FrontierThe story, in brief
DALL·E: Creating images from text
OpenAI just trained a neural network that turns text into images. Here's why that changes everything.
The KeyNews take
Why it matters
DALL·E represents a major capability breakthrough in multimodal AI—text-to-image generation at scale. This is a foundational model release that expands AI's reach beyond language into creative domains, signaling OpenAI's broader strategy to own multiple modalities.
The key facts
5 to knowOpenAI released DALL·E, a neural network for text-to-image generation
Model generates images from natural language captions
Multimodal capability breakthrough (text input → image output)
Published January 5, 2021 — early-stage public release of generative vision capability
Demonstrates text-to-image generation at scale across diverse concepts
Go to the source
OpenAI Blogopenai.com
Publisher excerpt: We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.