PAN 2 vs Viggle Remake
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | World simulation | Video-to-video editing |
| Published capabilities | Predicts what happens after an action in a starting scene. | Edits people, objects or scenery in source footage. Two LoRA modes run on the MiniMax H3 transformer. |
| Access | Public weights, full training code and inference code | Viggle app and downloadable editing adapters |
| Result | Simulated video conditioned on a scene and action | Edited video retaining the source motion and soundtrack |
| Sources | Publisher documentation | Model weights · Additional documentation |
| Inputs | Text, Images | Text, Images, Video |
| Context window | — | — |
| Input price per million tokens | — | — |
| Output price per million tokens | — | — |
| Weights | Open weights · Apache-2.0 | Open weights · MiniMax H3 Community License |
| Released | Nov 10, 2026 | Nov 2, 2026 |