JimmyLiaoo commited on
Commit
1ec64a8
·
verified ·
1 Parent(s): da6195c

Release video generation transformer and document downloads

Browse files
README.md CHANGED
@@ -9,7 +9,7 @@ tags:
9
 
10
  # LO-World
11
 
12
- Pretrained checkpoints for joint future 3D occupancy and LiDAR prediction in a shared BEV latent space.
13
 
14
  ## Checkpoints
15
 
@@ -34,6 +34,29 @@ hf download JimmyLiaoo/LO-World \
34
 
35
  Weights are saved to `ckpts/`. Use the matching configuration and data preparation instructions in the code repository. World Model checkpoints include tokenizer parameters.
36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  ## Data downloads
38
 
39
  Download nuScenes train/validation annotation infos to `data/nus_infos/`:
 
9
 
10
  # LO-World
11
 
12
+ Pretrained checkpoints for joint future 3D occupancy and LiDAR prediction in a shared BEV latent space, with a GenieDrive transformer for six-camera video generation.
13
 
14
  ## Checkpoints
15
 
 
34
 
35
  Weights are saved to `ckpts/`. Use the matching configuration and data preparation instructions in the code repository. World Model checkpoints include tokenizer parameters.
36
 
37
+ ## Video generation
38
+
39
+ The released GenieDrive transformer generates six-camera videos at 448 × 800. Install the `loworld-genie` environment and prepare scene RGB/semantic conditions using the LO-World code repository.
40
+
41
+ Download the transformer and its required Wan base model from the repository root:
42
+
43
+ ```bash
44
+ hf download JimmyLiaoo/LO-World --include "ckpts/geniedrive/loworld_448x800/**" --local-dir .
45
+ hf download alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control \
46
+ --local-dir ckpts/geniedrive/Wan2.1-Fun-V1.1-1.3B-Control
47
+ (cd ckpts/geniedrive/loworld_448x800 && sha256sum -c SHA256SUMS)
48
+ ```
49
+
50
+ The transformer is saved to `ckpts/geniedrive/loworld_448x800/checkpoint-1000/transformer/`, matching the default inference path. Generate videos for a prepared scene:
51
+
52
+ ```bash
53
+ conda run --no-capture-output -n loworld-genie python \
54
+ tools/genie/inference/generate_scene.py \
55
+ --scene-dir work_dirs/visualization/scene_0001
56
+ ```
57
+
58
+ Output: six camera MP4s and a surround-view GIF under `work_dirs/visualization/scene_0001/video/`.
59
+
60
  ## Data downloads
61
 
62
  Download nuScenes train/validation annotation infos to `data/nus_infos/`:
ckpts/geniedrive/loworld_448x800/SHA256SUMS ADDED
@@ -0,0 +1 @@
 
 
1
+ 39991dbcacc030e55e5349a9900d60b3763063a61d656523e6bd01792f9907e1 checkpoint-1000/transformer/diffusion_pytorch_model.safetensors
ckpts/geniedrive/loworld_448x800/checkpoint-1000/transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39991dbcacc030e55e5349a9900d60b3763063a61d656523e6bd01792f9907e1
3
+ size 3337138152