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

arXiv: https://arxiv.org/abs/2310.19981 · HTML: https://mlsanity.com/paper/2310.19981/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Generating Images from Captions with Attention](https://mlsanity.com/paper/1511.02793/) (2015)
- [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022)
- [American == White in Multimodal Language-and-Image AI](https://mlsanity.com/paper/2207.00691/) (2022)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- [A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?](https://mlsanity.com/paper/2302.07159/) (2023)
- [Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Models](https://mlsanity.com/paper/2304.13855/) (2023)
- [Gender Classification and Bias Mitigation in Facial Images](https://mlsanity.com/paper/2007.06141/) (2020)

## Built on by (most cited first, 30 of 33)

- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.01261/) (2023)
- [Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval](https://mlsanity.com/paper/2407.20371/) (2024)
- [ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation](https://mlsanity.com/paper/2401.06310/) (2024)
- [AI-generated faces influence gender stereotypes and racial homogenization](https://mlsanity.com/paper/2402.01002/) (2024)
- [A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2503.23398/) (2025)
- [From Melting Pots to Misrepresentations: Exploring Harms in Generative AI](https://mlsanity.com/paper/2403.10776/) (2024)
- [BiasDora: Exploring Hidden Biased Associations in Vision-Language Models](https://mlsanity.com/paper/2407.02066/) (2024)
- [A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models](https://mlsanity.com/paper/2402.13636/) (2024)
- [Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution](https://mlsanity.com/paper/2408.17285/) (2024)
- [Un-Straightening Generative AI: How Queer Artists Surface and Challenge the Normativity of Generative AI Models](https://mlsanity.com/paper/2503.09805/) (2025)
- [POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation](https://mlsanity.com/paper/2504.13392/) (2025)
- [Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes](https://mlsanity.com/paper/2506.06506/) (2025)
- [Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity](https://mlsanity.com/paper/2508.17465/) (2025)
- [Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models](https://mlsanity.com/paper/2505.23798/) (2025)
- [Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models](https://mlsanity.com/paper/2510.03721/) (2025)
- [DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model](https://mlsanity.com/paper/2501.18642/) (2025)
- [BiasConnect: Investigating Bias Interactions in Text-to-Image Models](https://mlsanity.com/paper/2503.09763/) (2025)
- [Discovering Divergent Representations between Text-to-Image Models](https://mlsanity.com/paper/2509.08940/) (2025)
- [Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking](https://mlsanity.com/paper/2604.13776/) (2026)
- [What if AI systems weren't chatbots?](https://mlsanity.com/paper/2605.07896/) (2026)
- [AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation](https://mlsanity.com/paper/2406.12805/) (2024)
- [Neutral Prompts, Non-Neutral People: Quantifying Gender and Skin-Tone Bias in Gemini Flash 2.5 Image and GPT Image 1.5](https://mlsanity.com/paper/2602.12133/) (2026)
- [Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models](https://mlsanity.com/paper/2604.21036/) (2026)
- [Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems](https://mlsanity.com/paper/2609.11532/) (2026)
- [FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing](https://mlsanity.com/paper/2502.03826/) (2025)
- [From job titles to jawlines: Using context voids to study generative AI systems](https://mlsanity.com/paper/2504.13947/) (2025)
- [When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Models](https://mlsanity.com/paper/2508.03483/) (2025)
- [Designing and Evaluating Malinowski's Lens: An AI-Native Educational Game for Ethnographic Learning](https://mlsanity.com/paper/2511.07682/) (2025)
- [Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Education](https://mlsanity.com/paper/2601.14506/) (2026)

## Abstract (arXiv)

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.