Image-to-3D
Transformers
Safetensors
depth_anything_3
feature-extraction
depth-anything-3
depth-estimation
multi-view-geometry
custom_code
Instructions to use bigshanedogg/DA3-LARGE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigshanedogg/DA3-LARGE with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bigshanedogg/DA3-LARGE", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processing_depth_anything_3.py from bigshanedogg/DA3-LARGE: direct link, hf CLI and curl.
- Browser
- Download file 515 Bytes
-
https://huggingface.co/bigshanedogg/DA3-LARGE/resolve/main/processing_depth_anything_3.py
- Command line
-
hf download hf://bigshanedogg/DA3-LARGE/processing_depth_anything_3.py
-
curl -L -o processing_depth_anything_3.py https://huggingface.co/bigshanedogg/DA3-LARGE/resolve/main/processing_depth_anything_3.py
515 Bytes
| """Depth Anything 3 processor: ``DepthAnything3ImageProcessor`` (the package API's InputProcessor) as its only part.""" | |
| from transformers.processing_utils import ProcessorMixin | |
| class DepthAnything3Processor(ProcessorMixin): | |
| attributes = ["image_processor"] | |
| def __init__(self, image_processor=None, **kwargs): | |
| super().__init__(image_processor, **kwargs) | |
| def __call__(self, images=None, **kwargs): | |
| return self.image_processor(images, **kwargs) | |
| __all__ = ["DepthAnything3Processor"] | |