KyutaiOVIE
OVIE 512
OVIE 512 generates a view of a scene from an input image and a target camera pose. It predicts the new image without building a separate scene representation for each input.
Research release
The checkpoint has a specific training history
This is the base design retrained at 512-by-512 resolution for 250,000 steps with the same training mix. It is not simply a resized base-model output.ovie-512: Kyutai model card
Generated views are estimates
Practical guidance. A plausible new view does not establish the true shape of hidden objects. Check consistency when using generated views for a larger scene or animation.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/ovie-512 |
| License | MIT.ovie-512: Kyutai model card |
Related models
A single-image model that generates new scene views from a target camera pose at 256-by-256 resolution.
Launch date not confirmedResearch releaseDownloadable