BWM: Physically consistent, action-conditioned video world model for robotic manipulation
| Property | Value |
|---|---|
| Base Model | Wan2.2-TI2V-5B |
| Resolution | 480 x 640 |
| Frames | 81 frames |
| Control Signals | Robot action trajectories |
| Architecture | Trainable DiT + Action Encoder |
To use these weights, please refer to our GitHub repository.
This project builds upon the following open-source projects and benchmarks:
BWM: Physically consistent, action-conditioned video world model for robotic manipulation
| Property | Value |
|---|---|
| Base Model | Wan2.2-TI2V-5B |
| Resolution | 480 x 640 |
| Frames | 81 frames |
| Control Signals | Robot action trajectories |
| Architecture | Trainable DiT + Action Encoder |
To use these weights, please refer to our GitHub repository.
This project builds upon the following open-source projects and benchmarks:
