Break-for-Make: Modular Low-Rank Adaptations for Composable Content-Style Customization

arXiv:2403.19456v1 Announce Type: new
Abstract: Personalized generation paradigms empower designers to customize visual intellectual properties with the help of textual descriptions by tuning or adapting pre-trained text-to-image models on a few images. Recent works explore approaches for concurrently customizing both content and detailed visual style appearance. However, these existing approaches often generate images where the content and style are entangled. In this study, we reconsider the customization of content and style concepts from the perspective of parameter space construction. Unlike …

abstract arxiv cs.cv cs.gr cs.mm customization designers explore generate however image images low modular personalized style text text-to-image textual type visual