Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

arXiv:2403.08381v1 Announce Type: new
Abstract: Most diffusion models assume that the reverse process adheres to a Gaussian distribution. However, this approximation has not been rigorously validated, especially at singularities, where t=0 and t=1. Improperly dealing with such singularities leads to an average brightness issue in applications, and limits the generation of images with extreme brightness or darkness. We primarily focus on tackling singularities from both theoretical and practical perspectives. Initially, we establish the error bounds for the reverse process approximation, …

arxiv cs.cv diffusion diffusion models endpoints type