arxiv:2412.00176

Art-Free Generative Models: Art Creation Without Graphic Art Knowledge

Published on Nov 29

· Submitted by

jomat on Dec 3

Upvote

Authors:

Hui Ren ,

Joanna Materzynska ,

Rohit Gandikota ,

David Bau ,

Antonio Torralba

Abstract

We explore the question: "How much prior art knowledge is needed to create art?" To investigate this, we propose a text-to-image generation model trained without access to art-related content. We then introduce a simple yet effective method to learn an art adapter using only a few examples of selected artistic styles. Our experiments show that art generated using our method is perceived by users as comparable to art produced by models trained on large, art-rich datasets. Finally, through data attribution techniques, we illustrate how examples from both artistic and non-artistic datasets contributed to the creation of new artistic styles.

View arXiv page View PDF Add to collection

Community

jomat

Paper author Paper submitter 8 days ago

We explore the question: "How much prior art knowledge is needed to create art?". To find out, we designed a text-to-image generation model that skips training on art-related content entirely. Then, we developed a straightforward method to create an "art adapter," which learns artistic styles using just a handful of examples. Our experiments reveal that the art generated this way is rated by users as on par with pieces from models trained on massive, art-heavy datasets. Finally, through data attribution techniques, we illustrate how examples from both artistic and non-artistic datasets contributed to the creation of new artistic styles.

Project website: https://joaanna.github.io/art-free-diffusion/