UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation
Researchers have introduced UniCustom, a novel framework designed to enhance multi-reference image generation by unifying visual conditioning. This approach integrates semantic and appearance-rich features before encoding, allowing models to better associate subjects with their specific visual details from reference images. UniCustom employs a two-stage training strategy and a slot-wise binding regularization to improve subject consistency and reduce attribute leakage, demonstrating superior performance on relevant benchmarks. AI
IMPACT Enhances multi-reference image generation by improving subject consistency and reducing attribute leakage.