Splat Maker

Scene

Images

Viewing from

1Input

The photo and the views the engine uses when it creates new views. Click one to look from it.

2Place new frames

Move to a spot the scene does not cover well, then add a frame there. Up to 4 at a time.

3Create new views for frames

The AI imagines what is missing: in the empty areas you are looking at now, or from frames you placed. Your photo is not changed. The view is sent to Cloudflare.

1Camera path

Move to where the shot starts and add a keyframe. Move on and add more. The camera glides through them in order.

2Shot

How long the video is, and its shape.

3Render video

Draws the camera path frame by frame and saves it as an MP4 file.

Drop a photo to start a scene

Your photo is turned into a 3D space exactly as it is. Nothing is added to it, and it stays on this device. (The first time, about 100 MB of depth model is downloaded.) Afterwards you decide whether the AI imagines more: the surroundings, or new views you place.