Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a Low-Rank Adaptations (LoRA) fusion matrix of multiple LoRA to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, which occurs when the model cannot preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through Concept Injection Constraints, enhancing concept visibility via an expanded cross-attention mechanism. To combat concept confusion, Concept Isolation Constraints are introduced, refining the self-attention computation. Furthermore, Latent Re-initialization is proposed to effectively stimulate concept-specific latent within designated regions. Our extensive testing showcases a notable enhancement in LoRA-Composer's performance compared to standard baselines, especially when eliminating the image-based conditions like canny edge or pose estimations. Code is released at https://github.com/Young98CN/LoRA\_Composer.

翻译：定制化生成技术已在不同上下文中显著推进了特定概念的合成。多概念定制成为该领域中极具挑战性的任务。现有方法通常依赖训练多个低秩适配（LoRA）的融合矩阵，以将不同概念合并至单张图像中。然而，我们发现这种直接方法面临两大挑战：1）概念混淆——模型无法保留各概念的独特特征；2）概念消失——模型无法生成预期主体。为解决这些问题，我们提出LoRA-Composer，一种无训练框架，旨在无缝集成多个LoRA，从而增强生成图像中不同概念间的和谐性。LoRA-Composer通过概念注入约束解决概念消失问题，借助扩展的交叉注意力机制提升概念可见性；针对概念混淆，引入概念隔离约束以优化自注意力计算。此外，提出潜在表征重新初始化方法，有效激发指定区域内的概念特定潜在特征。大量实验表明，与标准基线相比，LoRA-Composer性能显著提升，尤其在消除边缘检测或姿态估计等图像条件时。代码已开源至https://github.com/Young98CN/LoRA_Composer。