{"id":200786,"date":"2024-12-04T18:23:47","date_gmt":"2024-12-05T00:23:47","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2024\/12\/deepminds-genie-2-can-generate-interactive-worlds-that-look-like-video-games"},"modified":"2024-12-04T18:23:47","modified_gmt":"2024-12-05T00:23:47","slug":"deepminds-genie-2-can-generate-interactive-worlds-that-look-like-video-games","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2024\/12\/deepminds-genie-2-can-generate-interactive-worlds-that-look-like-video-games","title":{"rendered":"DeepMind\u2019s Genie 2 can generate interactive worlds that look like video games"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/deepminds-genie-2-can-generate-interactive-worlds-that-look-like-video-games2.jpg\"><\/a><\/p>\n<p>DeepMind, Google\u2019s AI research org, has unveiled a <a href=\"https:\/\/deepmind.google\/discover\/blog\/genie-2-a-large-scale-foundation-world-model\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">model<\/a> that can generate an \u201cendless\u201d variety of playable 3D worlds.<\/p>\n<p>Called Genie 2, the model \u2014 the successor to DeepMind\u2019s Genie, which was released earlier this year \u2014 can generate an interactive, real-time scene from a single image and text description (e.g. \u201cA cute humanoid robot in the woods\u201d). In this way, it\u2019s similar to models under development by Fei-Fei Li\u2019s company, <a href=\"https:\/\/techcrunch.com\/2024\/12\/02\/world-labs-ai-can-generate-interactive-3d-scenes-from-a-single-photo\/\">World Labs<\/a>, and Israeli startup <a href=\"https:\/\/techcrunch.com\/2024\/10\/31\/decarts-ai-simulates-a-real-time-playable-version-of-minecraft\/\">Decart<\/a>.<\/p>\n<p>DeepMind claims that Genie 2 can generate a \u201cvast diversity of rich 3D worlds,\u201d including worlds in which users can take actions like jumping and swimming by using a mouse or keyboard. Trained on videos, the model\u2019s able to simulate object interactions, animations, lighting, physics, reflections, and the behavior of \u201cNPCs.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"<p>DeepMind, Google\u2019s AI research org, has unveiled a model that can generate an \u201cendless\u201d variety of playable 3D worlds. Called Genie 2, the model \u2014 the successor to DeepMind\u2019s Genie, which was released earlier this year \u2014 can generate an interactive, real-time scene from a single image and text description (e.g. \u201cA cute humanoid robot [\u2026]<\/p>\n","protected":false},"author":396,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[219,6],"tags":[],"class_list":["post-200786","post","type-post","status-publish","format-standard","hentry","category-physics","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/200786","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\/396"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=200786"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/200786\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=200786"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=200786"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=200786"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}