2 papers
cs.CV2026
CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets
Jihun Park, Kyoungmin Lee, Jongmin Gim +6
Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for mode…
cs.CV2026
Setting the Stage: Text-Driven Scene-Consistent Image Generation
Cong Xie, Che Wang, Yan Zhang +4
We focus on the foundational task of Scene Staging: given a reference scene image and a text condition specifying an actor category to be generated in the scene and its spatial rel…