在中关村论坛未来人工智能先锋论坛上，生数科技与清华大学共同宣布了一项重大突破——中国首个长时长、高一致性、高动态性视频大模型「Vidu」的正式发布。
这一创新性的模型融合了Diffusion与Transformer架构，被命名为U-ViT。它的独特之处在于能够支持一键生成长达16秒、分辨率高达1080P的高清视频内容。这是人工智能领域的一大进步，标志着我国在视频生成技术方面的突破。
「Vidu」大模型的推出，将极大地推动媒体、娱乐、教育等领域的发展。其长时长的特点，使得制作高质量的视频内容变得更加便捷；高一致性则保证了视频的质量和风格的一致性；高动态性则使得视频内容更加丰富和生动。
生数科技与清华大学的合作，展示了我国科技领域的强大实力和创新能力。未来，「Vidu」大模型有望在各个领域发挥更大的作用，推动人工智能领域的发展。
该模型的发布得到了业内专家的高度评价，他们认为这是视频生成技术的一大突破，将为未来媒体的发展带来革命性的影响。此次合作也展示了我国科技领域的活力和创新能力，期待未来更多类似的创新成果。
英语如下：
News Title: Shengshu Tech and Tsinghua University Join Forces to Release China’s First Long-Duration Video Macro Model “Vidu”: A Groundbreaking Announcement
Keywords: Shengshu Tech & Tsinghua University Macro Model Release, Long-Duration Video Macro Model “Vidu”, U-ViT Architecture
News Content:
News Title: Shengshu Tech and Tsinghua University Collaborate to Launch China’s First Long-Duration Video Macro Model “Vidu”
At the Zhongguancun Forum Future AI Vanguard Forum, Shengshu Tech and Tsinghua University jointly announced a major breakthrough – the official release of China’s first long-duration, high-consistency, and high-dynamic video macro model “Vidu”.
This innovative model combines the Diffusion and Transformer architectures and is named U-ViT. Its uniqueness lies in its ability to support the generation of high-definition video content up to 16 seconds long with a resolution of up to 1080P. This is a major advancement in the field of artificial intelligence, marking a breakthrough in video generation technology in China.
The launch of the “Vidu” macro model will greatly promote the development of fields such as media, entertainment, and education. Its long duration makes it convenient to produce high-quality video content, while high consistency ensures the quality and style of the videos remain consistent. High dynamics enrich and animate the video content.
The collaboration between Shengshu Tech and Tsinghua University demonstrates the strong strength and innovation capabilities of China’s technology sector. In the future, the “Vidu” macro model is expected to play a greater role in various fields, driving the development of the artificial intelligence field.
The release of this model has been highly praised by industry experts, who believe it is a breakthrough in video generation technology and will bring revolutionary impacts to the development of future media. This collaboration also showcases the vitality and innovation capabilities of China’s technology sector, and we look forward to more similar innovations in the future.
【来源】https://mp.weixin.qq.com/s/Lba_WJTQWjQ3lOaLNJA4qA
Views: 2