Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914974482300928 |
|---|---|
| author | Ma, Zhiyuan Zhang, Yuzhu Jia, Guoli Zhao, Liangliang Ma, Yichao Ma, Mingjie Liu, Gaofeng Zhang, Kaiyan Li, Jianjun Zhou, Bowen |
| author_facet | Ma, Zhiyuan Zhang, Yuzhu Jia, Guoli Zhao, Liangliang Ma, Yichao Ma, Mingjie Liu, Gaofeng Zhang, Kaiyan Li, Jianjun Zhou, Bowen |
| contents | 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} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices Ma, Zhiyuan Zhang, Yuzhu Jia, Guoli Zhao, Liangliang Ma, Yichao Ma, Mingjie Liu, Gaofeng Zhang, Kaiyan Li, Jianjun Zhou, Bowen Computer Vision and Pattern Recognition I.4.9 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} |
| title | Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices |
| topic | Computer Vision and Pattern Recognition I.4.9 |
| url | https://arxiv.org/abs/2410.11795 |