{"id":16820,"date":"2024-07-31T09:48:32","date_gmt":"2024-07-31T01:48:32","guid":{"rendered":"https:\/\/www.1ai.net\/?p=16820"},"modified":"2024-07-31T10:13:11","modified_gmt":"2024-07-31T02:13:11","slug":"%e7%94%9f%e6%95%b0%e7%a7%91%e6%8a%80ai%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e6%a8%a1%e5%9e%8b-vidu-%e5%ae%98%e7%bd%91%e5%85%a8%e7%90%83%e4%b8%8a%e7%ba%bf-%e5%8f%af%e5%b0%86%e5%9b%be-%e6%96%87%e8%bd%ac","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/16820.html","title":{"rendered":"Vidu, the AI video generation model of Shengshu Technology, is now available globally, and can convert images\/text into videos."},"content":{"rendered":"<p data-pm-slice=\"0 0 []\">today,<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%8c%97%e4%ba%ac%e7%94%9f%e6%95%b0%e7%a7%91%e6%8a%80\" title=\"[Sees articles with tags in Beijing]\" target=\"_blank\" >Beijing Biodata Technology<\/a>Announce<a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e6%a8%a1%e5%9e%8b\" title=\"[SEE ARTICLES WITH [AI VIDEO GENERATION MODEL] LABELS]\" target=\"_blank\" >AI video generation model<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/vidu\" title=\"[See articles with [Vidu] label]\" target=\"_blank\" >Vidu<\/a> The official website is launched globally. Vidu is a model that uses artificial intelligence technology to generate videos from text or pictures.<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-16821\" title=\"get-954\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/get-954.jpg\" alt=\"get-954\" width=\"1000\" height=\"526\" \/><\/div>\n<p data-track=\"79\">In April this year, Shengshu Technology and Tsinghua University jointly released China&#039;s first<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a7%86%e9%a2%91%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with tags]\" target=\"_blank\" >Video mockup<\/a>\u2014 \u201cVidu\u201d \u2014 marks an important step in China's video-generation technology\u3002<\/p>\n<p data-track=\"80\">\u201cVidu\u201d uses a team-generated U-ViT structure that integrates Diffusion and Transformer technology. This innovative big video model can quickly generate up to 16 seconds, 1080 P-high-resolution videos, while also demonstrating great imagination and creativity based on simulation of the real physical world. Its multiple lens generation capacity and spatial and temporal consistency are prominent features of \u201cVidu\u201d\u3002<\/p>\n<p data-track=\"81\">Since its launch, the Vidu has made a remarkable breakthrough on a global scale, with its performance at the highest international level and continuing to evolve and optimize. This achievement was the result of a deep accumulation of teams in the field of machine learning and large multi-mode models in Bayes, as well as a number of original results\u3002<\/p>\n<p data-track=\"82\">With a deep understanding of the U-ViT architecture and extensive engineering and data experience, the team quickly managed to capture the key technical challenges of long video expression and processing, and successfully developed the \"Vidu\" video megamodel. Vidu has achieved significant results in improving video coherence and dynamics, and has contributed to the development of video-processing technologies\u3002<\/p>\n<p data-track=\"83\">Experience address:<a href=\"https:\/\/www.1ai.net\/en\/16856.html\/\">https:\/\/www.1ai.net\/16856.html\u00a0<\/a><\/p>\n<p>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>Today, Beijing Student Science and Technology announced that the AI Video Generation Model, Vidu Network, is online worldwide. Vidu is a model that uses artificial intelligence technology to generate video through text or pictures. In April this year, Student Science and Technology and the University of Chinghua jointly released China's first big video model, \u201cVidu\u201d, which marks an important step forward in China's video-generation technology. \u201cVidu\u201d uses a team-generated U-ViT structure that integrates Diffusion and Transformer technology. This innovative video big model can quickly generate up to 16 seconds, 1080 P-high-level video, and at the same time display a very high level of imagination and imagination based on simulation of the real physical world<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3801,2417,3802,980],"collection":[],"class_list":["post-16820","post","type-post","status-publish","format-standard","hentry","category-news","tag-ai","tag-vidu","tag-3802","tag-980"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16820","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=16820"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16820\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=16820"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=16820"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=16820"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=16820"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}