Wednesday, January 06, 2021

OpenAI debuts DALL-E for generating images from text

Recommendable! Text to image synthesis! Multimodal machine learning is imminent!

"... Tests OpenAI shared today appear to demonstrate that DALL-E has the ability to manipulate and rearrange objects in generated imagery and also create things that don’t exist, like a cube with the texture of a porcupine or a cube of clouds. Based on text prompts, images generated by DALL-E can appear as if they were taken from the real world or can depict works of art. ..."

"... We’ve found that 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. ..."

OpenAI debuts DALL-E for generating images from text | VentureBeat

Here is the link to the respective OpenAI blog post:
DALL·E: Creating Images from Text 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



No comments: