{"ID":2831280,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.08785","arxiv_id":"2512.08785","title":"LoFA: Learning to Predict Personalized Priors for Fast Adaptation of Visual Generative Models","abstract":"Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization. While a few hypernetwork-based approaches attempt to predict adaptation weights directly, they struggle to map fine-grained user prompts to complex LoRA distributions, limiting their practical applicability. To bridge this gap, we propose LoFA, a general framework that efficiently predicts personalized priors for fast model adaptation. We first identify a key property of LoRA: structured distribution patterns emerge in the relative changes between LoRA and base model parameters. Building on this, we design a two-stage hypernetwork: first predicting relative distribution patterns that capture key adaptation regions, then using these to guide final LoRA weight prediction. Extensive experiments demonstrate that our method consistently predicts high-quality personalized priors within seconds, across multiple tasks and user prompts, even outperforming conventional LoRA that requires hours of processing. Project page: https://jaeger416.github.io/lofa/.","short_abstract":"Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization. While a few hypernetwork-based approaches attempt to predict adaptation weights...","url_abs":"https://arxiv.org/abs/2512.08785","url_pdf":"https://arxiv.org/pdf/2512.08785v1","authors":"[\"Yiming Hao\",\"Mutian Xu\",\"Chongjie Ye\",\"Jie Qin\",\"Shunlin Lu\",\"Yipeng Qin\",\"Xiaoguang Han\"]","published":"2025-12-09T16:39:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"LoRA\"]","has_code":false}