Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art
Preprint
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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks2025
- Review of large vision models and visual prompt engineeringMeta-Radiology, 2023
- Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models2023
- Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning2023
- Communication in Human–AI Co-Creation: Perceptual Analysis of Paintings Generated by Text-to-Image SystemApplied Sciences, 2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- LAION-5B: An Open Large-Scale Dataset for Training Next Generation Image-Text Models2022
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Table for Estimating the Goodness of Fit of Empirical DistributionsThe Annals of Mathematical Statistics, 1948