{"id":428802,"date":"2022-04-08T22:21:16","date_gmt":"2022-04-08T19:21:16","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/openais-new-image-generator-sparks-both-excitement-and-fear\/"},"modified":"2022-04-08T22:21:16","modified_gmt":"2022-04-08T19:21:16","slug":"openais-new-image-generator-sparks-both-excitement-and-fear","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/openais-new-image-generator-sparks-both-excitement-and-fear\/","title":{"rendered":"#OpenAI\u2019s new image generator sparks both excitement and fear"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<label for=\"ez-toc-cssicon-toggle-item-6a3b5e9e05b67\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #dd3333;color:#dd3333\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #dd3333;color:#dd3333\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a3b5e9e05b67\" checked aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/buradabiliyorum.com\/en\/openais-new-image-generator-sparks-both-excitement-and-fear\/#%E2%80%9COpenAIs_new_image_generator_sparks_both_excitement_and_fear%E2%80%9D\" >&#8220;OpenAI\u2019s new image generator sparks both excitement and fear&#8221;<\/a><\/li><\/ul><\/nav><\/div>\n<h1><span class=\"ez-toc-section\" id=\"%E2%80%9COpenAIs_new_image_generator_sparks_both_excitement_and_fear%E2%80%9D\"><\/span>&#8220;OpenAI\u2019s new image generator sparks both excitement and fear&#8221;<span class=\"ez-toc-section-end\"><\/span><\/h1>\n<div>\n                            OpenAI has unveiled a new AI tool that turns text into images \u2014 and the results are stunning.<\/p>\n<p>Named DALL-E 2, the system is the successor to a model unveiled last year. While its predecessor generated some impressive outputs, the new version is a major upgrade.<\/p>\n<figure class=\"post-image post-mediaBleed aligncenter\"><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384307 js-lazy\" alt=\"This picture in the style of Claude Monet illustrates the improvements of the new model.\" width=\"1554\" height=\"818\" sizes=\"auto, (max-width: 1554px) 100vw, 1554px\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37.png\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37.png 1554w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-280x147.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-256x135.png 256w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-513x270.png 513w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-1536x809.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-796x419.png 796w\"\/><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2022%2F04%2F08%2Fopenai-dalle-2-text-to-image-generator-shows-ai-could-transform-design%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: This picture in the style of Claude Monet illustrates the improvements. Credit: OpenAI\" data-title=\"Share This picture in the style of Claude Monet illustrates the improvements. Credit: OpenAI on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share This picture in the style of Claude Monet illustrates the improvements. Credit: OpenAI on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>This picture in the style of Claude Monet illustrates the improvements. Credit: OpenAI<\/figcaption><noscript><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384307\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37.png\" alt=\"This picture in the style of Claude Monet illustrates the improvements of the new model.\" width=\"1554\" height=\"818\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37.png 1554w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-280x147.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-256x135.png 256w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-513x270.png 513w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-1536x809.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.09.37-796x419.png 796w\"\/><\/noscript><\/figure>\n<p>DALL-E-2 adds enhanced textual comprehension, faster image generation, and four times greater resolution.<\/p>\n<p dir=\"ltr\" role=\"presentation\"><span>\u201cWhen <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/download-scripts-themes-apps\/\" data-internallinksmanager029f6b8e52c=\"9\" title=\"Download Scripts &amp; Themes &amp; Apps\" target=\"_blank\" rel=\"noopener\">app<\/a>roaching DALL-E 2 we focused on improving the image resolution quality and improving latency, rather than building a bigger system,\u201d OpenAI researcher Aditya Ramesh told TNW.<\/span><\/p>\n<blockquote class=\"twitter-tweet\" data-width=\"500\" data-dnt=\"true\">\n<p lang=\"en\" dir=\"ltr\">Animal helicopter chimeras generated with DALL\u00b7E 2: <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/t.co\/5b8a9iq3k9\">pic.twitter.com\/5b8a9iq3k9<\/a><\/p>\n<p>\u2014 Aditya Ramesh (@model_mechanic) <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/twitter.com\/model_mechanic\/status\/1511868139583139845?ref_src=twsrc%5Etfw\">April 7, 2022<\/a><\/p>\n<\/blockquote>\n<p>The new tool also introduces two extra capabilities: reinterperations of existing images and an\u00a0editing feature called inpainting.