Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art

TL;DR

This study evaluates how well humans and combined human-AI efforts can infer original prompts from AI-generated images in art marketplaces, revealing moderate success but limited improvement over individual inferences.

Contribution

It introduces the first human subject study on prompt inference and explores collaborative human-AI prompt inference techniques in AI-generated art.

Findings

Humans can moderately infer prompts from images.

Combined human-AI prompts do not outperform human-only prompts.

Original prompts lead to higher image similarity than inferred prompts.

Abstract

The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts to generate unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered bona fide intellectual property, given that humans and AI tools may be able to infer the prompts based on publicly advertised sample images accompanying each prompt on sale. Specifically, our study aims to assess (i) how accurately humans can infer the original prompt solely by examining an AI-generated image, with the goal of generating images similar to the original image, and (ii) the possibility of improving upon individual human and AI prompt inferences by crafting combined human and AI prompts with the help of a large language model. Although previous research has explored AI-driven prompt inference and protection strategies, our work is the first to incorporate a human subject study and examine collaborative human-AI prompt inference in depth. Our findings indicate that while prompts inferred by humans and prompts inferred through a combined human and AI effort can generate images with a moderate level of similarity, they are not as successful as using the original prompt. Moreover, combining human- and AI-inferred prompts using our suggested merging techniques did not improve performance over purely human-inferred prompts.