Presentation
B4M: Breaking Low-Rank Adapter for Making Content-Style Customization
DescriptionThis paper proposes a novel framework for personalized content-style fusion generation by training content and style in separated parameter space of low-rank adaptations for pre-trained text-to-image models. We introduce “partly learnable projection” (PLP) matrices and a “break-for-make” pipeline, achieving superior content-style alignment compared to state-of-the-art methods.
Authors
Technical Papers Fast Forward Presenter
Event Type
Technical Papers
TimeThursday, 18 December 20259:54am - 10:05am HKT
LocationMeeting Room S423+S424, Level 4