Relational Diffusion Distillation for Efficient Image Generation

TL;DR

This paper introduces Relational Diffusion Distillation (RDD), a novel method that improves the efficiency of diffusion models for image generation by transferring knowledge more effectively, enabling high-quality results with minimal sampling steps.

Contribution

The paper proposes RDD, a new distillation approach that incorporates cross-sample relationships, significantly enhancing diffusion model performance at low sampling steps.

Findings

Achieves 1.47 FID reduction with 1 sampling step.

Enables 256x faster inference compared to DDIM.

Outperforms existing diffusion distillation methods.

Abstract

Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling methods have been proposed to reduce the number of sampling steps required for diffusion models. However, they perform poorly under a very small number of sampling steps. Thanks to the emergence of knowledge distillation technology, the existing training scheme methods have achieved excellent results at very low step numbers. However, the current methods mainly focus on designing novel diffusion model sampling methods with knowledge distillation. How to transfer better diffusion knowledge from teacher models is a more valuable problem but rarely studied. Therefore, we propose Relational Diffusion Distillation (RDD), a novel distillation method tailored specifically for distilling diffusion models. Unlike existing methods that simply align teacher and student models at pixel level or feature distributions, our method introduces cross-sample relationship interaction during the distillation process and alleviates the memory constraints induced by multiple sample interactions. Our RDD significantly enhances the effectiveness of the progressive distillation framework within the diffusion model. Extensive experiments on several datasets (e.g., CIFAR-10 and ImageNet) demonstrate that our proposed RDD leads to 1.47 FID decrease under 1 sampling step compared to state-of-the-art diffusion distillation methods and achieving 256x speed-up compared to DDIM strategy. Code is available at https://github.com/cantbebetter2/RDD.