LoFA: Learning to Predict Personalized Prior for Fast Adaptation of Visual Generative Models

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: jaeger416.github.io/lofa.