Prompt fidelity of ChatGPT4o / Dall-E3 text-to-image visualisations

Dirk HR Spennemann
10/21/2025
cs.CVcs.AI

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

This study examines the prompt fidelity of ChatGPT4o / DALL-E3 text-to-image visualisations by analysing whether attributes explicitly specified in autogenously generated prompts are correctly rendered in the resulting images. Using two public-domain datasets comprising 200 visualisations of women working in the cultural and creative industries and 230 visualisations of museum curators, the study assessed accuracy across personal attributes (age, hair), appearance (attire, glasses), and paraphernalia (name tags, clipboards). While correctly rendered in most cases, DALL-E3 deviated from prompt specifications in 15.6% of all attributes (n=710). Errors were lowest for paraphernalia, moderate for personal appearance, and highest for depictions of the person themselves, particularly age. These findings demonstrate measurable prompt-to-image fidelity gaps with implications for bias detection and model evaluation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment

83% match2025

Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis

83% match1 repo32024

Towards Geographic Inclusion in the Evaluation of Text-to-Image Models

83% match2024

AAPMT: AGI Assessment Through Prompt and Metric Transformer

82% match2024

PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions

82% match2025

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

82% match1 repo102024

Cite this paper

@article{spennemann2025prompt,
  title  = {Prompt fidelity of ChatGPT4o / Dall-E3 text-to-image visualisations},
  author = {Dirk HR Spennemann},
  year   = {2025},
  eprint = {2510.21821},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.21821v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.21821.svg)](https://codeofpaper.com/paper/2510.21821)

Discussion