AI RESEARCH
CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models
arXiv CS.AI
•
ArXi:2507.13984v2 Announce Type: replace-cross Disentangling content and style from a single image, known as content-style decomposition (CSD), enables recontextualization of extracted content and stylization of extracted styles, offering greater creative flexibility in visual synthesis. While recent personalization methods have explored the decomposition of explicit content style, they remain tailored for diffusion models.