高阶线性多步求解器，用强化学习直接优化少步预览质量与预览-终稿一致性，可作为即插即用的采样器替换 DPM-Solver 类求解器，用于交互式生成与预览-精修流程。
原文依据 we propose ConsistencySolver derived from general linear multistep methods, a lightweight, trainable high-order solver optimized via Reinforcement Learning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像扩散模型缓慢的推理过程显著降低了交互式用户体验。为解决这一问题，我们提出扩散预览（Diffusion Preview）这一新范式：采用快速的少步采样生成初步输出供用户评估，并将完整步数的精修推迟到预览被判定为满意之后。现有加速方法（包括免训练求解器与训练后蒸馏）难以提供高质量的预览，也难以保证预览与最终输出之间的一致性。本文提出 ConsistencySolver，它由一般线性多步方法导出，是一种轻量、可训练的高阶求解器，并通过强化学习进行优化，从而提升预览质量与一致性。实验结果表明，ConsistencySolver 在少步场景下显著提升生成质量，使其非常适用于高效的预览-精修工作流。值得注意的是，它在步数减少 47% 的情况下取得了与 Multistep DPM-Solver 相当的弗雷歇初始距离分数，同时优于蒸馏基线。此外，用户研究表明，我们的方法在保持生成质量的同时，将用户总体交互时间缩短了近 50%。
英文原文摘要 1196 字符
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. In this paper, 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 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.