<\/p>\n<p>Inpainting makes edits to an existing image\u00a0by analyzing a natural language caption.<\/p>\n<p>It can add and remove components, while integrating the expected changes to shadows, reflections, and textures.<\/p>\n<figure class=\"post-image post-mediaBleed aligncenter\"><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384310 js-lazy\" alt=\"DALL\u00b7E 2 can make realistic edits to existing images from a natural language caption. It can add and remove elements while taking shadows, reflections, and textures into account.\" width=\"1552\" height=\"750\" sizes=\"auto, (max-width: 1552px) 100vw, 1552px\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43.png\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43.png 1552w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-280x135.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-270x130.png 270w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-540x261.png 540w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-1536x742.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-796x385.png 796w\"\/><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2022%2F04%2F08%2Fopenai-dalle-2-text-to-image-generator-shows-ai-could-transform-design%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: In this example, a corgi is placed in the user\u2019s choice of location. Credit: OpenAI\" data-title=\"Share In this example, a corgi is placed in the user\u2019s choice of location. Credit: OpenAI on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share In this example, a corgi is placed in the user\u2019s choice of location. Credit: OpenAI on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>In this example, a corgi is placed in the user\u2019s choice of location. Credit: OpenAI<\/figcaption><noscript><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384310\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43.png\" alt=\"DALL\u00b7E 2 can make realistic edits to existing images from a natural language caption. It can add and remove elements while taking shadows, reflections, and textures into account.\" width=\"1552\" height=\"750\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43.png 1552w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-280x135.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-270x130.png 270w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-540x261.png 540w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-1536x742.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-14.12.43-796x385.png 796w\"\/><\/noscript><\/figure>\n<p>DALL\u00b7E 2 was trained on pairs of images and their corresponding captions, which taught the model about the relationships between pictures and words.<\/p>\n<p>New images are generated through a process called diffusion.<\/p>\n<p>This begins with a pattern of random dots. The system then gradually transforms the pattern into a picture when it recognizes specific aspects of that image.<\/p>\n<p>\u00a0<\/p>\n<figure class=\"post-image post-mediaBleed aligncenter\"><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384266 js-lazy\" alt=\"DALL-E 2 can combine concepts, attributes, and styles in its creations. \" width=\"1542\" height=\"914\" sizes=\"auto, (max-width: 1542px) 100vw, 1542px\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15.png\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15.png 1542w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-280x166.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-228x135.png 228w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-456x270.png 456w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-1536x910.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-796x472.png 796w\"\/><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2022%2F04%2F08%2Fopenai-dalle-2-text-to-image-generator-shows-ai-could-transform-design%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: DALL-E 2 can combine concepts, attributes, and styles in its creations. Credit: OpenAI\" data-title=\"Share DALL-E 2 can combine concepts, attributes, and styles in its creations. Credit: OpenAI on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share DALL-E 2 can combine concepts, attributes, and styles in its creations. Credit: OpenAI on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>DALL-E 2 can combine concepts, attributes, and styles in its creations. Credit: OpenAI<\/figcaption><noscript><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384266\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15.png\" alt=\"DALL-E 2 can combine concepts, attributes, and styles in its creations. \" width=\"1542\" height=\"914\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15.png 1542w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-280x166.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-228x135.png 228w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-456x270.png 456w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-1536x910.