Tuning-Free Image Customization with Image and Text Guidance

arXiv:2403.12658v1 Announce Type: new
Abstract: Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference image or text descriptions; and 3) time-consuming fine-tuning, which limits their practical application. In response, we introduce a tuning-free framework for simultaneous text-image-guided image customization, enabling precise editing of specific image regions within seconds. Our approach preserves the semantic features of the reference …

abstract application arxiv cs.cv current customization diffusion diffusion models fine-tuning free guidance image limitations practical reference text type