Instructions to use mlx-community/Video-Depth-Anything-Base-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Video-Depth-Anything-Base-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Video-Depth-Anything-Base-MLX mlx-community/Video-Depth-Anything-Base-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -15,18 +15,13 @@ Architecture: DINOv2 backbone + DPT head with AnimateDiff-style temporal motion
|
|
| 15 |
## Usage
|
| 16 |
|
| 17 |
```python
|
| 18 |
-
from
|
| 19 |
-
from mlx_vlm.utils import load_model
|
| 20 |
-
from mlx_vlm.models.video_depth_anything.processing_video_depth_anything import (
|
| 21 |
-
VideoDepthProcessor,
|
| 22 |
-
)
|
| 23 |
from mlx_vlm.models.video_depth_anything.generate import (
|
| 24 |
VideoDepthPredictor,
|
| 25 |
read_video_frames,
|
| 26 |
)
|
| 27 |
|
| 28 |
-
model =
|
| 29 |
-
processor = VideoDepthProcessor.from_pretrained("mlx-community/Video-Depth-Anything-Base-MLX")
|
| 30 |
predictor = VideoDepthPredictor(model, processor)
|
| 31 |
|
| 32 |
frames, fps = read_video_frames("input.mp4", max_len=300, target_fps=15)
|
|
|
|
| 15 |
## Usage
|
| 16 |
|
| 17 |
```python
|
| 18 |
+
from mlx_vlm import load
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
from mlx_vlm.models.video_depth_anything.generate import (
|
| 20 |
VideoDepthPredictor,
|
| 21 |
read_video_frames,
|
| 22 |
)
|
| 23 |
|
| 24 |
+
model, processor = load("mlx-community/Video-Depth-Anything-Base-MLX"))
|
|
|
|
| 25 |
predictor = VideoDepthPredictor(model, processor)
|
| 26 |
|
| 27 |
frames, fps = read_video_frames("input.mp4", max_len=300, target_fps=15)
|