sourced story
5 January 2021Primary source · 2 sourcesWell documented

DALL-E generates images directly from text captions

A 12-billion-parameter version of GPT-3 learns to draw what it's told

On the timeline · around 5 January 2021 · Transformers and the Generative AI WaveTransformers and the Generative AI WaveRecognition and ReasoningDALL-E generates images directly from text captions20192020202120222023

Quick facts

Institution
OpenAI
Parameters
12 billion
Method
Autoregressive Transformer over text and image tokens

What happened

OpenAI announced DALL-E, a 12-billion-parameter version of the GPT-3 Transformer architecture trained to generate images from text descriptions rather than text from text. Aditya Ramesh and co-authors described the underlying method in 'Zero-Shot Text-to-Image Generation': the model treated both text and image patches as tokens in a single stream, using a discrete variational autoencoder to compress images into a manageable vocabulary of visual tokens the Transformer could then predict autoregressively, one token at a time, conditioned on the caption. DALL-E could generate plausible images for captions describing combinations that had likely never co-occurred in its training data, such as anthropomorphized objects or animals rendered in specific artistic styles, and it could also apply requested edits or transformations to existing images.

Why it matters

DALL-E demonstrated that the same Transformer approach behind large language models could be extended to generate images directly from natural-language descriptions, helping trigger the wave of text-to-image systems, including Stable Diffusion the following year, that made image generation broadly accessible.

How we know

OpenAI's own announcement describes the model's scale and GPT-3 lineage directly; the companion technical paper on arXiv documents the token-based architecture in full detail.

Sources

See something wrong? . Corrections with a source get fixed fastest.

Part of a timelineArtificial Intelligence30 events · From a wartime theory of neurons to machines that write, paint, and fold proteinsView all →
DALL-E generates images directly from text captions · Artificial Intelligence · SourcedStory