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

arXiv: https://arxiv.org/abs/2508.02165 · HTML: https://mlsanity.com/paper/2508.02165/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Mixture of LoRA experts, one of 12 directions in Mixture-of-experts.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Placed in

- Mixture-of-experts / [Mixture of LoRA experts](https://mlsanity.com/moe/mixture-of-lora-experts/)

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://mlsanity.com/paper/2404.02948/) (2024)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [StyleDrop: Text-to-Image Generation in Any Style](https://mlsanity.com/paper/2306.00983/) (2023)
- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs](https://mlsanity.com/paper/2311.13600/) (2023)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [Localizing Object-level Shape Variations with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.11306/) (2023)
- [Implicit Style-Content Separation using B-LoRA](https://mlsanity.com/paper/2403.14572/) (2024)
- [Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks](https://mlsanity.com/paper/2110.08398/) (2021)
- [K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs](https://mlsanity.com/paper/2502.18461/) (2025)
- [ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation](https://mlsanity.com/paper/2312.02109/) (2023)

## Built on by (most cited first, 5 of 5)

- [Spanning the Visual Analogy Space with a Weight Basis of LoRAs](https://mlsanity.com/paper/2602.15727/) (2026)
- [NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion](https://mlsanity.com/paper/2511.11051/) (2025)
- [Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models](https://mlsanity.com/paper/2604.10095/) (2026)
- [Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting](https://mlsanity.com/paper/2606.03792/) (2026)
- [LoRA-Diffusion: Parameter-Efficient Fine-Tuning via Low-Rank Trajectory Decomposition](https://mlsanity.com/paper/2608.12328/) (2026)

## Abstract (arXiv)

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: underlineEnergy of matrix, underlineStyle discrepancy scores and underlineTime 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.