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-BASE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigshanedogg/DA3-BASE with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bigshanedogg/DA3-BASE", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from bigshanedogg/DA3-BASE: direct link, hf CLI and curl.
- Browser
- Download file 1.51 kB
-
https://huggingface.co/bigshanedogg/DA3-BASE/resolve/main/NOTICE
- Command line
-
hf download hf://bigshanedogg/DA3-BASE/NOTICE
-
curl -L -o NOTICE https://huggingface.co/bigshanedogg/DA3-BASE/resolve/main/NOTICE
1.51 kB
| DA3-BASE -- unofficial transformers-format package (trust_remote_code) | |
| Packaged by bigshanedogg, 2026. NOT an official release of the original authors. | |
| Components | |
| ---------- | |
| 1. DA3-BASE weights | |
| Source: https://huggingface.co/depth-anything/DA3-BASE | |
| Copyright: ByteDance; authors Haotong Lin, Sili Chen, Jun Hao Liew, Donny Y. Chen, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang | |
| License: Apache-2.0 -- LICENSE | |
| 2. Depth Anything 3 code (vendored into da3_*.py) | |
| Source: https://github.com/ByteDance-Seed/depth-anything-3 @ 3d835ec1a5802d64a8b8b15f817a1ab54809bfe4 | |
| Copyright: Copyright (c) 2025 ByteDance Ltd. and/or its affiliates | |
| License: Apache-2.0 -- LICENSE | |
| Changes made in this package | |
| ---------------------------- | |
| - da3_*.py: the official files concatenated into flat files; package-internal imports replaced by relative imports; the dinov2 layer files' 'dinov2' logger renamed. No computation changed. cfg.create_object is replaced by modeling_depth_anything_3.build_object, which builds the same object graph from the vendored classes. | |
| - configuration_ / modeling_ / image_processing_ / processing_depth_anything_3.py: new transformers wrappers; the model runs the network's own forward; the image processor is the package API's InputProcessor. | |
| - model.safetensors: the original tensors re-saved by save_pretrained, names unchanged, every tensor checked equal. | |
| License files | |
| ------------- | |
| - LICENSE: Apache License 2.0, copy from ByteDance-Seed/depth-anything-3 (code and weights) | |