Shang Shu Technology Unveils VDU, China’s First Text-to-AI Video Model

Shang Shu Technology, a Chinese AI firm, teamed up with Ting University to create VDU. VDU is China's first AI model that turns text into videos. It can make high-quality videos that last 16 seconds and are in 1080P resolution. With just one click, VDU creates these videos. It's set up to compete with OpenAI’s Sora model. VDU is special because it can include Chinese things like pandas and dragons in its videos.

The news about VDU was shared a few days ago. Many people had different opinions about it. Making videos through AI is very hard. Most free AI tools cannot do what VDU does. This shows that China is really pushing forward with AI technology. They also made big updates in robots and language models this week.

VDU had a demo that showed off what it can do. Some might say the best parts were picked to show. But that's common in demos. The demo’s quality was good, especially for an early version like this. The details in the videos, like how clothes moved, were pretty realistic.

Shang Shu Technology’s new tool shows how China is catching up in the AI field. Making videos with AI is tricky. But VDU has shown it can handle details well, like keeping movements smooth and accurate.

This news about VDU is a big step for AI video-making technology. It shows new possibilities for creating videos from just text.