Measuring Style Similarity in Diffusion Models

TL;DR

This paper introduces a new framework and dataset for extracting style descriptors from images to attribute and retrieve styles in generative diffusion models, addressing concerns about style replication.

Contribution

It presents a novel dataset and method for style descriptor extraction, enabling style attribution and matching in diffusion models, which was previously underexplored.

Findings

Effective style retrieval in diffusion models

Quantitative and qualitative analysis of style attribution

Promising results in style matching tasks

Abstract

Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine whether the properties of the image are attributable to specific training data, every time before a generated image is used for professional purposes. Existing tools for this purpose focus on retrieving images of similar semantic content. Meanwhile, many artists are concerned with style replication in text-to-image models. We present a framework for understanding and extracting style descriptors from images. Our framework comprises a new dataset curated using the insight that style is a subjective property of an image that captures complex yet meaningful interactions of factors including but not limited to colors, textures, shapes, etc. We also propose a method to extract style descriptors that can be used to attribute style of a generated image to the images used in the training dataset of a text-to-image model. We showcase promising results in various style retrieval tasks. We also quantitatively and qualitatively analyze style attribution and matching in the Stable Diffusion model. Code and artifacts are available at https://github.com/learn2phoenix/CSD.