DALL·E: Creating Images from Text
OpenAI,
Jan 06, 2021
Here's the headline: "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." Oh, but do look at the article; it is chock-full of examples of images created for different types of phrases and expressions. "It has a diverse set of capabilities, including creating anthropomorphized versions of animals and objects, combining unrelated concepts in plausible ways, rendering text, and applying transformations to existing images." The MIT Technology Review article loved the example of the avocado-shaped chair (and frankly, so do I, but I also like the snail with the texture of a harp and the baby daikon radish in a tutu walking a dog). The name is a portmanteau of the artist Salvador Dalí and Pixar's WALL·E. Personally, I'm waiting for BALL-E, an AI that creates and sends vacation pictures to your social media accounts.
Today: 3 Total: 3 [Direct link] [Share]
