Interactive Discovery and Exploration of Visual Bias in Generative Text-to-Image Models
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Bias in generative Text-to-Image (T2I) models is a known issue, yet systematically analyzing such models' outputs to uncover it remains challenging. We introduce the Visual Bias Explorer (ViBEx) to interactively explore the output space of T2I models to support the discovery of visual bias. ViBEx introduces a novel flexible prompting tree interface in combination with zeroshot bias probing using CLIP for quick and approximate bias exploration. It additionally supports in-depth confirmatory bias analysis through visual inspection of forward, intersectional, and inverse bias queries. ViBEx is model-agnostic and publicly available. In four case study interviews, experts in AI and ethics were able to discover visual biases that have so far not been described in literature.
Description
CCS Concepts: Human-centered computing → Visualization; Computing methodologies → Artificial intelligence
@article{10.1111:cgf.70135,
journal = {Computer Graphics Forum},
title = {{Interactive Discovery and Exploration of Visual Bias in Generative Text-to-Image Models}},
author = {Eschner, Johannes and Labadie-Tamayo, Roberto and Zeppelzauer, Matthias and Waldner, Manuela},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70135}
}