On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization
Abstract
The emergence of various notions of "consistency" in diffusion models has garnered considerable attention and helped achieve improved sample quality, likelihood estimation, and accelerated sampling. Although similar concepts have been proposed in the literature, the precise relationships among them remain unclear. In this study, we establish theoretical connections between three recent "consistency" notions designed to enhance diffusion models for distinct objectives. Our insights offer the potential for a more comprehensive and encompassing framework for consistency-type models.
Cite
Text
Lai et al. "On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization." ICML 2023 Workshops: SPIGM, 2023.Markdown
[Lai et al. "On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization." ICML 2023 Workshops: SPIGM, 2023.](https://mlanthology.org/icmlw/2023/lai2023icmlw-equivalence/)BibTeX
@inproceedings{lai2023icmlw-equivalence,
title = {{On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization}},
author = {Lai, Chieh-Hsin and Takida, Yuhta and Uesaka, Toshimitsu and Murata, Naoki and Mitsufuji, Yuki and Ermon, Stefano},
booktitle = {ICML 2023 Workshops: SPIGM},
year = {2023},
url = {https://mlanthology.org/icmlw/2023/lai2023icmlw-equivalence/}
}