2 papers
cs.CV2026
Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation
Shuang Li, Chao Deng, Hang Chen +8
Subject-Driven Text-to-Image (T2I) Generation aims to preserve a subject's identity while editing its context based on a text prompt. A core challenge in this task is the "similari…
cs.CV2023
Domain-Controlled Prompt Learning
Qinglong Cao, Zhengqin Xu, Yuntian Chen +2
Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However,…