{"id":9261,"date":"2024-04-28T09:31:02","date_gmt":"2024-04-28T01:31:02","guid":{"rendered":"https:\/\/www.1ai.net\/?p=9261"},"modified":"2024-04-28T14:45:53","modified_gmt":"2024-04-28T06:45:53","slug":"%e6%b8%85%e5%8d%8e%e5%9b%a2%e9%98%9f%e5%9b%bd%e4%ba%a7sora%e7%81%ab%e4%ba%86%ef%bc%9a%e7%94%9f%e6%95%b0%e7%a7%91%e6%8a%80%e5%8f%91%e5%b8%83%e8%a7%86%e9%a2%91%e5%a4%a7%e6%a8%a1","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/9261.html","title":{"rendered":"Tsinghua team's domestically produced "Sora" is popular: Shengshu Technology releases a large video model Vidu"},"content":{"rendered":"

At the Future Artificial Intelligence Pioneer Forum of Zhongguancun Forum, Shengshu Technology andTsinghua University<\/a>Join hands and officially launch ChinaThe first<\/span>With long duration, high consistency and high dynamicsVideo mockup<\/a>\u2014\u2014"Vidu<\/a>\u201d.<\/p>\n

The core of this leading video model lies in the U-ViT architecture that is a fusion of Diffusion and Transformer. It can not only generate a 16-second high-definition video with a resolution of 1080P in one click, but also show amazing imagination while simulating the real physical world. Multi-lens generation and high consistency of time and space are the unique charms of Vidu.<\/p>\n

\"OpenAI<\/p>\n

It is worth mentioning that Vidu has made significant breakthroughs worldwide since its release.top notch<\/span>The level is comparable and is still being iterated and optimized. This achievement is inseparable from the team's deep accumulation and many original achievements in the fields of Bayesian machine learning and multimodal large models.<\/p>\n

In particular, the U-ViT architecture proposed by the team in September 2022 is the globalThe first<\/span>The fusion architecture of Diffusion and Transformer laid a solid foundation for the birth of Vidu. Subsequently, in March 2023, the team took the lead again and open-sourced the multimodal diffusion model UniDiffuser based on the U-ViT fusion architecture, successfully verifying the large-scale scalability of the U-ViT architecture.<\/p>\n

Based on the in-depth understanding of the U-ViT architecture and rich engineering and data experience, the team overcame many key technical challenges in long video representation and processing in a very short time, and developed the Vidu video model. This model performs well in improving video coherence and dynamics, further promoting the development of video processing technology.<\/p>\n

The launch of Vidu not only once again verifies the excellent performance of the U-ViT fusion architecture in large-scale visual tasks, but also demonstrates Shengshu Technology's continuous innovation capabilities and industry-leading position in the field of multimodal native large models. As a universal visual model, Vidu can generate more diverse and longer video content, and its flexible architecture will also provide unlimited possibilities for future compatibility with a wider range of modalities and expanding the boundaries of multimodal general capabilities.<\/p>\n

Application address:<\/strong><\/p>\n

https:\/\/shengshu.feishu.cn\/share\/base\/form\/shrcnybSDE4Id1JnA5EQ0scv1Ph<\/p>","protected":false},"excerpt":{"rendered":"

In the Future Artificial Intelligence Pioneer Forum of Zhongguancun Forum, BioDigital Technology, together with Tsinghua University, formally launched China's first video big model with long duration, high consistency and high dynamics - \"Vidu\". The core of this era-leading video model lies in the team's original Diffusion and Transformer fusion of U-ViT architecture. It can not only generate HD videos up to 16 seconds long and 1080P in definition with one click, but also show amazing imagination while simulating the real physical world. Multi-camera generation and high degree of temporal and spatial consistency are the unique charms of Vidu. It is worth mentioning that since its release, Vidu has made remarkable breakthroughs around the world, its performance is on par with the international top level, and it is still iterating!<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[2417,1712,980],"collection":[],"class_list":["post-9261","post","type-post","status-publish","format-standard","hentry","category-news","tag-vidu","tag-1712","tag-980"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/9261","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=9261"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/9261\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=9261"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=9261"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=9261"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=9261"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}