Improved denoising diffusion probabilistic models with efficient non-diagonal covariance modeling
Rui XiaAyan DasArtem ArtemevAndy ZhangGuillaume HennequinAlberto Bernacchia
Paper Abstract The sampling process of Denoising Diffusion Probabilistic Models (DDPMs) can be accelerated by leveraging second-order information in the form of approximations to the denoising posterior covariance – allowing samples of acceptable quality to be produced in fewer but larger...