{"id":10755,"date":"2024-02-16T11:24:44","date_gmt":"2024-02-16T09:24:44","guid":{"rendered":"https:\/\/forklog.com\/en\/openai-unveils-sora-enthusiasm-and-challenges\/"},"modified":"2024-02-16T11:24:44","modified_gmt":"2024-02-16T09:24:44","slug":"openai-unveils-sora-enthusiasm-and-challenges","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/openai-unveils-sora-enthusiasm-and-challenges\/","title":{"rendered":"OpenAI Unveils Sora: Enthusiasm and Challenges"},"content":{"rendered":"<p>On February 15, OpenAI introduced Sora, a new generative AI model that transforms text into video. The tool has generated excitement on social media, though it requires significant refinement before a full launch.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Introducing Sora, our text-to-video model.<\/p>\n<p>Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. <a href=\"https:\/\/t.co\/7j2JN27M3W\">https:\/\/t.co\/7j2JN27M3W<\/a><\/p>\n<p>Prompt: \u201cBeautiful, snowy\u2026 <a href=\"https:\/\/t.co\/ruTEWn87vf\">pic.twitter.com\/ruTEWn87vf<\/a><\/p>\n<p>\u2014 OpenAI (@OpenAI) <a href=\"https:\/\/twitter.com\/OpenAI\/status\/1758192957386342435?ref_src=twsrc%5Etfw\">February 15, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Sora can generate videos up to 60 seconds long with resolutions up to 1080p based on simple text prompts. These videos can include multiple characters, specific types of motion, and precise details of objects and backgrounds.<\/p>\n<p>The tool is based on research from GPT and DALL-E 3. It operates using a diffusion model\u2014transforming an initial image into <a href=\"https:\/\/ru.wikipedia.org\/wiki\/%D0%93%D0%B0%D1%83%D1%81%D1%81%D0%BE%D0%B2%D1%81%D0%BA%D0%B8%D0%B9_%D1%88%D1%83%D0%BC\">statistical noise<\/a> and then gradually removing this noise.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Announcing Sora \u2014 our model which creates minute-long videos from a text prompt: <a href=\"https:\/\/t.co\/SZ3OxPnxwz\">https:\/\/t.co\/SZ3OxPnxwz<\/a> <a href=\"https:\/\/t.co\/0kzXTqK9bG\">pic.twitter.com\/0kzXTqK9bG<\/a><\/p>\n<p>\u2014 Greg Brockman (@gdb) <a href=\"https:\/\/twitter.com\/gdb\/status\/1758193811489243408?ref_src=twsrc%5Etfw\">February 15, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Developers acknowledge that Sora still has several shortcomings. It struggles to accurately model the physics of complex scenes, often confusing cause and effect.<\/p>\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u201cFor example, a person might bite a cookie, but the bite mark might not appear,\u201d OpenAI explains.<\/p>\n<\/blockquote>\n<p>The tool also has issues with spatial details. The resulting video may not align with specified directions, mistaking right for left.<\/p>\n<p>Currently, Sora is available to a \u201cred team\u201d of testers, as well as select designers, artists, and filmmakers.<\/p>\n<h2 class=\"wp-block-heading\"><strong>Social Media Reaction<\/strong><\/h2>\n<p>The tool has captivated social media, trending on X with over 173,000 posts.<\/p>\n<p>To demonstrate the model&#8217;s capabilities, OpenAI CEO Sam Altman has begun accepting user requests for video generation. At the time of writing, he has shared a total of nine videos created by Sora.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"zxx\" dir=\"ltr\"><a href=\"https:\/\/t.co\/uCuhUPv51N\">https:\/\/t.co\/uCuhUPv51N<\/a> <a href=\"https:\/\/t.co\/nej4TIwgaP\">pic.twitter.com\/nej4TIwgaP<\/a><\/p>\n<p>\u2014 Sam Altman (@sama) <a href=\"https:\/\/twitter.com\/sama\/status\/1758218820542763012?ref_src=twsrc%5Etfw\">February 15, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>AI experts have noted that Sora&#8217;s capabilities are \u201cspeechless.\u201d<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">I don\u2019t even know what to say\u2026<\/p>\n<p>These clips generated by OpenAI\u2019s Sora model have me speechless.<\/p>\n<p>We knew good AI text-to-video would come, but this quickly? Unreal.<\/p>\n<p>We\u2019re stepping into a new world.<\/p>\n<p>Buckle up. <a href=\"https:\/\/t.co\/zP7b5fKw5x\">pic.twitter.com\/zP7b5fKw5x<\/a><\/p>\n<p>\u2014 Mckay Wrigley (@mckaywrigley) <a href=\"https:\/\/twitter.com\/mckaywrigley\/status\/1758237675847565328?ref_src=twsrc%5Etfw\">February 15, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>According to Nvidia senior research scientist Jim Fan, Sora is much more than just another \u201ccreative toy\u201d like DALL-E 3. He described it as a \u201cdata-driven physics engine,\u201d as the AI model not only generates abstract video but also intuitively creates the physics of objects within the scene.