Demographic Stereotypes in Text-to-Image Generation
88 Citations•2023•
Federico Bianchi, Pratyusha Kalluri, Esin Durmus
journal unavailable
This research underscores the urgent need for policymakers to address the harms resulting from the mass dissemination of stereotypes through major text-to-image AI models.
Abstract
and breadth of biases in recently popularized text-to-image AI models, namely Stable Diffusion and DALL-E. We test a variety of ordinary text prompts and find that the resulting images perpetuate substantial biases and stereotypes—whether or not the prompts contain explicit references to demographic attributes. Our research underscores the urgent need for policymakers to address the harms resulting from the mass dissemination of stereotypes through major text-to-image AI models.