Instructions to use chenchenshi/DriveWAM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use chenchenshi/DriveWAM with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("chenchenshi/DriveWAM", 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
Upload 2 files
Browse files
navsim/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"patch_size": [
|
| 3 |
+
1,
|
| 4 |
+
2,
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"num_attention_heads": 24,
|
| 8 |
+
"attention_head_dim": 128,
|
| 9 |
+
"in_channels": 48,
|
| 10 |
+
"out_channels": 48,
|
| 11 |
+
"action_dim": 30,
|
| 12 |
+
"text_dim": 4096,
|
| 13 |
+
"freq_dim": 256,
|
| 14 |
+
"ffn_dim": 14336,
|
| 15 |
+
"num_layers": 30,
|
| 16 |
+
"cross_attn_norm": true,
|
| 17 |
+
"eps": 1e-06,
|
| 18 |
+
"rope_max_seq_len": 1024,
|
| 19 |
+
"pos_embed_seq_len": null,
|
| 20 |
+
"attn_mode": "flex",
|
| 21 |
+
"ego_command_classes": 4,
|
| 22 |
+
"ego_velocity_acc_dim": 4,
|
| 23 |
+
"ego_history_pose_dim": 12,
|
| 24 |
+
"_use_default_values": [
|
| 25 |
+
"ego_history_pose_dim",
|
| 26 |
+
"ego_velocity_acc_dim",
|
| 27 |
+
"ego_command_classes"
|
| 28 |
+
],
|
| 29 |
+
"_class_name": "WanTransformer3DNavSimModel",
|
| 30 |
+
"_diffusers_version": "0.35.0.dev0"
|
| 31 |
+
}
|
navsim/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27e4846b0a25e22fc299f7aca90c01d802072d2b297741c85ed074b689ef26a9
|
| 3 |
+
size 12482164484
|