2025/06/09 by Sedat Porikli, Porikli, Sedat, Vedat Porikli +1
Arts and Humanities · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #Digital Humanities and Scholarship #FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2506.13780
openalex publication_date 2025/06/09 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28
Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To investigate these issues, we curated a diverse set of prompts spanning thematic categories such as occupations, traits, actions, ideologies, emotions, family roles, place descriptions, spirituality, and life events. For each of the 160 unique topics, we crafted multiple prompt variations to reflect a wide range of meanings and perspectives. Using Stable Diffusion 1.5 (UNet-based) and Flux-1 (DiT-based) models with original checkpoints, we generated over 16,000 images under consistent settings. Additionally, we collected 8,000 comparison images from Google Image Search. All outputs were filtered to exclude abstract, distorted, or nonsensical results. Our analysis reveals significant disparities in the representation of gender, race, age, somatotype, and other human-centric factors across generated images. These disparities often mirror and reinforce harmful stereotypes embedded in societal narratives. We discuss the implications of these findings and emphasize the need for more inclusive datasets and development practices to foster fairness in generative visual systems.