Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

arXiv:2606.14756v1 Announce Type: cross Abstract: The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models during sampling. Much like managing a specialized workforce, our method creates a fair but efficient division of labor across models. Central to our m