混合展示：用于扩散模型的多概念定制的分散式低秩适应

摘要

公开的大规模文本到图像扩散模型，如稳定扩散，已经引起了社区的广泛关注。这些模型可以通过低秩适应（LoRAs）轻松定制新概念。然而，利用多个概念LoRAs来共同支持多个定制概念提出了挑战。我们将这种情况称为分散式多概念定制，涉及单客户概念调整和中心节点概念融合。在本文中，我们提出了一个名为Mix-of-Show的新框架，解决了分散式多概念定制的挑战，包括由现有单客户LoRA调整引起的概念冲突和模型融合过程中的身份丢失。Mix-of-Show采用嵌入分解LoRA（ED-LoRA）进行单客户调整，采用梯度融合进行中心节点以保留单个概念的领域本质，并支持理论上无限的概念融合。此外，我们引入了区域可控采样，将空间可控采样（例如ControlNet和T2I-Adaptor）扩展到多概念采样中，以解决属性绑定和缺失对象问题。大量实验证明Mix-of-Show能够以高保真度组合多个定制概念，包括字符、物体和场景。

English

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.

混合展示：用于扩散模型的多概念定制的分散式低秩适应

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

摘要

Support