Distilling Diffusion Models into Conditional GANs

arXiv:2405.05967v1 Announce Type: cross
Abstract: We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a paired image-to-image translation task, using noise-to-image pairs of the diffusion model's ODE trajectory. For efficient regression loss computation, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space, utilizing an ensemble of augmentations. Furthermore, we adapt a diffusion model to …

abstract arxiv cs.cv cs.gr cs.lg diffusion diffusion model diffusion models distillation gan gans image image-to-image image-to-image translation inference loss noise quality regression trajectory translation type while