# Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models

arXiv: https://arxiv.org/abs/2511.00749 · HTML: https://mlsanity.com/paper/2511.00749/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 52 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Into the LAIONs Den: Investigating Hate in Multimodal Datasets](https://mlsanity.com/paper/2311.03449/) (2023)
- [Understanding the Impact of Negative Prompts: When and How Do They Take Effect?](https://mlsanity.com/paper/2406.02965/) (2024)
- [Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting](https://mlsanity.com/paper/2004.14088/) (2020)
- [Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models](https://mlsanity.com/paper/2309.08902/) (2023)
- [Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis](https://mlsanity.com/paper/2011.12086/) (2020)
- [Classist Tools: Social Class Correlates with Performance in NLP](https://mlsanity.com/paper/2403.04445/) (2024)
- [Improving image synthesis with diffusion-negative sampling](https://mlsanity.com/paper/2411.05473/) (2024)
- [Lookism: The overlooked bias in computer vision](https://mlsanity.com/paper/2408.11448/) (2024)

## Built on by (most cited first, 1 of 1)

- [Position: Universal Aesthetic Alignment Narrows Artistic Expression](https://mlsanity.com/paper/2512.11883/) (2025)

## Abstract (arXiv)

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models -- biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.