H3-Tiny-17B-FewStep-Ref2VA-v0.1 vs PAN 2
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Audiovisual generation | World simulation |
| Published capabilities | Generates video and synchronized sound from reference imagery using a pruned MiniMax H3 transformer. | Predicts what happens after an action in a starting scene. |
| Model size | 17.08B transformer parameters | — |
| Access | Downloadable transformer checkpoint for the H3 pipeline | Public weights, full training code and inference code |
| Result | — | Simulated video conditioned on a scene and action |
| Operating limits | Six steps by default | — |
| Sources | Model weights | Publisher documentation |
| Inputs | Text, Images | Text, Images |
| Weights | Open weights · MiniMax H3 Community License | Open weights · Apache-2.0 |
| Released | Nov 19, 2026 | Nov 10, 2026 |