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。