# 免训练多概念LoRA组合：提示词感知加权策略

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-02 08:00
- AIHOT 分数：64
- AIHOT 链接：https://aihot.virxact.com/items/cmpzjq2v8045islkpt9zbifmm
- 原文链接：https://arxiv.org/abs/2606.03792

## AI 摘要

LoRA可个性化文生图模型，但多概念组合时直接叠加会干扰概念，降低质量与保真度。本文提出免训练方法，通过W-Switch与W-Composite两种策略，根据目标提示词中触发token的语义重要性对每个LoRA模块输出加权组合，实现多概念自定义。同时提出基于真实参考图像与自动分割概念区域的图像相似度评估框架。在ComposLoRA测试集上，该方法在视觉质量、身份保持和组合性上一致超越现有方法。LLM评估与用户研究验证有效性。代码已开源。

## 正文

Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual concepts and styles. However, extending such models to multi-concept customization remains challenging. Naively combining multiple LoRA weights or their outputs often leads to interference among concepts, resulting in degraded visual quality and reduced fidelity to the reference images of individual concepts. This paper proposes a simple yet effective approach for multi-concept customization by optimally combining the outputs of multiple LoRA modules. We leverage the relative importance of each concept during generation, as inferred from its corresponding prompt tokens and introduce two methods, W-Switch and W-Composite, that employ a prompt-aware importance weighting strategy in which each LoRA is weighted according to the semantic influence of its trigger words in the target prompt. In addition, we extend existing quantitative evaluation metrics by proposing a new image-based similarity evaluation framework that assesses image fidelity and identity preservation through comparisons between real-world reference images and automatically segmented concept regions from generated images. We evaluate our approach on the ComposLoRA testbed and demonstrate consistent improvements over existing state-of-the-art methods in terms of visual quality, identity preservation and compositionality. Qualitative evaluations, including a Large Language Model (LLM) based assessment and a user study, further validate the effectiveness of the proposed methods and align with the newly introduced quantitative image-based metrics. Our code is available at https://github.com/GeorgeTsoumplekas/Prompt-Aware-Multi-LoRA-Composition.