Spatial world model that turns images, panoramas or video plus a camera path into explorable, consistent novel-view video.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
InSpatio-World 1.5 is a model from InSpatio that generates novel-view video from a source scene. It accepts a single image, a set of images, a panorama or a video, and renders a camera path through the scene, including areas hidden in the original view. Version 1.0 worked from a single video; 1.5 extends the inputs and supports wider viewpoint changes.
The project emphasises consistency of subject identity, spatial structure and style as the camera moves and, for video input, as time advances. Stated use cases include cinematography, bullet-time sequences from multiple synchronized images, immersive experiences, and research in spatial and embodied intelligence. It is trained for next-view prediction on large-scale data from dynamic real-world scenes.
According to a YouTube creator summary, the released code is based on Wan 2.1 1.3B and runs in under 6 GB. The project page says it is available to try and that the code is released as open source. No license, repository or weights links were found in the provided material, so those details are unverified.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Takes an image, multiple images, panorama or video plus a camera path and generates a video walking through the scene. Code released, based on Wan 2.1 1.3B, under 6 GB.
Closest neighbours by meaning, not just by category.
Model
World model that turns a few context images into an editable, physics-simulated 3D world rendered by a video model.
Model · Adobe
Adobe Research video world model that builds navigable interactive worlds from an image or video at 16 FPS.
Model
Research model that unifies 3D scene generation and reconstruction in a single pixel-space diffusion model.
Model
Interactive autoregressive world model generating minute-long playable video with real-time camera control and prompt events.
Research
Research system that turns a single image into a 360° Gaussian scaffold and renders interactive video at 8 FPS.
Research
Training-free research system that reconstructs simulation-ready 4D mesh scenes from a single monocular video.