Text-to-Image Model

A generative AI system that produces images from natural-language prompts. Prominent examples include DALL-E, Stable Diffusion, and Midjourney. In accessibility contexts, text-to-image models have been shown to replicate and amplify disability stereotypes — for example, depicting disabled people as sad or pitiful, using overly bionic or superhero-style assistive technology, or rendering assistive devices incorrectly — making user-level evaluation and prompting strategies a significant concern for responsible use.