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-12.31.15-796x472.png 796w\"\/><\/noscript><\/figure>\n<p>Some of DALL-E 2\u2019s creations look almost too good to be true. Yet the researchers say\u00a0the system tends to generate visually coherent images for most captions that people try.<\/p>\n<p>The above pictures of an astronaut, for example, were curated from a set of nine produced by the model. Prafulla Dhariwal a research scientist at OpenAI, said the results are <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/general\/\" data-internallinksmanager029f6b8e52c=\"3\" title=\"General\" target=\"_blank\" rel=\"noopener\">general<\/a>ly consistent:<\/p>\n<blockquote><p>Sometimes, it can be helpful to iterate with the model in a feedback loop by modifying the prompt based on its interpretation of the previous one or by trying a different style like \u2018an oil painting,\u2019 \u2018digital art,\u2019 \u2018a photo,\u2019 \u2018an emoji,\u2019 etcetera. This can be helpful for achieving a desired style or aesthetic.<\/p>\n<\/blockquote>\n<figure class=\"post-image post-mediaBleed aligncenter\"><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384276 js-lazy\" alt=\"Budding fraudsters note that Klimt's less renowned Adele Bloch-Bauer I sold for $135 million in 2006. \" width=\"1548\" height=\"748\" sizes=\"auto, (max-width: 1548px) 100vw, 1548px\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22.png\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22.png 1548w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-280x135.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-270x130.png 270w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-540x261.png 540w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-1536x742.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-796x385.png 796w\"\/><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2022%2F04%2F08%2Fopenai-dalle-2-text-to-image-generator-shows-ai-could-transform-design%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: A reimagining of Gustav Klimt\u2019s \u201cThe Kiss.\u201d Budding fraudsters may recall that a Klimt painting sold for $150 million in 2016. Credit: OpenAI\" data-title=\"Share A reimagining of Gustav Klimt\u2019s \u201cThe Kiss.\u201d Budding fraudsters may recall that a Klimt painting sold for $150 million in 2016. Credit: OpenAI on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share A reimagining of Gustav Klimt\u2019s \u201cThe Kiss.\u201d Budding fraudsters may recall that a Klimt painting sold for $150 million in 2016. Credit: OpenAI on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>A reimagining of Gustav Klimt\u2019s \u201cThe Kiss.\u201d Budding fraudsters may recall that a Klimt painting <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/news.artnet.com\/market\/oprah-sells-famed-gustav-klimt-portrait-150-million-851537\">sold for $150 million<\/a> in 2016. Credit: OpenAI<\/figcaption><noscript><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-1384276\" src=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22.png\" alt=\"Budding fraudsters note that Klimt's less renowned Adele Bloch-Bauer I sold for $135 million in 2006. \" width=\"1548\" height=\"748\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22.png 1548w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-280x135.png 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-270x130.png 270w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-540x261.png 540w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-1536x742.png 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Screenshot-2022-04-08-at-13.05.22-796x385.png 796w\"\/><\/noscript><\/figure>\n<p><span style=\"font-size: 16px;\">DALL-E 2\u2019s potential uses are vast.<\/span><\/p>\n<p>Graphic designers, app developers, <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/social-mediaa\/\" data-internallinksmanager029f6b8e52c=\"1\" title=\"Social Media\" target=\"_blank\" rel=\"noopener\">media<\/a> outlets, architects, commercial illustrators, and product designers could all use the tool for inspiration, new creations, and editing.<\/p>\n<p>Commercial artists may be nervous about their future employment prospects. Ramesh acknowledges that many jobs could change:<\/p>\n<blockquote><p>We have seen AI be a good tool for people in the creative space. For example, as photo editing software has become more powerful and accessible it has allowed more people to enter the photography field. In recent years, we\u2019ve also seen artists use AI to create new kinds of art.<\/p>\n<p>It\u2019s hard to predict the future, but we do know AI will have an impact on jobs much like personal computers did. The nature of many jobs will change, jobs that never existed before will be created, and others may be eliminated.<\/p>\n<\/blockquote>\n<blockquote class=\"twitter-tweet\" data-width=\"500\" data-dnt=\"true\">\n<p lang=\"en\" dir=\"ltr\">Created with DALL\u00b7E 2 by <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/twitter.com\/OpenAI?ref_src=twsrc%5Etfw\">@OpenAI<\/a> <\/p>\n<p>Prompt: <br \/>&#8220;Mona Lisa is drinking wine with da Vinci.&#8221;<\/p>\n<p>\/\/ Even if we don&#8217;t see Maestro, the composition is perfect. Note the horizontal level of liquid in the glass.