Identifying Prompted Artist Names from Generated Images
This work addresses the need for responsible moderation of text-to-image models by providing a public benchmark to detect artist-specific prompts, though it is incremental as it builds on existing recognition and attribution techniques.
The paper tackles the problem of identifying which artist names were used in prompts to generate images from text-to-image models, by introducing a benchmark with 1.95M images across 110 artists and evaluating various methods, finding that supervised and few-shot models perform well on seen artists and complex prompts, while style descriptors transfer better for pronounced styles, with multi-artist prompts being the most challenging.
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/