https://www.youtube.com/watch?v=aQJkQ5KlnCA

DALL-E
From Wikipedia, the free encyclopedia:


DALL-E (stylized as DALL·E) and DALL-E 2 are transformer models developed by OpenAI to generate digital images from natural language descriptions. Its name is a portmanteau of WALL-E and Salvador Dalí. 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. As of 20 July 2022, DALL-E entered into a beta phase with invitations sent to 1 million waitlisted individuals. Access was previously restricted to pre-selected users for a research preview due to concerns about ethics and safety.Despite this, several open-source imitations trained on smaller amounts of data were released by others.