In a groundbreaking move that echoes OpenAI’s monumental SORA, China has taken the AI world by storm with the introduction of Vidu. This cutting-edge text-to-video generative AI, unveiled at a forum in Beijing, marks China’s assertive stride into the realm of artificial intelligence.
Developed collaboratively by Tsinghua University and the renowned Chinese AI firm, ShengShu Technology, Vidu stands as the nation’s first video large AI model, boasting unparalleled capabilities. With a simple click, Vidu can craft a 16-second, high-definition video in 1080p resolution, promising extended duration, exceptional consistency, and dynamic prowess.
According to Zhu Jun, deputy director of the Tsinghua Institute for Artificial Intelligence, Vidu showcases remarkable proficiency in comprehending and generating Chinese content, seamlessly weaving together cultural icons like the beloved panda and the revered Chinese dragon, known as the loong.
The genesis of Vidu’s core architecture traces back to 2022, a testament to China’s forward-thinking approach to AI innovation. As the world watches in awe, Vidu emerges as a symbol of China’s unwavering commitment to technological advancement and its quest to push the boundaries of AI possibilities.
Watch as Vidu changes the text-to-video AI landscape and puts China at the forefront of the global AI scene — until Sora.
Useful links:
∘ On x
Their official website is nowhere to be found; if you find it, please let me know by email.
Thank you for reading!
KINOMOTO.MAG 