Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text representation is unknown. We propose the Diffusion Lens, a method for analyzing the text encoder of T2I models by generating images from its intermediate representations. Using the Diffusion Lens, we perform an extensive analysis of two recent T2I models. Exploring compound prompts, we find that complex scenes describing multiple objects are composed progressively and more slowly compared to simple scenes; Exploring knowledge retrieval, we find that representation of uncommon concepts requires further computation compared to common concepts, and that knowledge retrieval is gradual across layers. Overall, our findings provide valuable insights into the text encoder component in T2I pipelines.

我们提出了扩散镜，一种用于分析T2I模型中的文本编码器的方法，通过从其中间表示生成图像。通过扩散镜，我们对两个最近的T2I模型进行了广泛分析。我们发现，描述多个对象的复杂场景相对简单的场景被逐步且更慢地生成；我们还发现，表示不常见概念需要更多计算，并且知识检索在各层之间逐步进行。总的来说，我们的研究结果为T2I流程中的文本编码器组件提供了有价值的见解。

扩散镜：在文本到图像处理过程中解释文本编码器