today,Beijing Biodata TechnologyAnnounceAI video generation model Vidu The official website is launched globally. 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 firstVideo mockup-- "Vidu", which marks an important step in China's video generation technology.
"Vidu utilizes the team's original U-ViT architecture, which combines Diffusion and Transformer technologies. This innovative video model is capable of rapidly generating up to 16 seconds of 1080p HD video, while demonstrating a high degree of imagination and creativity based on the simulation of the real physical world. Its multi-camera generation capability and temporal consistency are the distinguishing features of "Vidu".
Since its release, "Vidu" has made remarkable breakthroughs globally, and its performance has reached the international top level, and is still being iterated and optimized. This achievement is attributed to the team's deep accumulation in the field of Bayesian machine learning and multimodal large models, as well as a number of original results.
With in-depth understanding of U-ViT architecture and rich engineering and data experience, the team quickly overcame the key technical challenges of long video representation and processing, and successfully developed the "Vidu" video model, which has achieved remarkable results in improving video coherence and dynamics, and driven the development of video processing technology. Vidu" has achieved remarkable results in improving video coherence and dynamics, and has pushed forward the development of video processing technology.
Experience address:https://www.1ai.net/16856.html