Identifying Prompted Artist Names from Generated Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Grace, Wang, Sheng-Yu, Hertzmann, Aaron, Shechtman, Eli, Zhu, Jun-Yan, Zhang, Richard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912499946749952
author Su, Grace
Wang, Sheng-Yu
Hertzmann, Aaron
Shechtman, Eli
Zhu, Jun-Yan
Zhang, Richard
author_facet Su, Grace
Wang, Sheng-Yu
Hertzmann, Aaron
Shechtman, Eli
Zhu, Jun-Yan
Zhang, Richard
contents A common and controversial use of text-to-image models is to generate pictures by explicitly naming artists, such as "in the style of Greg Rutkowski". We introduce a benchmark for prompted-artist recognition: predicting which artist names were invoked in the prompt from the image alone. The dataset contains 1.95M images covering 110 artists and spans four generalization settings: held-out artists, increasing prompt complexity, multiple-artist prompts, and different text-to-image models. We evaluate feature similarity baselines, contrastive style descriptors, data attribution methods, supervised classifiers, and few-shot prototypical networks. Generalization patterns vary: supervised and few-shot models excel on seen artists and complex prompts, whereas style descriptors transfer better when the artist's style is pronounced; multi-artist prompts remain the most challenging. Our benchmark reveals substantial headroom and provides a public testbed to advance the responsible moderation of text-to-image models. We release the dataset and benchmark to foster further research: https://graceduansu.github.io/IdentifyingPromptedArtists/
format Preprint
id arxiv_https___arxiv_org_abs_2507_18633
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Identifying Prompted Artist Names from Generated Images
Su, Grace
Wang, Sheng-Yu
Hertzmann, Aaron
Shechtman, Eli
Zhu, Jun-Yan
Zhang, Richard
Computer Vision and Pattern Recognition
A common and controversial use of text-to-image models is to generate pictures by explicitly naming artists, such as "in the style of Greg Rutkowski". We introduce a benchmark for prompted-artist recognition: predicting which artist names were invoked in the prompt from the image alone. The dataset contains 1.95M images covering 110 artists and spans four generalization settings: held-out artists, increasing prompt complexity, multiple-artist prompts, and different text-to-image models. We evaluate feature similarity baselines, contrastive style descriptors, data attribution methods, supervised classifiers, and few-shot prototypical networks. Generalization patterns vary: supervised and few-shot models excel on seen artists and complex prompts, whereas style descriptors transfer better when the artist's style is pronounced; multi-artist prompts remain the most challenging. Our benchmark reveals substantial headroom and provides a public testbed to advance the responsible moderation of text-to-image models. We release the dataset and benchmark to foster further research: https://graceduansu.github.io/IdentifyingPromptedArtists/
title Identifying Prompted Artist Names from Generated Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18633