RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models

TL;DR

RealCompo is a training-free framework that dynamically balances existing text-to-image and spatial-aware diffusion models to improve multi-object compositional generation while maintaining realism.

Contribution

It introduces a novel balancer mechanism that enables plug-and-play integration of models, enhancing compositionality without additional training.

Findings

Outperforms state-of-the-art models in multi-object compositional tasks

Maintains high realism and compositionality in generated images

Seamlessly extends to various spatial-aware diffusion models

Abstract

Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositional generation. In this paper, we propose RealCompo, a new training-free and transferred-friendly text-to-image generation framework, which aims to leverage the respective advantages of text-to-image models and spatial-aware image diffusion models (e.g., layout, keypoints and segmentation maps) to enhance both realism and compositionality of the generated images. An intuitive and novel balancer is proposed to dynamically balance the strengths of the two models in denoising process, allowing plug-and-play use of any model without extra training. Extensive experiments show that our RealCompo consistently outperforms state-of-the-art text-to-image models and spatial-aware image diffusion models in multiple-object compositional generation while keeping satisfactory realism and compositionality of the generated images. Notably, our RealCompo can be seamlessly extended with a wide range of spatial-aware image diffusion models and stylized diffusion models. Our code is available at: https://github.com/YangLing0818/RealCompo