Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models

ArXi:2605.23275v1 Announce Type: new In this paper, we propose Diffusion Domain Expansion (DDE), a method that efficiently extends pre-trained diffusion models to generate larger objects and handle complex conditioning beyond their original capabilities. Our method employs a compact trainable network designed to coordinate the denoised outputs of pre-trained diffusion models. We nstrate that the coordinator can be universally simple while being capable of generalizing to domains larger than those observed during its.