Vidu
Shengshu Technology
Text-, image-, and reference-to-video generation at up to 1080p.
An AI video generator from Tsinghua-spinout Shengshu Technology. Turns text prompts, still images, or reference images into short high-resolution clips, with text-to-video, image-to-video, and reference-to-video modes. Known for fast, low-cost generation and keeping multiple uploaded subjects consistent across a shot.
Worth knowing
Unveiled in April 2024 as China's first text-to-video model billed as on par with OpenAI's Sora, two months after Sora's reveal.
- video-generation
- text-to-video
- image-to-video
- reference-to-video