AI Glossary

Text-to-image

Also called T2I

What does “Text-to-image” mean?

Text-to-image: Generating a picture from a written description. You type a prompt such as a scene, subject or style, and the model produces one or more images that try to match it. Most current systems are diffusion models trained on large collections of captioned images.

Text-to-image visual guide: Generating a picture from a written description. You type a prompt such as a scene, subject or style, and the model produces one or more images that try to match it. Most current systems are diffusion models trained on large collections of captioned images.
Visual guide Open full size (new tab)

What is an example of “Text-to-image”?

Typing "a lighthouse at dusk in watercolor style" into Midjourney or a Stable Diffusion app returns several candidate images to choose from.

Keep learning

See also

Diffusion modelTermNegative promptTermCFG scaleTermImage-to-imageTerm

Same topic

3D generationTermContent provenance (C2PA)TermControlNetTermLatent diffusionTermLoRA (image models)Term