不需训练，用修正算法提速图像生成，低步数下效果更好
CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth
- 将采样过程转换到统一校正坐标系，用多步预测+历史速度修正
- 6-20次函数评估下显著提升图像质量，优于多数现有方法
- 适合追求高效生成的开发者，尤其适用于低计算资源场景
流模型和扩散模型能生成高保真、高分辨率图像，但采样时通常需要大量函数评估（NFE）。现有加速方法要么需通过蒸馏额外训练，要么依赖无训练的高阶求解器，两者在低NFE预算下都会降低样本质量。我们提出CAB（Corrected Adams-Bashforth），一种无需训练的采样器，可加速两类模型。CAB首先将采样动态转换至统一的校正坐标系，再使用基于历史速度评估的简单修正项增强多步Adams-Bashforth预测器，不增加额外NFE。该方法结构简单，跨模型形式一致，具有至少三阶局部截断误差和二阶全局误差。在预训练流模型与扩散模型（包括类别条件与大规模文本到图像基准）上的实验表明，CAB在6-20 NFE的低步数区间显著改善了质量与NFE的权衡。在更高步数下，也保持与强训练自由采样器相当的竞争力。官方代码已开源：https://github.com/Anuska-Roy/CAB。
原文摘要 · Abstract (English)
Flow and diffusion models achieve high-fidelity, high-resolution image synthesis, but often require many function evaluations (NFEs) at sampling time. Existing acceleration methods either require additional training through distillation or rely on training-free high-order solvers, and both can degrade sample quality at low NFE budgets. We propose CAB (Corrected Adams-Bashforth), a training-free sampler that accelerates both flow and diffusion models. CAB first transforms the sampling dynamics to a common rectified coordinate system, and then applies a multistep Adams-Bashforth predictor augmented with a simple correction term based on past velocity evaluations and therefore incurs no additional NFEs. The resulting method is simple, has the same algorithmic form across model classes, and has at least third-order local truncation error and second-order global error. Experiments on pretrained flow and diffusion models, including class-conditional and large-scale text-to-image benchmarks, show that CAB improves quality-NFE trade-offs in the low-step regime of 6-20 NFEs. It also remains competitive with strong training-free samplers at higher step counts across most tested models. The official implementation is available at https://github.com/Anuska-Roy/CAB.
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。