{"id":4709,"date":"2024-03-01T09:32:47","date_gmt":"2024-03-01T01:32:47","guid":{"rendered":"https:\/\/www.1ai.net\/?p=4709"},"modified":"2024-03-01T09:32:47","modified_gmt":"2024-03-01T01:32:47","slug":"openai%e6%88%96%e7%94%a83d%e5%bc%95%e6%93%8e-%e8%99%9a%e5%b9%bb%e5%bc%95%e6%93%8e%e8%ae%ad%e7%bb%83%e8%a7%86%e9%a2%91%e6%a8%a1%e5%9e%8bsora","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/4709.html","title":{"rendered":"OpenAI may use 3D engine\/Unreal Engine to train video model Sora"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/openai\" title=\"[View articles tagged with [OpenAI]]\" target=\"_blank\" >OpenAI<\/a>Recently published several<a href=\"https:\/\/www.1ai.net\/en\/tag\/sora\" title=\"[See articles with [Sora] label]\" target=\"_blank\" >Sora<\/a>The resulting videos, which showcase stunning 3D effects, include everything from diving to exploring a shipwreck to dioramas depicting serene scenes from Japan\u2019s Edo period.<\/p>\n<p>In addition, Sora also demonstrated some new features, such as seamless transitions. This means that the two input videos can be gradually interpolated to present a smoother transition effect. Some netizens began to discuss the source of the training data behind Sora&#039;s generated videos. The mainstream view is that Sora may have used<a href=\"https:\/\/www.1ai.net\/en\/tag\/3d%e5%bc%95%e6%93%8e\" title=\"[SEES ARTICLES WITH LABELS OF 3D ENGINE]\" target=\"_blank\" >3D Engine<\/a>or<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%99%9a%e5%b9%bb%e5%bc%95%e6%93%8e\" title=\"[Sees articles with labels]\" target=\"_blank\" >Unreal Engine<\/a>Conduct training.<\/p>\n<p class=\"article-content__img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-4710\" title=\"202305091556160776_8\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/03\/202305091556160776_8.jpg\" alt=\"202305091556160776_8\" width=\"695\" height=\"469\" \/><\/p>\n<p>Source Note: The image is generated by AI, and the image is authorized by Midjourney<\/p>\n<p>These newly released videos once again highlight OpenAI&#039;s leading position in the field of artificial intelligence and their continuous efforts in developing cutting-edge technologies. Through continuous optimization and updates, Sora&#039;s generative video technology has reached an amazing level, bringing users a more vivid and attractive visual experience.<\/p>\n<p>OpenAI&#039;s Sora video generation technology not only demonstrates its innovative capabilities in the field of artificial intelligence, but also shows us the potential of the future in digital media and visual effects. These videos are not only visually stunning, but also spark people&#039;s imagination of the infinite potential of artificial intelligence technology in the fields of creation and entertainment.<\/p>","protected":false},"excerpt":{"rendered":"<p>OpenAI recently released several videos by Sora showing the amazing 3D effect. These videos are rich and include diving to explore shipwrecks, and a 3D model of the quiet scene of the Edo era in Japan. In addition, Sora has shown some new features, such as seamless connections. This means that a gradual interpolation between two input videos is possible, with a more fluid transition effect. Some netizens have begun to discuss the sources of training data behind Sora's video generation, and the prevailing view is that Sora may have used 3D or fictional engines for training. The newly released videos highlight once again the leading position of OpenAI in the area of artificial intelligence and their presence in the field of artificial intelligence<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1430,190,1249,1431],"collection":[],"class_list":["post-4709","post","type-post","status-publish","format-standard","hentry","category-news","tag-3d","tag-openai","tag-sora","tag-1431"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/4709","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=4709"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/4709\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=4709"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=4709"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=4709"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=4709"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}