# Balancing Act: Distribution-Guided Debiasing in Diffusion Models

arXiv: https://arxiv.org/abs/2402.18206 · HTML: https://mlsanity.com/paper/2402.18206/

## Key facts

- Cited by 52 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 54 of its 66 references that are in the map.
- First posted on arXiv 28 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, 30 of 54)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (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)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Universal Guidance for Diffusion Models](https://mlsanity.com/paper/2302.07121/) (2023)
- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Sketch-Guided Text-to-Image Diffusion Models](https://mlsanity.com/paper/2211.13752/) (2022)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)

## Built on by (most cited first, 30 of 52)

- [Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion](https://mlsanity.com/paper/2408.12692/) (2024)
- [PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control](https://mlsanity.com/paper/2408.05083/) (2024)
- [VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation](https://mlsanity.com/paper/2412.10768/) (2024)
- [Compass Control: Multi Object Orientation Control for Text-to-Image Generation](https://mlsanity.com/paper/2504.06752/) (2025)
- [Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention](https://mlsanity.com/paper/2506.13298/) (2025)
- [FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions](https://mlsanity.com/paper/2412.18810/) (2024)
- [OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes](https://mlsanity.com/paper/2501.00962/) (2025)
- [MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World](https://mlsanity.com/paper/2504.15397/) (2025)
- [High-dimensional Analysis of Synthetic Data Selection](https://mlsanity.com/paper/2510.08123/) (2025)
- [FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models](https://mlsanity.com/paper/2510.21363/) (2025)
- [AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models](https://mlsanity.com/paper/2407.11480/) (2024)
- [Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation](https://mlsanity.com/paper/2503.10125/) (2025)
- [DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusion](https://mlsanity.com/paper/2505.01857/) (2025)
- [Implicit Bias Injection Attacks against Text-to-Image Diffusion Models](https://mlsanity.com/paper/2504.01819/) (2025)
- [How I Met Your Bias: Investigating Bias Amplification in Diffusion Models](https://mlsanity.com/paper/2512.20233/) (2025)
- [Multi-Group Proportional Representation for Text-to-Image Models](https://mlsanity.com/paper/2505.24023/) (2025)
- [RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation](https://mlsanity.com/paper/2509.15257/) (2025)
- [Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2512.03749/) (2025)
- [Composing Parts for Expressive Object Generation](https://mlsanity.com/paper/2406.10197/) (2024)
- [GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2408.16700/) (2024)
- [Diffusion Models for Hyperspectral Image Analysis: A Comprehensive Review](https://mlsanity.com/paper/2505.11158/) (2025)
- [SCALEX: Scalable Concept and Latent Exploration for Diffusion Models](https://mlsanity.com/paper/2511.13750/) (2025)
- [Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder](https://mlsanity.com/paper/2603.11793/) (2026)
- [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)
- [Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales](https://mlsanity.com/paper/2605.28036/) (2026)
- [Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation](https://mlsanity.com/paper/2607.14962/) (2026)
- [AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation](https://mlsanity.com/paper/2406.12805/) (2024)
- [MoESD: Mixture of Experts Stable Diffusion to Mitigate Gender Bias](https://mlsanity.com/paper/2407.11002/) (2024)
- [Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts](https://mlsanity.com/paper/2410.21314/) (2024)

## Abstract (arXiv)

Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the training datasets. This is especially concerning in the context of faces, where the DM prefers one demographic subgroup vs others (eg. female vs male). In this work, we present a method for debiasing DMs without relying on additional data or model retraining. Specifically, we propose Distribution Guidance, which enforces the generated images to follow the prescribed attribute distribution. To realize this, we build on the key insight that the latent features of denoising UNet hold rich demographic semantics, and the same can be leveraged to guide debiased generation. We train Attribute Distribution Predictor (ADP) - a small mlp that maps the latent features to the distribution of attributes. ADP is trained with pseudo labels generated from existing attribute classifiers. The proposed Distribution Guidance with ADP enables us to do fair generation. Our method reduces bias across single/multiple attributes and outperforms the baseline by a significant margin for unconditional and text-conditional diffusion models. Further, we present a downstream task of training a fair attribute classifier by rebalancing the training set with our generated data.