<\/p>\n<p>Made with <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/twitter.com\/hashtag\/DALLE?src=hash&amp;ref_src=twsrc%5Etfw\">#DALLE<\/a> \/\/ <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/twitter.com\/hashtag\/DALLEmerz?src=hash&amp;ref_src=twsrc%5Etfw\">#DALLEmerz<\/a> <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/t.co\/wk8Kf6DKcd\">pic.twitter.com\/wk8Kf6DKcd<\/a><\/p>\n<p>\u2014 Merzmensch Kosmopol (@Merzmensch) <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/twitter.com\/Merzmensch\/status\/1511740044259778567?ref_src=twsrc%5Etfw\">April 6, 2022<\/a><\/p>\n<\/blockquote>\n<p>\u00a0<\/p>\n<p>The system hasn\u2019t yet been released to the public. OpenAI CEO Sam Altman hopes to launch the product this summer, but the researchers first want to investigate the risks.<\/p>\n<p>They plan to integrate safeguards that prevent the system from generating<span style=\"color: #000000;\"> <\/span>deceptive and otherwise harmful content.<\/p>\n<p>In addition, DALL\u00b7E 2 inherits various biases from its training data \u2014 and its outputs sometimes reinforce societal stereotypes.<\/p>\n<p>The team has already removed explicit content from the training data and banned violent, hateful, and adult content in their <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/labs.openai.com\/policies\/content-policy\">content policy<\/a>.<\/p>\n<p>If filters identify images and text prompts that break the rules, the system won\u2019t generate the outputs. <span>Automated and human monitoring systems have also been\u00a0implemented as safeguards against misuse.<\/span><\/p>\n<p>\u00a0<\/p>\n<blockquote class=\"instagram-media\" style=\"background: #FFF; border: 0; border-radius: 3px; box-shadow: 0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width: 540px; min-width: 326px; padding: 0; width: calc(100% - 2px);\" data-instgrm-captioned=\"\" data-instgrm-permalink=\"https:\/\/www.instagram.com\/p\/CcAtEDVlL5G\/?utm_source=ig_embed&amp;utm_campaign=loading\" data-instgrm-version=\"14\">\n<\/blockquote>\n<p>Altman believes DALL-E\u2019s mechanism could change how we interact with machines.<\/p>\n<p>\u201cThis is another example of what I think is going to be a new computer interface trend: you say what you want in natural language or with contextual clues, and the computer does it,\u201d he said in <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/blog.samaltman.com\/dall-star-e-2\">a blogpost<\/a>.<\/p>\n<p>DALL-E may also boost our understanding of how AI sees the world. OpenAI hopes this helps them create systems that benefit humanity \u2014 and aren\u2019t manipulated to foster hatred and deception.\n                        <\/p><\/div>\n<p><script async src=\"\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><script async defer src=\"https:\/\/platform.instagram.com\/en_US\/embeds.js\"><\/script><\/p>\n<blockquote><p><strong><span style=\"color: #ff6600;\">If you liked the article, do not forget to share it with your friends. Follow us on\u00a0<span style=\"color: #ff0000;\"><a style=\"color: #ff0000;\" href=\"https:\/\/news.google.com\/publications\/CAAqBwgKMLG0nwswvr63Aw\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\">For forums sites go to <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/forum.buradabiliyorum.com\/\" target=\"_blank\" rel=\"noopener\">Forum.BuradaBiliyorum.Com<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\"><strong>If you want to read more like this article, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/en.buradabiliyorum.com\/technology\/\" target=\"_blank\" rel=\"noopener\">Technology category.<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/thenextweb.com\/news\/openai-dalle-2-text-to-image-generator-shows-ai-could-transform-design\" target=\"_blank\" rel=\"noopener\">Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;OpenAI\u2019s new image generator sparks both excitement and fear&#8221; OpenAI has unveiled a new AI tool that turns text into images \u2014 and the results are stunning. Named DALL-E 2, the system is the successor to a model unveiled last year. While its predecessor generated some impressive outputs, the new version is a major upgrade&#8230;.<\/p>\n","protected":false},"author":1,"featured_media":428803,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/img-cdn.tnwcdn.com\/image\/neural?filter_last=1&fit=1280,640&url=https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/04\/Untitled-design-4.jpg&signature=e7f1447312b512b0c9a34730f1935788","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[],"class_list":["post-428802","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/428802","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=428802"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/428802\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/428803"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=428802"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=428802"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=428802"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}