nan
c5b77c5c85
- Introduced `onnx_moge2.py` for MoGe-2 ONNX inference with NumPy post-processing. - Added `onnx_ben2.py` for BEN2 ONNX inference with Pillow and NumPy preprocessing. - Created `onnx_da3.py` for Depth Anything 3 inference with ONNX Runtime and NumPy. - Implemented shared ONNX Runtime session helpers in `onnx_runtime.py`. - Developed unit tests for server functionalities in `test_server.py`, including model caching and job management. - Enhanced job server to handle frame extraction without requiring models.
1.6 KiB
1.6 KiB
开发与许可证
开发
uv run pytest tests -v
uv run python pack.py
项目结构：
.
├── pack.py
├── src/
│ └── snapform/
│ ├── blender_manifest.toml
│ ├── operators.py
│ ├── panel.py
│ ├── preferences.py
│ ├── properties.py
│ ├── job_runtime.py
│ ├── blendjob/
│ │ ├── client.py
│ │ ├── controller.py
│ │ ├── environment.py
│ │ ├── installer/environment.py
│ │ ├── operator.py
│ │ ├── runner.py
│ │ ├── runtime.py
│ │ └── server.py
│ ├── blender/
│ │ ├── depth_plane.py
│ │ └── surface.py
│ └── server/
│ ├── __init__.py
│ ├── model_catalog.py
│ ├── model_download.py
│ ├── model_manager.py
│ ├── media.py
│ ├── geometry.py
│ ├── background.py
│ ├── moge2.py
│ ├── da3.py
│ ├── onnx_ben2.py
│ ├── onnx_da3.py
│ ├── onnx_moge2.py
│ └── onnx_runtime.py
└── tests/
上游与许可证
- Depth Anything 3 代码采用 Apache 2.0。
- BEN2 ONNX 模型采用其仓库声明的 Apache 2.0 License。
- 本 Extension 代码采用 GPL-3.0-or-later。
- 模型权重许可证由所选 Hugging Face 模型仓库决定，Extension 下载前会在界面显示。