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">If you think OpenAI Sora is a creative toy like DALLE, \u2026 think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, &#8220;intuitive&#8221; physics, long-horizon reasoning, and semantic grounding, all\u2026 <a href=\"https:\/\/t.co\/pRuiXhUqYR\">pic.twitter.com\/pRuiXhUqYR<\/a><\/p>\n<p>\u2014 Jim Fan (@DrJimFan) <a href=\"https:\/\/twitter.com\/DrJimFan\/status\/1758210245799920123?ref_src=twsrc%5Etfw\">February 15, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Alongside this, some users have expressed concerns that tools like Sora could exacerbate the deepfake problem.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">OpenAI, the builders of ChatGPT, have built Sora. A text to video AI system that creates 60 sec videos. It\u2019s not yet available but is causing significant concern around its deep fake potential use. The issue isn\u2019t just video content but how it\u2019s used. <a href=\"https:\/\/t.co\/Qujz3TfeH2\">https:\/\/t.co\/Qujz3TfeH2<\/a><\/p>\n<p>\u2014 Ian McLintock (@ian_mcl) <a href=\"https:\/\/twitter.com\/ian_mcl\/status\/1758379840447697044?ref_src=twsrc%5Etfw\">February 16, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>One user suggested that major social networks should consider built-in protection against realistic fakes, highlighting the threat of substituting video evidence of crimes.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Open AI launched <a href=\"https:\/\/twitter.com\/hashtag\/Sora?src=hash&#038;ref_src=twsrc%5Etfw\">#Sora<\/a> that gives almost realistic text to video GAI:<br \/>1. Deep fake detection becomes super important against spread of misinformation (platforms like X should&#8217;ve in-built debunker of deep fakes)<br \/>2. Courts will have a hard time with video evidence as proof of crime<\/p>\n<p>\u2014 TheShunyaLab (@theshunyalab) <a href=\"https:\/\/twitter.com\/theshunyalab\/status\/1758391435131494505?ref_src=twsrc%5Etfw\">February 16, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Another user called for De-AI reverse engineering technology to prevent misinterpretation and misuse of content.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">This is amazing! But we badly need a De-AI reverse engineering technology to avoid misinterpretation and deepfake generation to avoid misuse.<a href=\"https:\/\/twitter.com\/hashtag\/Sora?src=hash&#038;ref_src=twsrc%5Etfw\">#Sora<\/a> <a href=\"https:\/\/twitter.com\/hashtag\/OpenAI?src=hash&#038;ref_src=twsrc%5Etfw\">#OpenAI<\/a> <a href=\"https:\/\/twitter.com\/hashtag\/AI?src=hash&#038;ref_src=twsrc%5Etfw\">#AI<\/a> <a href=\"https:\/\/twitter.com\/hashtag\/DeepFake?src=hash&#038;ref_src=twsrc%5Etfw\">#DeepFake<\/a> <a href=\"https:\/\/t.co\/hazxryNlHI\">https:\/\/t.co\/hazxryNlHI<\/a><\/p>\n<p>\u2014 Neeraj Chauriya?? (@neerajchauriya) <a href=\"https:\/\/twitter.com\/neerajchauriya\/status\/1758394270191636510?ref_src=twsrc%5Etfw\">February 16, 2024<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Previously, OpenAI began testing a \u201cmemory\u201d feature for the ChatGPT chatbot, which retains information discussed in conversations to enhance user interaction.<\/p>\n<p>Meanwhile, the company is actively countering the illegal use of its products.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>On February 15, OpenAI introduced Sora, a new generative AI model that transforms text into video. The tool has generated excitement on social media, though it requires significant refinement before a full launch. Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":10754,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"","news_style_id":"","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1190,1392],"class_list":["post-10755","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-openai","tag-video"],"aioseo_notices":[],"amp_enabled":true,"views":"71","promo_type":"","layout_type":"","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/10755","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=10755"}],"version-history":[{"count":0,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/10755\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/10754"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=10755"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=10755"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=10755"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}