UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward Paper โข 2509.06818 โข Published Sep 8 โข 29 โข 2
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning Paper โข 2508.18966 โข Published Aug 26 โข 56 โข 2
DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning Paper โข 2504.14509 โข Published Apr 20 โข 50 โข 8
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation Paper โข 2504.02160 โข Published Apr 2 โข 37 โข 3