Wonder is a world model in video: it generates an environment you can explore in real time, pressing keys to navigate. Technically it's still video — there's no 3D scene built behind it.
What sets it apart from other models of its kind is accepting a video as the starting point, not just an initial image.
Why this matters
- With an input video, it reproduces the same motion and even lets you walk through the scene, as if you were seeing that video in three dimensions.
- Works with varied styles: anime, digital art, illustration, and realistic scenes.
- You can change the camera angle within an action scene.
1.The difference between input image and video
2 minMost world models start from an image: you provide a frame and it invents the rest of the space. Wonder accepts an entire video.
This will render the same movements from the video, but now it lets you walk around the scene as if you were watching the video in 3D.
Spec sheet
- Status
- Code "coming soon"
- Entry
- Image or video
- Interaction
- Teclado, em tempo real
Continue in the full microcourse
You've read the opening of 3 classes
The microcourse covers the complete step-by-step, the selection criteria, where the tool fails, who it's really for — and, in the Expert version, the official address to start today.
- Quality, without makeup2 min
- The warning that matters more than the demo1 min
How we verified
We track releases straight from primary sources, transcribe what's demonstrated, check every name and number against the manufacturer's official documentation, and rewrite it in Portuguese — with what the tool no do it together, which is the part the ad leaves out.
