Backup current implementation and update .gitignore

.gitignore

@@ -61,4 +61,140 @@ pretrained_models/
 
 debug_vis/
 pretrained_models
-train_data
+train_data
+
+#### joe made this: http://goel.io/joe
+
+#####=== Python ===#####
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+__pycache__/
+*$py.class
+.vscode/
+example
+input
+
+# Private configuration files
+config.private.yml
+*.private.*
+secrets/
+credentials.json
+
+# GitHub Pages related
+_site/
+.jekyll-cache/
+.jekyll-metadata
+Gemfile.lock
+
+LHM-0.5B.tar
+LHM_prior_model.tar
+*.jpg
+*.png
+comfyui-reactor/
+gfpgan/
+temp_sync/
+~/*

ComfyUI-LHM/README.md

@@ -75,7 +75,7 @@ Place the weights in the `models` directory inside this node's folder.
 
 ## Troubleshooting
 
-If you encounter any issues with the installation or running the node, please check the [TROUBLESHOOTING.md](TROUBLESHOOTING.md) file for solutions to common problems.
+If you encounter any issues with the installation or running the node, check the [TROUBLESHOOTING.md](TROUBLESHOOTING.md) file for solutions to common problems.
 
 ## License
 

comfy_lhm_node/CHANGELOG.md

@@ -0,0 +1,60 @@
+# Changelog
+
+## 2023-06-20
+- Initial release of the LHM ComfyUI node
+- Basic implementation with simplified fallback
+
+## 2023-06-30
+- Added error handling for missing dependencies
+- Improved documentation
+
+## 2023-07-10
+- Added support for Pinokio installation
+- Created installation guide
+
+## 2023-11-15
+- Updated to support LHM 1.0
+- Added animation output
+
+## 2024-06-22
+- Enhanced troubleshooting guide with detailed installation steps
+- Added quality of life improvements for error messages
+
+## 2024-06-25
+- Added PyTorch3D installation scripts for Apple Silicon
+  - Created `install_pytorch3d_mac.sh` - Bash script for installing PyTorch3D on macOS
+  - Created `install_pytorch3d_mac.py` - Python version of the installation script
+  - Added `install_pytorch3d_lite.py` - Alternative lightweight implementation
+- Added PyTorch3D-Lite compatibility layer for easier installation
+- Updated TROUBLESHOOTING.md with detailed instructions for dealing with PyTorch3D installation issues
+- Added workaround for animation format issues in simplified mode using Tensor Reshape 
+
+## 2024-06-26
+- Added optimized PyTorch MPS installation script for Apple Silicon (`install_pytorch_mps.py`)
+  - Properly configures PyTorch with Metal Performance Shaders (MPS) support
+  - Attempts to install PyTorch3D from source with appropriate environment variables
+  - Sets up PyTorch3D-Lite as a fallback in case of installation issues
+  - Creates a smarter import fix that tries both regular PyTorch3D and the lite version
+- Updated TROUBLESHOOTING.md with the new recommended installation method
+
+## 2024-06-27
+- Added conda-based installation scripts for PyTorch3D
+  - Created `install_pytorch3d_conda.sh` - Bash script for installing PyTorch3D using conda
+  - Created `install_pytorch3d_conda.py` - Python version of the conda installation script
+  - These scripts provide the most reliable method for installing PyTorch3D
+  - Added conda-forge channel configuration for consistent package availability
+  - Enhanced compatibility layer that checks for conda-installed PyTorch3D first
+- Updated TROUBLESHOOTING.md to highlight conda as the recommended installation method 
+
+## 2024-06-28 (2)
+- Added `create_test_workflow.py` script to automatically generate a sample ComfyUI workflow for testing the LHM node
+- Updated `TROUBLESHOOTING.md` with direct references to the official PyTorch3D installation documentation
+- Reorganized installation sections to prioritize the official PyTorch3D installation methods
+- Added detailed environment variable guidance for Apple Silicon users based on successful installations
+
+## 2024-06-28
+- Successfully installed PyTorch3D from source following the official documentation
+- Added reference to official PyTorch3D installation guide in `TROUBLESHOOTING.md`
+- Created `test_imports.py` to verify all dependencies are properly installed
+- Updated `lhm_import_fix.py` to prioritize direct PyTorch3D imports and explicit paths to Pinokio's miniconda Python packages
+- Fixed dependency installation guidance for macOS with Apple Silicon and environment variable specifications for macOS compilation 

comfy_lhm_node/README.md

@@ -0,0 +1,82 @@
+# LHM Node for ComfyUI
+
+A custom node for ComfyUI that integrates the Large Human Model (LHM) for 3D human reconstruction from a single image.
+
+## Features
+
+- Reconstruct 3D human avatars from a single image
+- Generate animated sequences with the reconstructed avatar
+- Background removal option
+- Mesh export option for use in other 3D applications
+- Preview scaling for faster testing
+- Error handling with fallback to simplified implementation
+
+## Installation
+
+### Prerequisites
+
+- ComfyUI installed and running
+- Python 3.10+ with pip
+
+### Installation Steps
+
+1. Clone this repository into your ComfyUI custom_nodes directory:
+   ```bash
+   cd /path/to/ComfyUI/custom_nodes
+   git clone https://github.com/aigraphix/comfy_lhm_node.git
+   ```
+
+2. Run the installation script:
+   ```bash
+   cd comfy_lhm_node
+   chmod +x install_dependencies.sh
+   ./install_dependencies.sh
+   ```
+
+   Alternatively, you can use the Python installation script:
+   ```bash
+   cd comfy_lhm_node
+   chmod +x install_dependencies.py
+   ./install_dependencies.py
+   ```
+
+3. Restart ComfyUI
+
+### Optional: Using the Test Workflow
+
+We've included a sample workflow to help you test the LHM node functionality:
+
+1. Run the test workflow creation script:
+   ```bash
+   cd comfy_lhm_node
+   chmod +x create_test_workflow.py
+   ./create_test_workflow.py
+   ```
+
+2. Place a test image named `test_human.png` in your ComfyUI input directory
+
+3. In ComfyUI, load the workflow by clicking on the Load button and selecting `lhm_test_workflow.json`
+
+4. Click "Queue Prompt" to run the workflow
+
+The test workflow includes:
+- A LoadImage node that loads `test_human.png`
+- The LHM Reconstruction node configured with recommended settings
+- A TensorReshape node to format the animation output correctly
+- Preview Image nodes to display both the processed image and animation frames
+
+## Model Weights
+
+The model weights are automatically downloaded the first time you run the node. If you encounter any issues with the automatic download, you can manually download the weights from:
+
+- https://github.com/YuliangXiu/large-human-model
+
+Place the weights in the `models` directory inside this node's folder.
+
+## Troubleshooting
+
+If you encounter any issues with the installation or running the node, check the [TROUBLESHOOTING.md](TROUBLESHOOTING.md) file for solutions to common problems.
+
+## License
+
+This project is licensed under the terms of the MIT license. See [LICENSE](LICENSE) for more details.