Decoder. plain-English AI glossary

DALL-E

● Core

OpenAI's text-to-image generative model; turns descriptions into images.

Think of it like

The artist that exists in a computer; paints what you describe.

Example

Describe "a corgi in a space suit" and get four variations; DALL-E 3 integrates with ChatGPT.

How it actually works

DALL-E uses a diffusion model (like Stable Diffusion) but trained at scale on diverse image-text pairs. DALL-E 3 (2023) is better at instruction-following and text rendering.

For product teams

Monetized via API and ChatGPT Plus; creative workers debate impact.

For engineers

Generative model with diffusion; inference is slow but quality improved significantly.

Read anything AI without the jargon

Look up any term in plain English, or save terms as you read with the free Chrome extension.

Open DecoderAdd to Chrome