{"id":59765,"date":"2022-04-07T16:31:27","date_gmt":"2022-04-07T13:31:27","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=59765"},"modified":"2025-09-04T23:42:57","modified_gmt":"2025-09-04T20:42:57","slug":"openai-updates-dall-e-the-text-to-image-generator","status":"publish","type":"post","link":"https:\/\/u1f987.com\/en\/openai-updates-dall-e-the-text-to-image-generator\/","title":{"rendered":"OpenAI updates DALL-E, the text-to-image generator"},"content":{"rendered":"<p>The non-profit organisation OpenAI has unveiled a new version of its text-to-image generator that creates realistic images at higher resolution and with lower latency than the original.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Our newest system DALL\u00b7E 2 can create realistic images and art from a description in natural language. See it here: <a href=\"https:\/\/t.co\/Kmjko82YO5\">https:\/\/t.co\/Kmjko82YO5<\/a> <a href=\"https:\/\/t.co\/QEh9kWUE8A\">pic.twitter.com\/QEh9kWUE8A<\/a><\/p>\n<p>\u2014 OpenAI (@OpenAI) <a href=\"https:\/\/twitter.com\/OpenAI\/status\/1511707245536428034?ref_src=twsrc%5Etfw\">April 6, 2022<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>In DALL-E 2, users can select and edit specific regions of existing images, add or remove elements along with their shadows, create collages and variations of completed drawings.<\/p>\n<p>The neural network generates images at a resolution of 1024 pixels \u2014 four times higher than the original model.<\/p>\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-1 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" data-id=\"169699\" src=\"https:\/\/u1f987.com\/wp-content\/uploads\/FPqutjeVcAYavM8-1024x1024.jpg\" alt=\"OpenAI \u043e\u0431\u043d\u043e\u0432\u0438\u043b\u0430 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u043e\u0440 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043f\u043e \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u043e\u043c\u0443 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u044e DALL-E\" class=\"wp-image-169699\" srcset=\"https:\/\/u1f987.com\/wp-content\/uploads\/FPqutjeVcAYavM8.jpg 1024w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqutjeVcAYavM8-300x300.jpg 300w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqutjeVcAYavM8-150x150.jpg 150w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqutjeVcAYavM8-768x768.jpg 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" data-id=\"169700\" src=\"https:\/\/u1f987.com\/wp-content\/uploads\/FPqu_P4VEAEG5W6-1024x1024.jpg\" alt=\"OpenAI \u043e\u0431\u043d\u043e\u0432\u0438\u043b\u0430 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u043e\u0440 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043f\u043e \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u043e\u043c\u0443 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u044e DALL-E\" class=\"wp-image-169700\" srcset=\"https:\/\/u1f987.com\/wp-content\/uploads\/FPqu_P4VEAEG5W6.jpg 1024w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqu_P4VEAEG5W6-300x300.jpg 300w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqu_P4VEAEG5W6-150x150.jpg 150w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqu_P4VEAEG5W6-768x768.jpg 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" data-id=\"169701\" src=\"https:\/\/u1f987.com\/wp-content\/uploads\/FPqvfEsVUAc69Xs-1024x1024.jpg\" alt=\"OpenAI \u043e\u0431\u043d\u043e\u0432\u0438\u043b\u0430 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u043e\u0440 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043f\u043e \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u043e\u043c\u0443 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u044e DALL-E\" class=\"wp-image-169701\" srcset=\"https:\/\/u1f987.com\/wp-content\/uploads\/FPqvfEsVUAc69Xs.jpg 1024w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqvfEsVUAc69Xs-300x300.jpg 300w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqvfEsVUAc69Xs-150x150.jpg 150w, https:\/\/u1f987.com\/wp-content\/uploads\/FPqvfEsVUAc69Xs-768x768.jpg 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure><figcaption class=\"blocks-gallery-caption\">Images generated by DALL-E 2. Data: OpenAI.<\/figcaption><\/figure>\n<p>The DALL-E service (a portmanteau of the artist Salvador Dal\u00ed and the animated character WALL-E) is based on the OpenAI CLIP computer-vision model, announced in 2021.<\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>&#8220;The original model simply took a GPT-3-style language approach and applied it to the creation of images: we fed the images into a bag of words and learned to predict what would come next,&#8221; said OpenAI researcher Prafulla Dhariwal.<\/p>\n<\/blockquote>\n<p>As of today, DALL-E 2 is available to testers who have signed up on the waitlist. Users are not allowed to create obscene or extremist imagery, as well as material related to &#8220;current geopolitical events&#8221;.<\/p>\n<p>Earlier this year, in January, a machine-learning engineer created a Pok\u00e9mon generator based on the DALL-E model.<\/p>\n<p>In August 2021, an enthusiast developed a reduced-version of OpenAI&#8217;s text-to-image generator.<\/p>\n<p>Follow ForkLog on <a href=\"https:\/\/www.tiktok.com\/@forklogai\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">TikTok<\/a>!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The non-profit organisation OpenAI has unveiled a new version of its text-to-image generator that creates realistic images at higher resolution and with lower latency than the original.<\/p>\n","protected":false},"author":1,"featured_media":59766,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1190],"class_list":["post-59765","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-openai"],"aioseo_notices":[],"amp_enabled":true,"views":"19","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/59765","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/comments?post=59765"}],"version-history":[{"count":1,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/59765\/revisions"}],"predecessor-version":[{"id":59767,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/59765\/revisions\/59767"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media\/59766"}],"wp:attachment":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media?parent=59765"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/categories?post=59765"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/tags?post=59765"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}