Efficient Diffusion Models: A Survey
Authors: Hui Shen, Jingxuan Zhang, Boning Xiong, Rui Hu, Shoufa Chen, Zhongwei Wan, Xin Wang, Yu Zhang, Zixuan Gong, Guangyin Bao, Chaofan Tao, Yongfeng Huang, Ye Yuan, Mi Zhang
TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this survey, we provide a systematic and comprehensive review of research on efficient diffusion models. |
| Researcher Affiliation | Academia | 1The Ohio State University 2Indiana University 3Fudan University 4Hangzhou City University 5The University of Hong Kong 6Tongji University 7The Chinese University of Hong Kong 8Peking University |
| Pseudocode | No | The paper is a survey reviewing existing research. It describes various techniques and algorithms conceptually and with mathematical formulations but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | No | We have also created a Git Hub repository where we organize the papers featured in this survey at https://github.com/AIoT-MLSys-Lab/Efficient-Diffusion-Model-Survey. We will actively maintain it and incorporate new research as it emerges. |
| Open Datasets | Yes | Table 1: Representative applications of diffusion models. Task Datasets Metrics Articles Image Generation Image Net, CIFAR, Met Face, Celeb A HQ, MS COCO, UCI, FFHQ, Diffusion DB, AFHQ, LSUN, SYSTEM-X, LAION |
| Dataset Splits | No | This paper is a survey of efficient diffusion models and does not present new experimental results or define dataset splits. |
| Hardware Specification | No | This paper is a survey reviewing existing research. It discusses hardware considerations for efficient diffusion models (Section 4.1) but does not report on specific hardware used for its own experimental work. |
| Software Dependencies | No | This paper is a survey of efficient diffusion models and does not present new experimental results that would require specific software dependencies for its own methodology. It discusses various frameworks and tools within the field but not its own implementation. |
| Experiment Setup | No | This paper is a survey of efficient diffusion models and does not describe an experimental setup or specific hyperparameters for its own research. |