{"ID":2879043,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.16863","arxiv_id":"2508.16863","title":"Delta-SVD: Efficient Compression for Personalized Text-to-Image Models","abstract":"Personalized text-to-image models such as DreamBooth require fine-tuning large-scale diffusion backbones, resulting in significant storage overhead when maintaining many subject-specific models. We present Delta-SVD, a post-hoc, training-free compression method that targets the parameter weights update induced by DreamBooth fine-tuning. Our key observation is that these delta weights exhibit strong low-rank structure due to the sparse and localized nature of personalization. Delta-SVD first applies Singular Value Decomposition (SVD) to factorize the weight deltas, followed by an energy-based rank truncation strategy to balance compression efficiency and reconstruction fidelity. The resulting compressed models are fully plug-and-play and can be re-constructed on-the-fly during inference. Notably, the proposed approach is simple, efficient, and preserves the original model architecture. Experiments on a multiple subject dataset demonstrate that Delta-SVD achieves substantial compression with negligible loss in generation quality measured by CLIP score, SSIM and FID. Our method enables scalable and efficient deployment of personalized diffusion models, making it a practical solution for real-world applications that require storing and deploying large-scale subject customizations.","short_abstract":"Personalized text-to-image models such as DreamBooth require fine-tuning large-scale diffusion backbones, resulting in significant storage overhead when maintaining many subject-specific models. We present Delta-SVD, a post-hoc, training-free compression method that targets the parameter weights update induced by Dream...","url_abs":"https://arxiv.org/abs/2508.16863","url_pdf":"https://arxiv.org/pdf/2508.16863v1","authors":"[\"Tangyuan Zhang\",\"Shangyu Chen\",\"Qixiang Chen\",\"Jianfei Cai\"]","published":"2025-08-23T01:21:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}