# Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?

arXiv: https://arxiv.org/abs/2305.18398 · HTML: https://mlsanity.com/paper/2305.18398/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 28 May 2023.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?](https://mlsanity.com/paper/2202.06675/) (2022)
- [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://mlsanity.com/paper/2211.06679/) (2022)
- [MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation](https://mlsanity.com/paper/2305.15296/) (2023)
- [A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent Spaces](https://mlsanity.com/paper/2211.07292/) (2022)

## Built on by (most cited first, 16 of 16)

- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023)
- [Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation](https://mlsanity.com/paper/2311.17216/) (2023)
- [SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models](https://mlsanity.com/paper/2404.06666/) (2024)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models](https://mlsanity.com/paper/2406.05113/) (2024)
- [Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance](https://mlsanity.com/paper/2406.04551/) (2024)
- [Implicit Concept Removal of Diffusion Models](https://mlsanity.com/paper/2310.05873/) (2023)
- [Hyperbolic Safety-Aware Vision-Language Models](https://mlsanity.com/paper/2503.12127/) (2025)
- [Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You](https://mlsanity.com/paper/2401.16092/) (2024)
- [Risks and Opportunities of Open-Source Generative AI](https://mlsanity.com/paper/2405.08597/) (2024)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge](https://mlsanity.com/paper/2309.11575/) (2023)
- [Increasing the Utility of Synthetic Images through Chamfer Guidance](https://mlsanity.com/paper/2508.10631/) (2025)
- [GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2408.16700/) (2024)
- [Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models](https://mlsanity.com/paper/2605.26332/) (2026)
- [Security Risk of Misalignment between Text and Image in Multi-modal Model](https://mlsanity.com/paper/2510.26105/) (2025)

## Abstract (arXiv)

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on billion-sized datasets randomly scraped from the web, they also reproduce inappropriate human behavior. Specifically, we demonstrate inappropriate degeneration on a large-scale for various generative text-to-image models, thus motivating the need for monitoring and moderating them at deployment. To this end, we evaluate mitigation strategies at inference to suppress the generation of inappropriate content. Our findings show that we can use models' representations of the world's ugliness to align them with human preferences.