AI RESEARCH

MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics

arXiv CS.CV

ArXi:2603.21136v1 Announce Type: new Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with multiple distinct subjects while maintaining fine-grained control over their interactions remains challenging. Existing methods often struggle to provide explicit user-defined control over the compositional structure and precise spatial relationships between subjects. To address this, we