# Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity arXiv: https://arxiv.org/abs/2508.17465 ยท HTML: https://mlsanity.com/paper/2508.17465/ ## Key facts - Cited by 5 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 22 of its 52 references that are in the map. - First posted on arXiv 24 Aug 2025. ## 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, 22 of 22) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022) - [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017) - [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020) - [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019) - [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022) - [Towards a Critical Race Methodology in Algorithmic Fairness](https://mlsanity.com/paper/1912.03593/) (2019) - [A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'](https://mlsanity.com/paper/2410.12954/) (2024) - [Towards Measuring Fairness in AI: the Casual Conversations Dataset](https://mlsanity.com/paper/2104.02821/) (2021) - [Lifespan Age Transformation Synthesis](https://mlsanity.com/paper/2003.09764/) (2020) - [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023) - [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022) - ['Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion](https://mlsanity.com/paper/2310.19981/) (2023) - [Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation](https://mlsanity.com/paper/2205.03962/) (2022) - [Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans](https://mlsanity.com/paper/2401.08495/) (2024) - [Evidence for Hypodescent in Visual Semantic AI](https://mlsanity.com/paper/2205.10764/) (2022) - [A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?](https://mlsanity.com/paper/2302.07159/) (2023) - [Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color](https://mlsanity.com/paper/2309.05148/) (2023) - [Vision-Language Models Generate More Homogeneous Stories for Phenotypically Black Individuals](https://mlsanity.com/paper/2412.09668/) (2024) - [Black or White but never neutral: How readers perceive identity from yellow or skin-toned emoji](https://mlsanity.com/paper/2105.05887/) (2021) - [Documenting Patterns of Exoticism of Marginalized Populations within Text-to-Image Generators](https://mlsanity.com/paper/2508.02937/) (2025) ## Built on by (most cited first, 5 of 5) - [VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation](https://mlsanity.com/paper/2601.00996/) (2026) - [Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models](https://mlsanity.com/paper/2602.16149/) (2026) - [Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities](https://mlsanity.com/paper/2605.04127/) (2026) - [Gender Artifacts from Art History to Text-to-Image Generation](https://mlsanity.com/paper/2606.05829/) (2026) - [GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension](https://mlsanity.com/paper/2604.09923/) (2026) ## Abstract (arXiv) Text-to-image generators (T2Is) are liable to produce images that perpetuate social stereotypes, especially in regards to race or skin tone. We use a comprehensive set of 93 stigmatized identities to determine that three versions of Stable Diffusion (v1.5, v2.1, and XL) systematically associate stigmatized identities with certain skin tones in generated images. We find that SD XL produces skin tones that are 13.53% darker and 23.76% less red (both of which indicate higher likelihood of societal discrimination) than previous models and perpetuate societal stereotypes associating people of color with stigmatized identities. SD XL also shows approximately 30% less variability in skin tones when compared to previous models and 18.89-56.06% compared to human face datasets. Measuring variability through metrics which directly correspond to human perception suggest a similar pattern, where SD XL shows the least amount of variability in skin tones of people with stigmatized identities and depicts most (60.29%) stigmatized identities as being less diverse than non-stigmatized identities. Finally, SD shows more homogenization of skin tones of racial and ethnic identities compared to other stigmatized or non-stigmatized identities, reinforcing incorrect equivalence of biologically-determined skin tone and socially-constructed racial and ethnic identity. Because SD XL is the largest and most complex model and users prefer its generations compared to other models examined in this study, these findings have implications for the dynamics of bias amplification in T2Is, increasing representational harms and challenges generating diverse images depicting people with stigmatized identities.