Efficient Diffusion Models: A Survey

2025-02-03

AI Summary

Diffusion models achieve high generation quality but suffer from substantial computational overhead and high inference latency, hindering practical deployment. This work presents a systematic survey of efficiency optimization techniques for diffusion models, introducing the first three-dimensional taxonomy—spanning algorithms, systems, and frameworks—that unifies key technical directions including model compression, sampling acceleration, and hardware-aware adaptation. Our contributions are: (1) a structured, extensible research roadmap for efficient diffusion models; and (2) an open-source, standardized literature repository alongside a dynamically updated GitHub knowledge base, enabling rigorous tracking of technical evolution and identification of deployment bottlenecks. This work provides both academia and industry with a reusable methodological framework and foundational infrastructure to advance efficient diffusion modeling.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

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.

Problem

• Optimize computational resources for diffusion models
• Reduce generation time in diffusion models
• Systematic review of efficient diffusion model techniques

Innovation

• Efficient diffusion models
• Algorithm-level optimization
• System-level framework enhancement