Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion

We begin by evaluating T2I models' ability to innovate and generalize through controlled experiments, revealing that stable diffusion models can effectively recreate unseen elements with sufficiently diverse training data. Then, our key insight is that concepts and combinations of image elements the model is familiar with, and saw more during training, are more concisly represented in the model's latent space. We hence propose a method that leverages textual inversion to measure the originality of an image based on the number of tokens required for its reconstruction by the Figure 1: Illustration of our approach for measuring image model. Our approach is inspired by legal definitions originality using multi-token textual inversion. Original images of originality and aims to assess whether a require more tokens for accurate reconstruction, while model can produce original content without relying common images like Van Gogh's "Starry Night" need only on specific prompts or having the training data one token.