RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
This addresses a key bottleneck in text-to-image generation for applications requiring complex scene composition, though it is incremental as it builds on existing models without new training.
The paper tackles the problem of generating realistic and compositionally accurate images from text prompts involving multiple objects by proposing RealCompo, a training-free framework that balances text-to-image and spatial-aware diffusion models. The result shows consistent outperformance over state-of-the-art models in multiple-object compositional generation while maintaining realism and compositionality.
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