{"id":1183992,"date":"2023-09-20T18:35:55","date_gmt":"2023-09-20T22:35:55","guid":{"rendered":"https:\/\/www.prime-wow.com\/?p=1183992"},"modified":"2023-09-20T18:35:55","modified_gmt":"2023-09-20T22:35:55","slug":"openais-new-ai-image-generator-pushes-the-limits-in-detail-and-prompt-fidelity","status":"publish","type":"post","link":"https:\/\/www.prime-wow.com\/?p=1183992","title":{"rendered":"OpenAI\u2019s new AI image generator pushes the limits in detail and prompt fidelity"},"content":{"rendered":"<div id=\"rss-wrap\">\n<figure class=\"intro-image intro-left\">\n  <img decoding=\"async\" src=\"https:\/\/www.prime-wow.com\/wp-content\/uploads\/2023\/09\/dalle_2_hero-800x450-1.jpg\" alt=\"A series of images generated using OpenAI's DALL-E 3 image synthesis model.\" \/><\/p>\n<p class=\"caption\" style=\"font-size:0.8em\"><a href=\"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/09\/dalle_2_hero.jpg\" class=\"enlarge-link\" data-height=\"675\" data-width=\"1200\">Enlarge<\/a> <\/p>\n<\/figure>\n<div><a name=\"page-1\" \/><\/div>\n<p>On Wednesday, OpenAI <a href=\"https:\/\/openai.com\/dall-e-3\">announced<\/a> DALL-E 3, the latest version of its AI image synthesis model that features full integration with <a href=\"https:\/\/arstechnica.com\/information-technology\/2022\/12\/openai-invites-everyone-to-test-new-ai-powered-chatbot-with-amusing-results\/\">ChatGPT<\/a>. DALL-E 3 renders images by closely following complex descriptions and handling in-image text generation (such as labels and signs), which challenged earlier models. Currently in research preview, it will be available to ChatGPT Plus and Enterprise customers in early October.<\/p>\n<p>Like its <a href=\"https:\/\/arstechnica.com\/information-technology\/2022\/09\/openai-image-generator-dall-e-now-available-without-waitlist\/\">predecessor<\/a>, DALLE-3 is a text-to-image generator that creates novel images based on written descriptions called prompts. Although OpenAI released no technical details about DALL-E 3, the AI model at the heart of previous versions of DALL-E was trained on millions of images created by human artists and photographers, some of them licensed from stock websites like <a href=\"https:\/\/arstechnica.com\/information-technology\/2022\/10\/shutterstock-partners-with-openai-to-sell-ai-generated-artwork-compensate-artists\/\">Shutterstock<\/a>. It&#8217;s likely DALL-E 3 follows this same formula, but with new training techniques and more computational training time.<\/p>\n<p>Judging by the samples provided by OpenAI on its promotional blog, DALL-E 3 appears to be a radically more capable image synthesis model than anything else available in terms of following prompts. While OpenAI&#8217;s examples have been cherry-picked for their effectiveness, they appear to follow the prompt instructions faithfully and convincingly render objects with minimal deformations. Compared to <a href=\"https:\/\/arstechnica.com\/information-technology\/2022\/09\/openai-image-generator-dall-e-now-available-without-waitlist\/\">DALL-E 2<\/a>, OpenAI says that DALL-E 3 refines small details like hands more effectively, creating engaging images by default with &#8220;no hacks or prompt engineering required.&#8221;<\/p>\n<\/div>\n<p><a href=\"https:\/\/arstechnica.com\/?p=1969719#p3\">Read 10 remaining paragraphs<\/a> | <a href=\"https:\/\/arstechnica.com\/?p=1969719&amp;comments=1\">Comments<\/a><\/p>\n<p>&#013;<br \/>\n&#013;<br \/>\nSource: Ars Technica &#8211; <a href=\"https:\/\/arstechnica.com\/?p=1969719\" target=\"_blank\" rel=\"noopener\">OpenAI\u2019s new AI image generator pushes the limits in detail and prompt fidelity<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Enlarge On Wednesday, OpenAI announced DALL-E 3, the latest version of its AI image synthesis model that features full integration with ChatGPT. DALL-E 3 renders images by closely following complex descriptions and handling in-image text generation (such as labels and &hellip; <a href=\"https:\/\/www.prime-wow.com\/?p=1183992\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":1183993,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[27,110],"tags":[73],"class_list":["post-1183992","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ars-technica","category-unfiltered-rss","tag-ars-technica"],"_links":{"self":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts\/1183992","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1183992"}],"version-history":[{"count":0,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts\/1183992\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/media\/1183993"}],"wp:attachment":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1183992"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1183992"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1183992"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}