---
title: README
emoji: 🏃
colorFrom: pink
colorTo: indigo
sdk: static
pinned: false
---

# Stable Bias: Analyzing Societal Representations in Diffusion Models

As machine learning-enabled Text-to-Image (TTI) systems are becoming increasingly prevalent and seeing growing adoption as commercial services, characterizing the social biases they exhibit is a necessary first step to lowering their risk of discriminatory outcomes. This evaluation, however, is made more difficult by the synthetic nature of these systems' outputs; since artificial depictions of fictive humans have no inherent gender or ethnicity nor belong to socially constructed groups, we need to look beyond common definitions of diversity or representation.

To address this need, we propose a new method for exploring and quantifying social biases in TTI systems by directly comparing collections of generated images designed to showcase a model's variation across social attributes—such as gender or ethnicity—and target attributes for bias evaluation—such as professions or gender-coded adjectives. Our approach allows us to (i) identify specific bias trends through visualization tools, (ii) provide targeted scores to directly compare models in terms of diversity and representation, and (iii) jointly model related social variables to support a multidimensional analysis.

We find that all three models considered significantly over-represent the portion of their latent space associated with whiteness and masculinity across target attributes. Among those, \DallE shows the least diversity, followed by Stable Diffusion v2 then v1.4.