{"id":14818,"date":"2024-07-05T09:21:50","date_gmt":"2024-07-05T01:21:50","guid":{"rendered":"https:\/\/www.1ai.net\/?p=14818"},"modified":"2024-07-05T09:21:50","modified_gmt":"2024-07-05T01:21:50","slug":"%e8%81%94%e5%8f%91%e7%a7%91%e4%b8%8e%e5%bf%ab%e6%89%8b%e6%8e%a8%e5%87%ba%e7%ab%af%e4%be%a7%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e6%8a%80%e6%9c%af%ef%bc%8c%e6%94%af%e6%8c%81%e5%a4%a9%e7%8e%91-9300-8300","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/14818.html","title":{"rendered":"MediaTek and Kuaishou launch end-to-end video generation technology, supporting Dimensity 9300\/8300 mobile platforms"},"content":{"rendered":"<p data-vmark=\"46d8\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%81%94%e5%8f%91%e7%a7%91\" title=\"[Sees articles with [United Nations Development Programme] label]\" target=\"_blank\" >MediaTek<\/a>and<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bf%ab%e6%89%8b\" title=\"[See articles with [fast-hand] labels]\" target=\"_blank\" >quick worker<\/a>Yesterday, we jointly announced the launch of the high-efficiency end-side<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e6%8a%80%e6%9c%af\" title=\"[Sees articles with tags]\" target=\"_blank\" >Video Generation Technology<\/a>.<\/p>\n<p data-vmark=\"4e05\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-14819\" title=\"0ce29c3d-1149-423e-8169-7da6c7d87bf6.jpg@s_2w_820h_461\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/0ce29c3d-1149-423e-8169-7da6c7d87bf6.jpg@s_2w_820h_461.jpg\" alt=\"0ce29c3d-1149-423e-8169-7da6c7d87bf6.jpg@s_2w_820h_461\" width=\"820\" height=\"461\" \/><\/p>\n<p data-vmark=\"eba3\">This technology is a continuation and improvement of the video generation technology that debuted at the 2024 World Mobile Communications Conference. It combines Kuaishou\u2019s AI model I2V (image to video) Adapter with<strong>MediaTek Dimensity 9300 and Dimensity 8300 mobile platforms<\/strong>AI computing power,<strong>Generate dynamic video from static images on the client side<\/strong>.<\/p>\n<p data-vmark=\"c7b8\">With this technology, users only need to select an image on their device and the app can<strong>Identify people and scenes in photos<\/strong>, generate natural and smooth videos, and improve the creative expression and efficiency of video production.<\/p>\n<p data-vmark=\"97cf\">I2V-Adapter is a lightweight adapter module proposed by the Kuaishou AI team that is suitable for the Stable Diffusion-based Vincent video diffusion model and is specifically used for image-to-video generation tasks.<\/p>\n<p data-vmark=\"4acb\">According to reports, MediaTek Dimensity 9300 and Dimensity 8300 mobile platforms integrate NPU (neural network processing unit) designed for generative AI. NPU can accelerate the calculation of AI models. Combined with the adaptation and optimization of Kuaishou I2V Adapter model, it can achieve faster video generation speed while also having low power consumption characteristics.<\/p>\n<p data-vmark=\"cf82\">As previously reported by IT Home, at the Dimensity Developer Conference held in May, MediaTek, together with partners such as Alibaba Cloud, Baichuan Intelligence, Transsion, Zero One Things, OPPO, Honor, vivo, and Xiaomi, jointly launched the &quot;Dimensity AI Pioneer Plan&quot; to help developers build generative AI on terminal devices equipped with Dimensity chips.<\/p>","protected":false},"excerpt":{"rendered":"<p>MediaTek and Racer jointly announced yesterday the launch of an efficient end-side video generation technology. This technology is a continuation and enhancement of the video generation technology that was first unveiled at Mobile World Congress 2024, combining the I2V (image to video) Adapter, an AI model of Crypto, with the AI algorithms of MediaTek's Tenguet 9300 and Tenguet 8300 mobile platforms, to realize the generation of dynamic videos from static images on the end side. With this technology, users only need to select an image on the device, and the app can recognize the characters and scenes in the photo to generate a natural and smooth video, improving the creative performance and efficiency of video production. I2V-Adapter is an application proposed by Racer AI team for Stable Diffusel-based video production.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[2859,1591,3345],"collection":[],"class_list":["post-14818","post","type-post","status-publish","format-standard","hentry","category-news","tag-2859","tag-1591","tag-3345"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/14818","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=14818"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/14818\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=14818"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=14818"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=14818"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=14818"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}