{"ID":2846576,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01355","arxiv_id":"2511.01355","title":"Expanding the Content-Style Frontier: a Balanced Subspace Blending Approach for Content-Style LoRA Fusion","abstract":"Recent advancements in text-to-image diffusion models have significantly improved the personalization and stylization of generated images. However, previous studies have only assessed content similarity under a single style intensity. In our experiments, we observe that increasing style intensity leads to a significant loss of content features, resulting in a suboptimal content-style frontier. To address this, we propose a novel approach to expand the content-style frontier by leveraging Content-Style Subspace Blending and a Content-Style Balance loss. Our method improves content similarity across varying style intensities, significantly broadening the content-style frontier. Extensive experiments demonstrate that our approach outperforms existing techniques in both qualitative and quantitative evaluations, achieving superior content-style trade-off with significantly lower Inverted Generational Distance (IGD) and Generational Distance (GD) scores compared to current methods.","short_abstract":"Recent advancements in text-to-image diffusion models have significantly improved the personalization and stylization of generated images. However, previous studies have only assessed content similarity under a single style intensity. In our experiments, we observe that increasing style intensity leads to a significant...","url_abs":"https://arxiv.org/abs/2511.01355","url_pdf":"https://arxiv.org/pdf/2511.01355v1","authors":"[\"Linhao Huang\"]","published":"2025-11-03T09:03:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"LoRA\"]","has_code":false}