Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models

TL;DR

This paper introduces a flexible, plug-and-play diffusion model framework that synthesizes images satisfying multiple constraints without retraining, leveraging closed-form solutions and a novel reliability parameter for multi-modal content creation.

Contribution

It proposes a novel sampling strategy for combining multiple diffusion models trained on different tasks, enabling multi-modal synthesis without retraining or paired data.

Findings

Effective multi-constraint image generation demonstrated

Outperforms existing methods on standard multimodal tasks

Flexible use of off-the-shelf diffusion models during sampling

Abstract

Generating photos satisfying multiple constraints find broad utility in the content creation industry. A key hurdle to accomplishing this task is the need for paired data consisting of all modalities (i.e., constraints) and their corresponding output. Moreover, existing methods need retraining using paired data across all modalities to introduce a new condition. This paper proposes a solution to this problem based on denoising diffusion probabilistic models (DDPMs). Our motivation for choosing diffusion models over other generative models comes from the flexible internal structure of diffusion models. Since each sampling step in the DDPM follows a Gaussian distribution, we show that there exists a closed-form solution for generating an image given various constraints. Our method can unite multiple diffusion models trained on multiple sub-tasks and conquer the combined task through our proposed sampling strategy. We also introduce a novel reliability parameter that allows using different off-the-shelf diffusion models trained across various datasets during sampling time alone to guide it to the desired outcome satisfying multiple constraints. We perform experiments on various standard multimodal tasks to demonstrate the effectiveness of our approach. More details can be found in https://nithin-gk.github.io/projectpages/Multidiff/index.html