RayFlow：基于自适应流轨迹的实例感知扩散加速

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories

March 10, 2025

作者: Huiyang Shao, Xin Xia, Yuhong Yang, Yuxi Ren, Xing Wang, Xuefeng Xiao

cs.AI

摘要

扩散模型在多个领域取得了显著成功。然而，其生成速度缓慢仍是一个关键挑战。现有的加速方法虽然旨在减少采样步骤，但往往以牺牲样本质量、可控性或引入训练复杂性为代价。为此，我们提出了RayFlow，一种新颖的扩散框架，以解决这些局限。与以往方法不同，RayFlow引导每个样本沿着独特路径向实例特定的目标分布前进。该方法在最小化采样步骤的同时，保持了生成的多样性和稳定性。此外，我们引入了时间采样器（Time Sampler），一种重要性采样技术，通过聚焦于关键时间步来提升训练效率。大量实验表明，与现有加速技术相比，RayFlow在生成高质量图像方面具有更优的速度、控制性和训练效率。

English

Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality, controllability, or introduce training complexities. Therefore, we propose RayFlow, a novel diffusion framework that addresses these limitations. Unlike previous methods, RayFlow guides each sample along a unique path towards an instance-specific target distribution. This method minimizes sampling steps while preserving generation diversity and stability. Furthermore, we introduce Time Sampler, an importance sampling technique to enhance training efficiency by focusing on crucial timesteps. Extensive experiments demonstrate RayFlow's superiority in generating high-quality images with improved speed, control, and training efficiency compared to existing acceleration techniques.