Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple concept LoRAs to jointly support multiple customized concepts presents a challenge. We refer to this scenario as decentralized multi-concept customization, which involves single-client concept tuning and center-node concept fusion. In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion. Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion. Additionally, we introduce regionally controllable sampling, which extends spatially controllable sampling (e.g., ControlNet and T2I-Adaptor) to address attribute binding and missing object problems in multi-concept sampling. Extensive experiments demonstrate that Mix-of-Show is capable of composing multiple customized concepts with high fidelity, including characters, objects, and scenes.

翻译：公开的大规模文本到图像扩散模型（如Stable Diffusion）已引起学界广泛关注。这类模型可通过低秩适配（LoRA）轻松定制新概念。然而，利用多个概念LoRA联合支持多个定制概念存在挑战。我们将此场景称为去中心化多概念定制，涉及单客户端概念调优和中心节点概念融合。本文提出名为Mix-of-Show的新框架，解决了去中心化多概念定制的难题，包括现有单客户端LoRA调优导致的概念冲突以及模型融合时的身份丢失问题。Mix-of-Show采用嵌入分解LoRA（ED-LoRA）进行单客户端调优，并通过中心节点梯度融合保留单一概念的域内本质，支持理论上无限的概念融合。此外，我们引入区域可控采样，拓展了空间可控采样（如ControlNet和T2I-Adaptor）的能力，解决了多概念采样中的属性绑定和对象缺失问题。大量实验表明，Mix-of-Show能够高保真地组合多个定制概念，包括角色、对象和场景。