AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization
This addresses the challenge of generating coherent images with multiple user-specified subjects for applications in creative design and content creation, representing a novel method for a known bottleneck.
The paper tackles the problem of multi-subject customization in image synthesis by balancing text alignment, subject identity preservation, and layout control without additional training, achieving state-of-the-art performance with support for complex compositions and scaling to more subjects.
Multi-subject customization aims to synthesize multiple user-specified subjects into a coherent image. To address issues such as subjects missing or conflicts, recent works incorporate layout guidance to provide explicit spatial constraints. However, existing methods still struggle to balance three critical objectives: text alignment, subject identity preservation, and layout control, while the reliance on additional training further limits their scalability and efficiency. In this paper, we present AnyMS, a novel training-free framework for layout-guided multi-subject customization. AnyMS leverages three input conditions: text prompt, subject images, and layout constraints, and introduces a bottom-up dual-level attention decoupling mechanism to harmonize their integration during generation. Specifically, global decoupling separates cross-attention between textual and visual conditions to ensure text alignment. Local decoupling confines each subject's attention to its designated area, which prevents subject conflicts and thus guarantees identity preservation and layout control. Moreover, AnyMS employs pre-trained image adapters to extract subject-specific features aligned with the diffusion model, removing the need for subject learning or adapter tuning. Extensive experiments demonstrate that AnyMS achieves state-of-the-art performance, supporting complex compositions and scaling to a larger number of subjects.