{"id":137809,"date":"2022-04-07T12:03:13","date_gmt":"2022-04-07T17:03:13","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2022\/04\/openais-dall-e-2-produces-fantastical-images-of-most-anything-you-can-imagine"},"modified":"2022-04-07T12:03:13","modified_gmt":"2022-04-07T17:03:13","slug":"openais-dall-e-2-produces-fantastical-images-of-most-anything-you-can-imagine","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2022\/04\/openais-dall-e-2-produces-fantastical-images-of-most-anything-you-can-imagine","title":{"rendered":"OpenAI\u2019s DALL-E 2 produces fantastical images of most anything you can imagine"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/openais-dall-e-2-produces-fantastical-images-of-most-anything-you-can-imagine2.jpg\"><\/a><\/p>\n<p>In January, 2021, the OpenAI consortium \u2014 founded by Elon Musk and financially backed by Microsoft \u2014 unveiled its most ambitious project to date, the DALL-E machine learning system. This ingenious multimodal AI was capable of generating images (albeit, rather cartoonish ones) based on the attributes described by a user \u2014 think \u201ca cat made of sushi\u201d or \u201can x-ray of a Capybara sitting in a forest.\u201d On Wednesday, the consortium unveiled DALL-E\u2019s next iteration which boasts higher resolution and lower latency than the original.<\/p>\n<p>The first DALL-E (a portmanteau of \u201cDali,\u201d as in the artist, and \u201cWALL-E,\u201d as in the animated Disney character) could generate images as well as combine multiple images into a collage, provide varying angles of perspective, and even infer elements of an image \u2014 such as shadowing effects \u2014 from the written description.<\/p>\n<p>\u201cUnlike a 3D rendering engine, whose inputs must be specified unambiguously and in complete detail, DALL\u00b7E is often able to \u2018fill in the blanks\u2019 when the caption implies that the image must contain a certain detail that is not explicitly stated,\u201d the <a href=\"https:\/\/www.engadget.com\/dall-e-ai-gpt-make-image-from-any-description-135535140.html\">OpenAI team wrote in 2021<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In January, 2021, the OpenAI consortium \u2014 founded by Elon Musk and financially backed by Microsoft \u2014 unveiled its most ambitious project to date, the DALL-E machine learning system. This ingenious multimodal AI was capable of generating images (albeit, rather cartoonish ones) based on the attributes described by a user \u2014 think \u201ca cat made [\u2026]<\/p>\n","protected":false},"author":599,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2019,6],"tags":[],"class_list":["post-137809","post","type-post","status-publish","format-standard","hentry","category-elon-musk","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/137809","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/599"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=137809"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/137809\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=137809"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=137809"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=137809"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}