Glossary

Text-to-image

Also known as: T2I, txt2img

A generation mode where the input is text (the prompt) and the output is an image. The most common AI image generation mode.

In depth

What it means in practice

Text-to-image is the default for most image models. The model takes a written description and produces an image matching it. Nano Banana 2 supports text-to-image on hilens, with HiDream-O1-image-1.5 announced to follow.

Text-to-image contrasts with image-to-image (input is an existing image plus optional prompt, model produces a modified version) and image-to-video (input is an image, model produces a video). The same model often supports multiple modes through different parameter settings rather than as distinct models.

Related

← Back to glossary