Saved in:
Bibliographic Details
Main Authors: Ren, Hui, Materzynska, Joanna, Gandikota, Rohit, Bau, David, Torralba, Antonio
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.00176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909617713315840
author Ren, Hui
Materzynska, Joanna
Gandikota, Rohit
Bau, David
Torralba, Antonio
author_facet Ren, Hui
Materzynska, Joanna
Gandikota, Rohit
Bau, David
Torralba, Antonio
contents We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-image model exclusively on photographs, without access to any painting-related content. We show that it is possible to adapt a model that is trained without paintings to an artistic style, given only few examples. User studies and automatic evaluations confirm that our model (post-adaptation) performs on par with state-of-the-art models trained on massive datasets that contain artistic content like paintings, drawings or illustrations. Finally, using data attribution techniques, we analyze how both artistic and non-artistic datasets contribute to generating artistic-style images. Surprisingly, our findings suggest that high-quality artistic outputs can be achieved without prior exposure to artistic data, indicating that artistic style generation can occur in a controlled, opt-in manner using only a limited, carefully selected set of training examples.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00176
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Opt-In Art: Learning Art Styles Only from Few Examples
Ren, Hui
Materzynska, Joanna
Gandikota, Rohit
Bau, David
Torralba, Antonio
Computer Vision and Pattern Recognition
We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-image model exclusively on photographs, without access to any painting-related content. We show that it is possible to adapt a model that is trained without paintings to an artistic style, given only few examples. User studies and automatic evaluations confirm that our model (post-adaptation) performs on par with state-of-the-art models trained on massive datasets that contain artistic content like paintings, drawings or illustrations. Finally, using data attribution techniques, we analyze how both artistic and non-artistic datasets contribute to generating artistic-style images. Surprisingly, our findings suggest that high-quality artistic outputs can be achieved without prior exposure to artistic data, indicating that artistic style generation can occur in a controlled, opt-in manner using only a limited, carefully selected set of training examples.
title Opt-In Art: Learning Art Styles Only from Few Examples
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.00176