AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhiwen, Duan, Zhongjie, Chen, Die, Chen, Cen, Chen, Daoyuan, Li, Yaliang, Chen, Yingda
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909720571281408
author Li, Zhiwen
Duan, Zhongjie
Chen, Die
Chen, Cen
Chen, Daoyuan
Li, Yaliang
Chen, Yingda
author_facet Li, Zhiwen
Duan, Zhongjie
Chen, Die
Chen, Cen
Chen, Daoyuan
Li, Yaliang
Chen, Yingda
contents Despite recent advances in photorealistic image generation through large-scale models like FLUX and Stable Diffusion v3, the practical deployment of these architectures remains constrained by their inherent intractability to parameter fine-tuning. While low-rank adaptation (LoRA) have demonstrated efficacy in enabling model customization with minimal parameter overhead, the effective utilization of distributed open-source LoRA modules faces three critical challenges: sparse metadata annotation, the requirement for zero-shot adaptation capabilities, and suboptimal fusion strategies for multi-LoRA fusion strategies. To address these limitations, we introduce a novel framework that enables semantic-driven LoRA retrieval and dynamic aggregation through two key components: (1) weight encoding-base LoRA retriever that establishes a shared semantic space between LoRA parameter matrices and text prompts, eliminating dependence on original training data, and (2) fine-grained gated fusion mechanism that computes context-specific fusion weights across network layers and diffusion timesteps to optimally integrate multiple LoRA modules during generation. Our approach achieves significant improvement in image generation perfermance, thereby facilitating scalable and data-efficient enhancement of foundational models. This work establishes a critical bridge between the fragmented landscape of community-developed LoRAs and practical deployment requirements, enabling collaborative model evolution through standardized adapter integration.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02107
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation
Li, Zhiwen
Duan, Zhongjie
Chen, Die
Chen, Cen
Chen, Daoyuan
Li, Yaliang
Chen, Yingda
Computer Vision and Pattern Recognition
Despite recent advances in photorealistic image generation through large-scale models like FLUX and Stable Diffusion v3, the practical deployment of these architectures remains constrained by their inherent intractability to parameter fine-tuning. While low-rank adaptation (LoRA) have demonstrated efficacy in enabling model customization with minimal parameter overhead, the effective utilization of distributed open-source LoRA modules faces three critical challenges: sparse metadata annotation, the requirement for zero-shot adaptation capabilities, and suboptimal fusion strategies for multi-LoRA fusion strategies. To address these limitations, we introduce a novel framework that enables semantic-driven LoRA retrieval and dynamic aggregation through two key components: (1) weight encoding-base LoRA retriever that establishes a shared semantic space between LoRA parameter matrices and text prompts, eliminating dependence on original training data, and (2) fine-grained gated fusion mechanism that computes context-specific fusion weights across network layers and diffusion timesteps to optimally integrate multiple LoRA modules during generation. Our approach achieves significant improvement in image generation perfermance, thereby facilitating scalable and data-efficient enhancement of foundational models. This work establishes a critical bridge between the fragmented landscape of community-developed LoRAs and practical deployment requirements, enabling collaborative model evolution through standardized adapter integration.
title AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.02107