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.

翻译：图像扩散模型的缓慢推理过程显著降低了交互式用户体验。为解决该问题，我们提出扩散预览（Diffusion Preview）这一新范式：通过快速低步采样生成初步输出供用户评估，待预览结果满意后再进行全步细化。现有加速方法（包括免训练求解器与训练后蒸馏）难以提供高质量预览，或无法保证预览与最终输出间的一致性。我们提出基于一般线性多步法推导的一致性求解器（ConsistencySolver），这是一种经强化学习优化的轻量级可训练高阶求解器，可提升预览质量与一致性。实验表明，在低步场景下，一致性求解器显著改善了生成质量与一致性，适用于高效的预览-细化工作流。值得注意的是，其FID分数与多步DPM-Solver相当，但步数减少47%，同时优于蒸馏基线方法。此外，用户研究显示，本方法在保持生成质量的同时，将用户总交互时间降低近50%。代码已开源：https://github.com/G-U-N/consolver。