News
|
DALL·E: Creating Images from Text

DALL·E: Creating Images from Text

<p>DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text–image pairs. We’ve found that it has a diverse set of capabilities, including creating anthropomorphized versions of animals and objects, combining</p>

Breakdown

DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text–image pairs. We’ve found that it has a diverse set of capabilities, including creating anthropomorphized versions of animals and objects, combining

Read full post on →
Author profile picture

Author

Curated

Jan 6, 6:48 AM

Source

Tags

Brand logo for external website's link
Ad
Brand logo for external website's link
Letter
An AI-assisted newsletter builder for content creators, designers, and developers.
Get

Tomorrow's news, today

AI-driven updates, curated by humans and hand-edited for the Prototypr community