Bidirectional Consistency Models

arXiv:2403.18035v1 Announce Type: new
Abstract: Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE). Interestingly, DMs can also invert an input image to noise by moving backward along the PF ODE, a key operation for downstream tasks such as interpolation and image editing. However, the iterative nature of this process restricts its speed, hindering its broader application. Recently, …

abstract arxiv cs.cv cs.lg denoising differential differential equation diffusion diffusion models equation flow image key moving noise ordinary probability process quality random samples type vector