kb:dall_e_2

DALL·E 2

DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language.

Snippet from Wikipedia: DALL-E

DALL-E (stylized as DALL·E) and DALL-E 2 are machine learning models developed by OpenAI to generate digital images from natural language descriptions. DALL-E was revealed by OpenAI in a blog post in January 2021, and uses a version of GPT-3 modified to generate images. In April 2022, OpenAI announced DALL-E 2, a successor designed to generate more realistic images at higher resolutions that "can combine concepts, attributes, and styles".

OpenAI has not released source code for either model, although output from a limited selection of sample prompts is available on OpenAI's website. On 20 July 2022, DALL-E 2 entered into a beta phase with invitations sent to 1 million waitlisted individuals. Access had previously been restricted to pre-selected users for a research preview due to concerns about ethics and safety. On 28 September 2022, DALL-E 2 was opened to anyone and the waitlist requirement was removed; users can generate a certain number of images for free and may purchase additional ones. Several open-source imitations trained on smaller amounts of data have been released by others.

The software's name is a portmanteau of the names of animated robot Pixar character WALL-E and the Spanish surrealist artist Salvador Dalí.

Related:

  • kb/dall_e_2.txt
  • Last modified: 2022/08/13 10:51
  • by Henrik Yllemo