Fixed Point Diffusion Models

Figure 1. Fixed Point Diffusion Model (FPDM) is a novel and highly efficient approach to image generation with diffusion models. FPDM integrates an implicit fixed point layer into a denoising diffusion model, converting the sampling process into a sequence of fixed point equations. Our model significantly decreases model size and memory usage while improving performance in settings with limited sampling time or computation. We compare our model, trained at a 256 ⇥ 256 resolution against the state-of-the-art DiT [38] on four datasets (FFHQ, CelebA-HQ, LSUN-Church, ImageNet) using compute equivalent to 20 DiT sampling steps. FPDM (right) demonstrates enhanced image quality with 87% fewer parameters and 60% less memory during training.