MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DV7PNE2Rrecord.jsonopen to challenge →
read the original abstract
Current multi-subject customization approaches encounter two critical challenges: the difficulty in acquiring diverse multi-subject training data, and attribute entanglement across different subjects. To bridge these gaps, we propose MUSAR - a simple yet effective framework to achieve robust multi-subject customization while requiring only single-subject training data. Firstly, to break the data limitation, we introduce debiased diptych learning. It constructs diptych training pairs from single-subject images to facilitate multi-subject learning, while actively correcting the distribution bias introduced by diptych construction via static attention routing and dual-branch LoRA. Secondly, to eliminate cross-subject entanglement, we introduce dynamic attention routing mechanism, which adaptively establishes bijective mappings between generated images and conditional subjects. This design not only achieves decoupling of multi-subject representations but also maintains scalable generalization performance with increasing reference subjects. Comprehensive experiments demonstrate that our MUSAR outperforms existing methods - even those trained on multi-subject dataset - in image quality, subject consistency, and interaction naturalness, despite requiring only single-subject dataset.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.
-
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation
DomainShuttle introduces domain-aware modeling and token separation techniques to achieve high subject fidelity with generative flexibility in open-domain subject-driven text-to-video tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.