用贝叶斯优化直接优化采样步数，显著提速图像生成且不损失质量。
Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization
- 将采样步数选择转化为黑箱优化问题，直接优化生成质量。
- 5步最优调度保留94%质量，推理成本降低10倍。
- 无需训练，适配各类模型和采样器，适合高效生成场景。
从扩散模型采样通常需要多次前向传播大型神经网络，生成计算开销大。尽管已有大量工作聚焦于高效求解器与采样器，但对采样时间步选择的关注较少。现有方法优化的是样本质量的理论代理指标，而非真实质量指标。本文提出优化你的采样（OYS），将时间步选择视为黑箱优化问题，直接使用贝叶斯优化优化目标质量指标。OYS在文本到图像生成中优于默认调度及Align Your Steps方案，在修复及其他图像任务上也优于默认调度，且在定量与人工评估中均表现更优。OYS无需额外训练，适用于压缩模型，可提升Euler、DPM-Solver++等简单与复杂采样器性能。5步的OYS调度可保留50步调度89%-94%的质量，同时将推理成本降低10倍。
原文摘要 · Abstract (English)
Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparatively little attention has been paid to selecting the sampling timesteps themselves. A recent line of work optimizes theoretically derived surrogates for sample quality rather than the quality metric itself. We propose Optimizing Your Sampling (OYS), which instead treats timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization. OYS outperforms both the default schedules and those of Align Your Steps on text-to-image generation, and improves over the default schedules on inpainting and other image tasks, in both quantitative and human evaluations. OYS requires no additional training, is applicable even to distilled models, and improves both simple and sophisticated samplers such as Euler and DPM-Solver++. A 5-step OYS schedule retains 89%-94% of the quality of a 50-step schedule while reducing inference cost by 10x.
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。