{"id":599279,"date":"2026-04-22T09:02:11","date_gmt":"2026-04-22T09:02:11","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/599279\/"},"modified":"2026-04-22T09:02:11","modified_gmt":"2026-04-22T09:02:11","slug":"openai-beefs-up-chatgpts-image-generation-model","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/599279\/","title":{"rendered":"OpenAI Beefs Up ChatGPT\u2019s Image Generation Model"},"content":{"rendered":"<p>OpenAI launched a new image generation AI model on Tuesday, dubbed ChatGPT Images 2.0. This model can generate more than one image from a single prompt, like an entire study booklet, as well as output text, including in non-English languages like Chinese and Hindi. This release is available globally for <a href=\"https:\/\/www.wired.com\/tag\/chatgpt\/\" class=\"text link\" rel=\"nofollow noopener\" target=\"_blank\">ChatGPT<\/a> and <a href=\"https:\/\/www.wired.com\/story\/openai-codex-race-claude-code\/\" class=\"text link\" rel=\"nofollow noopener\" target=\"_blank\">Codex<\/a> users, with a more powerful version available for paying subscribers.<\/p>\n<p class=\"paywall\">When any major AI company releases a new image model, it can revive interest and boost usage, especially if social media users adopt a meme-able trend, transforming images of themselves. Last year, Google&#8217;s launch of the Nano Banana model was a major moment for the company, especially when users started posting <a data-offer-url=\"https:\/\/www.theverge.com\/news\/778106\/google-gemini-nano-banana-image-editor\" class=\"external-link text link\" data-event-click=\"{&quot;element&quot;:&quot;ExternalLink&quot;,&quot;outgoingURL&quot;:&quot;https:\/\/www.theverge.com\/news\/778106\/google-gemini-nano-banana-image-editor&quot;}\" href=\"https:\/\/www.theverge.com\/news\/778106\/google-gemini-nano-banana-image-editor\" rel=\"nofollow noopener\" target=\"_blank\">hyperrealistic figurines<\/a> of themselves online. Earlier this year, ChatGPT Images made waves on social media as users shared <a data-offer-url=\"https:\/\/www.fastcompany.com\/91487696\/chatgpt-caricature-trend-tiktok-ai-generated-pictures\" class=\"external-link text link\" data-event-click=\"{&quot;element&quot;:&quot;ExternalLink&quot;,&quot;outgoingURL&quot;:&quot;https:\/\/www.fastcompany.com\/91487696\/chatgpt-caricature-trend-tiktok-ai-generated-pictures&quot;}\" href=\"https:\/\/www.fastcompany.com\/91487696\/chatgpt-caricature-trend-tiktok-ai-generated-pictures\" rel=\"nofollow noopener\" target=\"_blank\">AI-generated caricatures<\/a>.<\/p>\n<p><img decoding=\"async\" alt=\"Image may contain Publication Advertisement Poster Face Head Person Adult Wedding Accessories and Sunglasses\" loading=\"lazy\" class=\"ResponsiveImageContainer-dkeESL cQPiWi responsive-image__image\"   src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/04\/A%20-%20ChatGPT%20Images%202,%20From%20OpenAI_.jpg\"\/>What\u2019s Different?<\/p>\n<p class=\"paywall\">Since the new model can tap into ChatGPT\u2019s \u201creasoning\u201d capabilities, Images 2.0 can search the internet for recent information and generate more than one image at a time. In essence, the bot can use additional steps to output more thorough generations from a single prompt. Images 2.0 also has a more recent knowledge cutoff date: December 2025.<\/p>\n<p class=\"paywall\">This also means that outputs from the new model are more granular. For example, I generated an infographic with San Francisco\u2019s weather forecast for the next day, as well as activities worth doing. The image ChatGPT generated included accurate weather details for the rainy day, along with accurate-looking drawings of the Ferry Building, Castro Theater, Painted Ladies houses, and Transamerica Pyramid.<\/p>\n<p class=\"paywall\">Additionally, Images 2.0 is more customizable for users who want unique aspect ratios for image outputs. The new model can generate images ranging from 3:1 wide to 1:3 tall, and users can adjust the image\u2019s size as part of their prompt to the AI tool.<\/p>\n<p>First Impressions<\/p>\n<p class=\"paywall\">After a few hours of generating images with the new model, I was generally impressed with the text rendering capabilities, in English at least. Not that long ago, image outputs featuring text, from any of the major models, often included numerous malformed characters or words with errant extra letters. ChatGPT <a href=\"https:\/\/www.wired.com\/story\/how-to-use-chatgpt-dalle-3-create-images\/\" class=\"text link\" rel=\"nofollow noopener\" target=\"_blank\">struggled to label<\/a> images accurately two years prior, so the cleaner, more complex outputs from Images 2.0 are a sign of continued improvement. Google has also focused on improving image outputs featuring text in its <a href=\"https:\/\/www.wired.com\/story\/google-nano-banana-2-ai-image-generator-hands-on\/\" class=\"text link\" rel=\"nofollow noopener\" target=\"_blank\">recent iterations<\/a> of Nano Banana.<\/p>\n<p><img decoding=\"async\" alt=\"Image may contain Advertisement Poster Person Beverage Coffee Coffee Cup Clothing Coat and Jacket\" loading=\"lazy\" class=\"ResponsiveImageContainer-dkeESL cQPiWi responsive-image__image\"   src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/04\/C%20-%20ChatGPT%20Image%202,%20From%20Reece%20Rogers.jpg\"\/><\/p>\n<p>AI-GENERATED BY REECE ROGERS<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI launched a new image generation AI model on Tuesday, dubbed ChatGPT Images 2.0. This model can generate&hellip;\n","protected":false},"author":2,"featured_media":599280,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[31],"tags":[5084,181,3195,1873,1283,74],"class_list":["post-599279","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-algorithms","tag-artificial-intelligence","tag-chatgpt","tag-generative-ai","tag-openai","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/599279","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=599279"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/599279\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/599280"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=599279"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=599279"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=599279"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}