Subject or Style: Adaptive and Training-Free Mixture of LoRAs

• URL: http://arxiv.org/abs/2508.02165v1
• Date: Mon, 04 Aug 2025 08:05:18 GMT
• Title: Subject or Style: Adaptive and Training-Free Mixture of LoRAs
• Authors: Jia-Chen Zhang, Yu-Jie Xiong,
• Abstract summary: EST-LoRA is a training-free adaptive LoRA fusion method.<n>It considers three critical factors: underlineEnergy of matrix, underlineStyle discrepancy scores and underlineTime steps.<n>It outperforms state-of-the-art methods in both qualitative and quantitative evaluations.
• Score: 3.8443430569753025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning models via Low-Rank Adaptation (LoRA) demonstrates remarkable performance in subject-driven or style-driven generation tasks. Studies have explored combinations of different LoRAs to jointly generate learned styles and content. However, current methods struggle to balance the original subject and style, and often require additional training. Recently, K-LoRA proposed a training-free LoRA fusion method. But it involves multiple hyperparameters, making it difficult to adapt to all styles and subjects. In this paper, we propose EST-LoRA, a training-free adaptive LoRA fusion method. It comprehensively considers three critical factors: \underline{E}nergy of matrix, \underline{S}tyle discrepancy scores and \underline{T}ime steps. Analogous to the Mixture of Experts (MoE) architecture, the model adaptively selects between subject LoRA and style LoRA within each attention layer. This integrated selection mechanism ensures balanced contributions from both components during the generation process. Experimental results show that EST-LoRA outperforms state-of-the-art methods in both qualitative and quantitative evaluations and achieves faster generation speed compared to other efficient fusion approaches. Our code is publicly available at: https://anonymous.4open.science/r/EST-LoRA-F318.

Related papers

• K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs [25.998945090549874]
  We argue that the intrinsic properties of LoRA can effectively guide diffusion models in merging learned subject and style.<n>In each attention layer, K-LoRA compares the Top-K elements in each LoRA to be fused, determining which LoRA to select for optimal fusion.<n> Experimental results demonstrate that the proposed method effectively integrates the subject and style information learned by the original LoRAs.
  arXiv  Detail & Related papers  (2025-02-25T18:59:12Z)
• A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models [22.457766373989365]
  Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation.<n>To address the limited expressive capacity of LoRA, the Mixture-of-Expert (MoE) has been introduced for incorporating multiple LoRA adapters.<n>We propose a new training strategy for MoE-LoRA, to stabilize and boost its feature learning procedure by multi-space projections.
  arXiv  Detail & Related papers  (2025-02-20T05:58:53Z)
• BeamLoRA: Beam-Constraint Low-Rank Adaptation [51.52097743781401]
  Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.<n>We propose BeamLoRA, which conceptualizes each LoRA module as a beam where each rank naturally corresponds to a potential sub-solution.
  arXiv  Detail & Related papers  (2025-02-19T10:33:22Z)
• Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning [53.053604713064544]
  Low-Rank Adaptation (LoRA) is widely used for adapting large language models (LLMs) to specific domains due to its efficiency and modularity.<n>Recent works adopt Mixture of Experts (MoE) by treating each LoRA module as an expert, thereby mitigating task interference through multiple specialized LoRA modules.<n>While effective, these methods often isolate knowledge within individual tasks, failing to fully exploit the shared knowledge across related tasks.<n>We propose Single-ranked Mixture of Experts LoRA (textbfSMoRA), which embeds MoE into LoRA by textittreating each rank as an
  arXiv  Detail & Related papers  (2025-01-25T06:56:39Z)
• CopRA: A Progressive LoRA Training Strategy [9.847045610578073]
  Low-Rank Adaptation (LoRA) is a parameter-efficient technique for fine-tuning foundation models. In this work, we propose a novel progressive training strategy for LoRA with random layer dropping. We refer to this method as Cooperative LoRA (CopRA)
  arXiv  Detail & Related papers  (2024-10-30T11:07:09Z)
• AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality [31.830108790753172]
  Low-Rank Adaptation (LoRA) is known to enhance training efficiency in Large Language Models (LLMs) Recent studies seek to combine LoRA with Mixture-of-Experts (MoE) to boost performance across various tasks. We introduce AlphaLoRA, a theoretically principled and training-free method for allocating LoRA experts to further redundancy.
  arXiv  Detail & Related papers  (2024-10-14T00:43:02Z)
• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• Mixture of LoRA Experts [87.50120181861362]
  This paper introduces the Mixture of LoRA Experts (MoLE) approach, which harnesses hierarchical control and unfettered branch selection. The MoLE approach achieves superior LoRA fusion performance in comparison to direct arithmetic merging.
  arXiv  Detail & Related papers  (2024-04-21T11:59:53Z)
• Multi-LoRA Composition for Image Generation [107.83002438126832]
  We study multi-LoRA composition through a decoding-centric perspective. We present two training-free methods: LoRA Switch, which alternates between different LoRAs at each denoising step, and LoRA Composite, which simultaneously incorporates all LoRAs to guide more cohesive image synthesis.
  arXiv  Detail & Related papers  (2024-02-26T18:59:18Z)
• ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs [56.85106417530364]
  Low-rank adaptations (LoRA) have been proposed as a parameter-efficient way of achieving concept-driven personalization. We propose ZipLoRA, a method to cheaply and effectively merge independently trained style and subject LoRAs. Experiments show that ZipLoRA can generate compelling results with meaningful improvements over baselines in subject and style fidelity.
  arXiv  Detail & Related papers  (2023-11-22T18:59:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.