Instructions to use tz2026/DriveLaW with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tz2026/DriveLaW with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tz2026/DriveLaW", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "drivelaw", | |
| "architectures": ["DriveLaWVideoDiT", "DriveLaWActionDiT"], | |
| "paper": "https://arxiv.org/abs/2512.23421", | |
| "project_page": "https://xiaomi-research.github.io/drivelaw/", | |
| "checkpoints": { | |
| "DriveLaW-Video": { | |
| "path": "DriveLaW-Video/dualflow_dit_best_fvd.safetensors", | |
| "stage": 1, | |
| "description": "Future-predictive Video DiT (best FVD on nuScenes)" | |
| }, | |
| "DriveLaW-Act": { | |
| "path": "DriveLaW-Act/diffusion_pytorch_model.safetensors", | |
| "stage": "2-3", | |
| "description": "World-grounded Action DiT / planner (NAVSIM)" | |
| } | |
| } | |
| } |