Zhu Jun, vice president of Tsinghua University's Institute of Artificial Intelligence and founder and chief scientist of Sangji Technology, released Vidu Q1, the industry's first highly controllable AI video big model, on March 29th. 1AI learned from the official, Vidu Q1 in multi-subject detail control (especially action, layout control), sound synchronization control, picture quality enhancement and other aspects have achieved significant results. Taking multi-subject detail controllable as an example, on the basis of semantic commands, by incorporating visual commands of reference diagrams, Vidu Q1 supports the position, size, and...

January 15 news, domestic AI video generation platform Vidu today released the latest big model Vidu 2.0. According to the introduction, its generation of 4 seconds 512P single clip video time in 10 seconds, Vidu 2.0-4s-512 model to generate a single second of video for only 4 cents. Officially, Vidu 2.0 also realized the effect of upgrading, so that the style, theme is more consistent, the first and last frames more natural; to provide a staggered peak mode, the low peak time is not limited, no deduction of points, while also supporting a one-time generation of 4 material. However, Vidu 2...

Introduction to Keyframes Keyframes are a term used in video production and animation to refer to frames in an animation sequence that define the state of an object at a specific point in time. Keyframes usually refer to the keyframes at the beginning of an animation, while Endframes are the keyframes at the end of an animation. In video production, the first and last frames are used to determine the start and end states of the action and the transition between them. In AI video generation software, the First and Last Frames feature allows users to specify the start and end frames of a video, usually by uploading two images. ...

Vidu, a domestic manufacturer of large-scale Vincennes video models, announced yesterday that the new version 1.5 of Vidu has been officially launched, which realizes a "world-leading" breakthrough -- the ability to understand diverse inputs and break through the "consistency" problem. Vidu announced yesterday that the new Vidu 1.5 version has gone live, achieving a "world-leading" breakthrough - the ability to understand diverse inputs and break through the "consistency" barrier. According to Vidu, it already has the ability to generate character consistency at the beginning of its launch, and by locking the facial features of characters, it can solve the key pain point of video generation and ensure the consistency of the characters' facial features. In the update released this time, Vidu shows the ability of contextual learning for the first time, which improves the controllability of the overall video model, and through the flexible multi-input real...

Since its release in February, sora has brought the AI video generation space into the heat of competition. But sora itself has become a large futures, may also be the lack of funds arithmetic, personnel loss, the listing has also become a distant future. However, it will also bring the AI video generation field into the stage of booming development, the major manufacturers have also launched their own AI video generation model. You side sang me on stage, especially our Chinese AI video generation model, dare not say it is far ahead, but definitely the first echelon is also a lot of exclusive. Today we'll take stock of the...

September 11, Vidu official microblogging released theme reference generation video new features, publicity video generation into a new stage, face and body shape, clothing features can also be effectively controlled. After seeing the effect of the official claim, I couldn't help but try it out, and the overall consistency effect has really improved a lot. If you don't want to spend more time generating each sub-scene image, the consistency of the single character video generated directly from the Vidu reference video is not bad. How to create character consistency video with Vidu subject reference generation video function? Go to the homepage of Vidu official website (www.vidu.studio), click the top...

Vidu is China's first long-duration, highly consistent, and highly dynamic video model released by Shengshu Technology and Tsinghua University. The model uses the original Diffusion and Transformer fusion architecture U-ViT, which supports one-click generation of up to 16 seconds of high-definition video content with a resolution of up to 1080P. Vidu can not only simulate the real physical world, but also has rich imagination, multi-lens generation, and high spatiotemporal consistency. Vidu function Long-duration high-definition video generation: Vidu can generate up to 16 seconds of high-definition video based on the user's text description...

Today, Beijing Shengshu Technology announced the global launch of the official website of AI video generation model Vidu. Vidu is a model that uses artificial intelligence technology to generate videos from text or pictures. In April this year, Shengshu Technology and Tsinghua University jointly released China's first large video model - "Vidu", which marked an important step for China in video generation technology. "Vidu" uses the team's original U-ViT architecture, which combines Diffusion and Transformer technologies. This...

At the Future Artificial Intelligence Pioneer Forum of the Zhongguancun Forum, Shengshu Technology and Tsinghua University jointly launched China's first long-duration, highly consistent and highly dynamic video model - "Vidu". The core of this era-leading video model lies in the team's original U-ViT architecture that combines Diffusion and Transformer. It can not only generate up to 16 seconds of high-definition video with a clarity of 1080P in one click, but also show amazing imagination while simulating the real physical world. Multi-lens generation and high consistency in time and space are all Vidu's features.

Today, Shengshu Technology attended the Future Artificial Intelligence Pioneer Forum of the Zhongguancun Forum and officially released China's first long-duration, highly consistent, and highly dynamic video model, Vidu, together with Tsinghua University. It is considered by the media and industry insiders to be the first Sora-level video model in China. According to the official description, the Vidu model combines Diffusion and Transformer to create U-ViT, which supports the one-click generation of high-definition video content up to 16 seconds and a resolution of up to 1080P. The official promotional materials demonstrated "A...