# Debiasing Text-to-Image Diffusion Models

arXiv: https://arxiv.org/abs/2402.14577 · HTML: https://mlsanity.com/paper/2402.14577/

## Key facts

- Cited by 10 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 12 of its 15 references that are in the map.
- First posted on arXiv 22 Feb 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, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)

## Built on by (most cited first, 10 of 10)

- [VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2411.13503/) (2024)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [FairSkin: Fair Diffusion for Skin Disease Image Generation](https://mlsanity.com/paper/2410.22551/) (2024)
- [How I Met Your Bias: Investigating Bias Amplification in Diffusion Models](https://mlsanity.com/paper/2512.20233/) (2025)
- [Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder](https://mlsanity.com/paper/2507.20973/) (2025)
- [Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2512.03749/) (2025)
- [Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models](https://mlsanity.com/paper/2604.06052/) (2026)
- [Inference-Time Attribute Distribution Alignment for Unconditional Diffusion](https://mlsanity.com/paper/2605.07456/) (2026)
- [ResidualDroppath: Enhancing Feature Reuse over Residual Connections](https://mlsanity.com/paper/2411.09475/) (2024)
- [AutoDebias: Automated Framework for Debiasing Text-to-Image Models](https://mlsanity.com/paper/2508.00445/) (2025)

## Abstract (arXiv)

Learning-based Text-to-Image (TTI) models like Stable Diffusion have revolutionized the way visual content is generated in various domains. However, recent research has shown that nonnegligible social bias exists in current state-of-the-art TTI systems, which raises important concerns. In this work, we target resolving the social bias in TTI diffusion models. We begin by formalizing the problem setting and use the text descriptions of bias groups to establish an unsafe direction for guiding the diffusion process. Next, we simplify the problem into a weight optimization problem and attempt a Reinforcement solver, Policy Gradient, which shows sub-optimal performance with slow convergence. Further, to overcome limitations, we propose an iterative distribution alignment (IDA) method. Despite its simplicity, we show that IDA shows efficiency and fast convergence in resolving the social bias in TTI diffusion models. Our code will be released.