Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
This work addresses the need for fine-grained spatial control in text-to-image generation for practical applications, offering an incremental improvement over existing methods.
The paper tackles the problem of precise layout composition in text-to-image generation by introducing RAG, a tuning-free method that decouples multi-region generation into hard binding and soft refinement, achieving superior performance in attribute binding and object relationships compared to previous tuning-free methods.
Regional prompting, or compositional generation, which enables fine-grained spatial control, has gained increasing attention for its practicality in real-world applications. However, previous methods either introduce additional trainable modules, thus only applicable to specific models, or manipulate on score maps within cross-attention layers using attention masks, resulting in limited control strength when the number of regions increases. To handle these limitations, we present RAG, a Regional-Aware text-to-image Generation method conditioned on regional descriptions for precise layout composition. RAG decouple the multi-region generation into two sub-tasks, the construction of individual region (Regional Hard Binding) that ensures the regional prompt is properly executed, and the overall detail refinement (Regional Soft Refinement) over regions that dismiss the visual boundaries and enhance adjacent interactions. Furthermore, RAG novelly makes repainting feasible, where users can modify specific unsatisfied regions in the last generation while keeping all other regions unchanged, without relying on additional inpainting models. Our approach is tuning-free and applicable to other frameworks as an enhancement to the prompt following property. Quantitative and qualitative experiments demonstrate that RAG achieves superior performance over attribute binding and object relationship than previous tuning-free methods.