Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

TL;DR

This survey comprehensively reviews the principles and practices behind efficient diffusion models, emphasizing architecture, training, inference, and deployment to facilitate understanding and application in various generative tasks.

Contribution

It provides an efficiency-oriented perspective on diffusion models, summarizing recent advances in design principles and practical methodologies for improved performance.

Findings

Highlights the importance of architecture design in diffusion models

Summarizes efficient training and inference techniques

Provides guidance for deploying diffusion models in real-world scenarios

Abstract

As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis, video generation, molecule design, 3D scene rendering and multimodal generation, relying on their dense theoretical principles and reliable application practices. The remarkable success of these recent efforts on diffusion models comes largely from progressive design principles and efficient architecture, training, inference, and deployment methodologies. However, there has not been a comprehensive and in-depth review to summarize these principles and practices to help the rapid understanding and application of diffusion models. In this survey, we provide a new efficiency-oriented perspective on these existing efforts, which mainly focuses on the profound principles and efficient practices in architecture designs, model training, fast inference and reliable deployment, to guide further theoretical research, algorithm migration and model application for new scenarios in a reader-friendly way. \url{https://github.com/ponyzym/Efficient-DMs-Survey}