On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization
This work addresses a theoretical gap for researchers in diffusion models, but it is incremental as it clarifies existing concepts rather than introducing new methods.
The paper tackles the unclear relationships among different 'consistency' notions in diffusion models by establishing theoretical connections between three recent approaches, offering potential for a more comprehensive framework.
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.