# When Image Generation Goes Wrong: A Safety Analysis of Stable Diffusion Models

arXiv: https://arxiv.org/abs/2411.15516 · HTML: https://mlsanity.com/paper/2411.15516/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2024.

## Built on by (most cited first, 3 of 3)

- [Selecting Fine-Tuning Examples by Quizzing VLMs](https://mlsanity.com/paper/2511.12002/) (2025)
- [Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending](https://mlsanity.com/paper/2605.25574/) (2026)
- [From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan](https://mlsanity.com/paper/2606.27234/) (2026)

## Abstract (arXiv)

Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW, violent, and personally sensitive material. We demonstrate that these models respond to harmful prompts by generating inappropriate content, which frequently displays troubling biases, such as the disproportionate portrayal of Black individuals in violent contexts. Our findings demonstrate a complete lack of any refusal behavior or safety measures in the models observed. We emphasize the importance of addressing this issue as image generation technologies continue to become more accessible and incorporated into everyday applications.