提出一种无需额外计算的流模型引导方法，提升生成图像质量与多样性。
Momentum Guidance: Plug-and-Play Guidance for Flow Models
- 通过追踪速度动量优化生成路径，不增加计算成本。
- 在ImageNet-256上，无CFG时FID降低36.54%，16步采样达1.553。
- 适用于大模型如Stable Diffusion 3，兼顾精度与多样性。
基于流的生成方法在高保真生成中表现优异，但预训练流模型在原始条件形式下很少被使用：图像生成时无引导的样本常显得模糊且缺乏细节。现有引导技术如无分类器引导（CFG）虽提升保真度，却降低了样本多样性。本文提出动量引导（Momentum Guidance, MG），通过沿微分方程轨迹外推当前速度，远离过去速度的指数移动平均，从而提升样本质量，同时保持每步仅一次评估的开销。MG在多个基准测试中均优于CFG，显著改善精确率-召回率帕累托前沿。在ImageNet-256上，无CFG时平均FID降低36.54%，有CFG时降低25.42%；在16步采样下达到FID 1.553。对Stable Diffusion 3和FLUX.1-dev等大型流模型的评估也证实了其在标准指标上的持续改进。
原文摘要 · Abstract (English)
Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in image generation, samples without guidance often appear diffuse and lack fine-grained detail. Existing guidance techniques such as classifier-free guidance (CFG) improve fidelity but reduce sample diversity. We introduce Momentum Guidance (MG), a guidance method that improves sample quality by extrapolating the current velocity away from an exponential moving average of past velocities along the ODE trajectory, while preserving the standard one-evaluation-per-step cost. MG provides gains beyond CFG, improving the precision-recall Pareto frontier. Experiments demonstrate the effectiveness of MG across benchmarks. On ImageNet-256, MG improves FID by 36.54% without CFG and 25.42% with CFG on average across sampling settings, attaining an FID of 1.553 at 16 sampling steps. Evaluations on large flow-based models, including Stable Diffusion 3 and FLUX.1-dev, further confirm improvements across standard metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。