Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance

arXiv:2405.01356v1 Announce Type: new
Abstract: In subject-driven text-to-image synthesis, the synthesis process tends to be heavily influenced by the reference images provided by users, often overlooking crucial attributes detailed in the text prompt. In this work, we propose Subject-Agnostic Guidance (SAG), a simple yet effective solution to remedy the problem. We show that through constructing a subject-agnostic condition and applying our proposed dual classifier-free guidance, one could obtain outputs consistent with both the given subject and input text prompts. We …

abstract arxiv cs.cv guidance image images improving process prompt reference sag show simple solution synthesis text text-to-image type work