This paper concerns the structure of learned representations in text-guided generative models, focusing on score-based models. A key property of such models is that they can compose disparate concepts in a `disentangled' manner. This suggests these models have internal representations that encode concepts in a `disentangled' manner. Here, we focus on the idea that concepts are encoded as subspaces of some representation space. We formalize what this means, show there's a natural choice for the representation, and develop a simple method for identifying the part of the representation corresponding to a given concept. In particular, this allows us to manipulate the concepts expressed by the model through algebraic manipulation of the representation. We demonstrate the idea with examples using Stable Diffusion.

翻译：本文关注文本引导生成模型中学习表示的内部结构，重点研究基于分数的模型。此类模型的一个关键特性是能够以"解耦"方式组合不同概念，这表明其内部表示以"解耦"方式编码概念。我们聚焦于"概念被编码为表示空间的子空间"这一思想，形式化其定义，证明存在对表示的自然选择，并开发一种简单方法用于识别与给定概念对应的表示部分。该方法使我们能够通过对表示进行代数运算来操纵模型所表达的概念。我们通过Stable Diffusion的实例演示了这一思想。