Efficient Diffusion Models: A Survey

TL;DR

This survey reviews recent advances in making diffusion models more efficient, addressing their high computational costs and long generation times to enable practical applications.

Contribution

It provides a comprehensive taxonomy of efficient diffusion model techniques across algorithm, system, and framework levels, serving as a valuable resource for researchers.

Findings

Organized literature into three main categories of efficiency techniques.

Created a GitHub repository for surveyed papers.

Highlighted key challenges and future directions in efficient diffusion models.

Abstract

Diffusion models have emerged as powerful generative models capable of producing high-quality contents such as images, videos, and audio, demonstrating their potential to revolutionize digital content creation. However, these capabilities come at the cost of their significant computational resources and lengthy generation time, underscoring the critical need to develop efficient techniques for practical deployment. In this survey, we provide a systematic and comprehensive review of research on efficient diffusion models. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient diffusion model topics from algorithm-level, system-level, and framework perspective, respectively. We have also created a GitHub repository where we organize the papers featured in this survey at https://github.com/AIoT-MLSys-Lab/Efficient-Diffusion-Model-Survey. We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of efficient diffusion model research and inspire them to contribute to this important and exciting field.