{"id":143939,"date":"2022-08-14T19:02:40","date_gmt":"2022-08-15T00:02:40","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2022\/08\/this-startup-is-setting-a-dall-e-2-like-ai-free-consequences-be-damned"},"modified":"2022-08-14T19:02:40","modified_gmt":"2022-08-15T00:02:40","slug":"this-startup-is-setting-a-dall-e-2-like-ai-free-consequences-be-damned","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2022\/08\/this-startup-is-setting-a-dall-e-2-like-ai-free-consequences-be-damned","title":{"rendered":"This startup is setting a DALL-E 2-like AI free, consequences be damned"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/this-startup-is-setting-a-dall-e-2-like-ai-free-consequences-be-damned.jpg\"><\/a><\/p>\n<p>DALL-E 2, OpenAI\u2019s powerful text-to-image AI system, can create photos in the style of cartoonists, 19th century daguerreotypists, stop-motion animators and more. But it has an important, artificial limitation: a filter that prevents it from creating images depicting public figures and content deemed too toxic.<\/p>\n<p>Now an open source alternative to DALL-E 2 is on the cusp of being released, and it\u2019ll have no such filter.<\/p>\n<p>London-and Los Altos-based startup <a href=\"https:\/\/stability.ai\/\" target=\"_blank\" rel=\"noopener\">Stability AI<\/a> this week announced the <a href=\"https:\/\/stability.ai\/academia-access-form\" target=\"_blank\" rel=\"noopener\">release<\/a> of a <a href=\"https:\/\/techcrunch.com\/tag\/dall-e\/\">DALL-E 2<\/a>-like system, Stable Diffusion, to just over a thousand researchers ahead of a public launch in the coming weeks. A collaboration between Stability AI, media creation company RunwayML, Heidelberg University researchers and the research groups EleutherAI and LAION, Stable Diffusion is designed to run on most high-end consumer hardware, generating 512\u00d7512-pixel images in just a few seconds given any text prompt.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>DALL-E 2, OpenAI\u2019s powerful text-to-image AI system, can create photos in the style of cartoonists, 19th century daguerreotypists, stop-motion animators and more. But it has an important, artificial limitation: a filter that prevents it from creating images depicting public figures and content deemed too toxic. Now an open source alternative to DALL-E 2 is on [\u2026]<\/p>\n","protected":false},"author":556,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-143939","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/143939","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\/556"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=143939"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/143939\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=143939"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=143939"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=143939"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}