'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion

Abstract

We study stereotypes embedded within one of the most popular text-to-image generators: Stable Diffusion. We examine what stereotypes of gender and nationality/continental identity does Stable Diffusion display in the absence of such information i.e. what gender and nationality/continental identity is assigned to `a person', or to `a person from Asia'. Using vision-language model CLIP's cosine similarity to compare images generated by CLIP-based Stable Diffusion v2.1 verified by manual examination, we chronicle results from 136 prompts (50 results/prompt) of front-facing images of persons from 6 different continents, 27 nationalities and 3 genders. We observe how Stable Diffusion outputs of `a person' without any additional gender/nationality information correspond closest to images of men and least with persons of nonbinary gender, and to persons from Europe/North America over Africa/Asia, pointing towards Stable Diffusion having a concerning representation of personhood to be a European/North American man. We also show continental stereotypes and resultant harms e.g. a person from Oceania is deemed to be Australian/New Zealander over Papua New Guinean, pointing to the erasure of Indigenous Oceanic peoples, who form a majority over descendants of colonizers both in Papua New Guinea and in Oceania overall. Finally, we unexpectedly observe a pattern of oversexualization of women, specifically Latin American, Mexican, Indian and Egyptian women relative to other nationalities, measured through an NSFW detector. This demonstrates how Stable Diffusion perpetuates Western fetishization of women of color through objectification in media, which if left unchecked will amplify this stereotypical representation. Image datasets are made publicly available.

Upcoming publication, Findings of EMNLP 2023

References in corpus (8)

• LAION-5B: An open large-scale dataset for training next generation image-text models
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
• Multimodal datasets: misogyny, pornography, and malignant stereotypes
• Stable Bias: Analyzing Societal Representations in Diffusion Models
• Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
• Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
• A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?
• Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Models

Cited by in corpus (3)

• Un-Straightening Generative AI: How Queer Artists Surface and Challenge the Normativity of Generative AI Models
• Working with Color: How Color Quantization Can Aid Researchers of Problematic Information
• A Civics-oriented Approach to Understanding Intersectionally Marginalized Users' Experience with Hate Speech Online