# Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution arXiv: https://arxiv.org/abs/2408.17285 ยท HTML: https://mlsanity.com/paper/2408.17285/ ## Key facts - Cited by 7 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 47 of its 76 references that are in the map. - First posted on arXiv 30 Aug 2024. ## 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, 30 of 47) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020) - [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021) - [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022) - [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022) - [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022) - [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021) - [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019) - [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015) - [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022) - [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022) - [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021) - [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022) - [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022) - [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022) - [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020) - [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022) - [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023) - [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020) - [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023) ## Built on by (most cited first, 7 of 7) - [HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns](https://mlsanity.com/paper/2501.16750/) (2025) - [SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models](https://mlsanity.com/paper/2510.05173/) (2025) - [Selective Fine-Tuning for Targeted and Robust Concept Unlearning](https://mlsanity.com/paper/2602.07919/) (2026) - [When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm](https://mlsanity.com/paper/2603.24079/) (2026) - [Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation](https://mlsanity.com/paper/2608.05210/) (2026) - [What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift](https://mlsanity.com/paper/2504.21042/) (2025) - [ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models](https://mlsanity.com/paper/2606.14351/) (2026) ## Abstract (arXiv) Text-to-image models, such as Stable Diffusion (SD), undergo iterative updates to improve image quality and address concerns such as safety. Improvements in image quality are straightforward to assess. However, how model updates resolve existing concerns and whether they raise new questions remain unexplored. This study takes an initial step in investigating the evolution of text-to-image models from the perspectives of safety, bias, and authenticity. Our findings, centered on Stable Diffusion, indicate that model updates paint a mixed picture. While updates progressively reduce the generation of unsafe images, the bias issue, particularly in gender, intensifies. We also find that negative stereotypes either persist within the same Non-White race group or shift towards other Non-White race groups through SD updates, yet with minimal association of these traits with the White race group. Additionally, our evaluation reveals a new concern stemming from SD updates: State-of-the-art fake image detectors, initially trained for earlier SD versions, struggle to identify fake images generated by updated versions. We show that fine-tuning these detectors on fake images generated by updated versions achieves at least 96.6% accuracy across various SD versions, addressing this issue. Our insights highlight the importance of continued efforts to mitigate biases and vulnerabilities in evolving text-to-image models.