China's VIDU: The Sora-Rival Shaking Things Up! Generate 16 Minutes 1080p Video from a Text Prompt!
Published 2024-04-27
At the 2024 Zhongguancun Forum in Beijing, China's first Sora-level text-to-video large model, Vidu, made its debut, marking a significant leap in the global AI competition. Created by Shengshu Technology and Tsinghua University, Vidu can generate a 16-second high-definition video with 1080p resolution in just one click. This model boasts exceptional consistency and dynamic capabilities, and is designed to represent Chinese elements like pandas and dragons. It's hailed as China's first video large model with extended duration and is seen as closely rivaling the United States' Sora model, developed by OpenAI. Interestingly, Vidu's core architecture was initiated earlier than Sora's, demonstrating China's commitment to leading AI technology.
Credit: VIDU - Shengshu Technology & Tsinghua University
Whether you're a beginner or an experienced professional, there's something for everyone on this channel.
Follow Us:
Website: https://www.elluscient.com
Facebook Page: https://www.facebook.com/ElluscientTe...
Instagram: https://www.instagram.com/elluscient
X (Twitter): https://twitter.com/elluscient
TikTok: https://www.tiktok.com/@elluscient
GitHub: https://github.com/erikelcsics
Pinterest: https://www.pinterest.com/elluscient
LinkedIn: https://www.linkedin.com/in/erik-elcs...
Discord: Available Soon!
Snapchat: https://www.snapchat.com/add/elluscie...
Lemon8: elluscient
#artificialintelligence #ai #sora #shengshutechnology #tsinghuauniversity #soramodel #AIGC #Vidu #texttovideoai #ai #aivideos #aivideogenerator
All Comments (3)
-
How does the competition between the US and China in text-to-video AI influence the development of more advanced and innovative solutions?
-
How would you leverage a text-to-video AI to create content, and in what context would it be most beneficial for you?
