Personalized image generation allows users to preserve styles or subjects of a provided small set of images for further image generation. With the advancement in large text-to-image models, many techniques have been developed to efficiently fine-tune those models for personalization, such as Low Rank Adaptation (LoRA). However, LoRA-based methods often face the challenge of adjusting the rank parameter to achieve satisfactory results. To address this challenge, AutoComponent-LoRA (AC-LoRA) is proposed, which is able to automatically separate the signal component and noise component of the LoRA matrices for fast and efficient personalized artistic style image generation. This method is based on Singular Value Decomposition (SVD) and dynamic heuristics to update the hyperparameters during training. Superior performance over existing methods in overcoming model underfitting or overfitting problems is demonstrated. The results were validated using FID, CLIP, DINO, and ImageReward, achieving an average of 9% improvement.
View on arXiv@article{cui2025_2504.02231,
title={ AC-LoRA: Auto Component LoRA for Personalized Artistic Style Image Generation },
author={ Zhipu Cui and Andong Tian and Zhi Ying and Jialiang Lu },
journal={arXiv preprint arXiv:2504.02231},
year={ 2025 }
}