237 lines
8.2 KiB
Markdown
237 lines
8.2 KiB
Markdown
# Luminance Stack Processor - ComfyUI Custom Nodes
|
|
|
|
[](https://github.com/sumitchatterjee13/Luminance-Stack-Processor)
|
|
[](https://python.org)
|
|
[](https://github.com/sumitchatterjee13/Luminance-Stack-Processor/blob/main/LICENSE)
|
|
[](https://github.com/comfyanonymous/ComfyUI)
|
|
[](https://github.com/sumitchatterjee13/Luminance-Stack-Processor)
|
|
|
|
Professional HDR (High Dynamic Range) processing nodes for ComfyUI using the **Debevec Algorithm** for merging multiple exposure images into a single high dynamic range image.
|
|
|
|
**Version: 1.0.0** | **Release Date: 2025-01-20**
|
|
|
|
## 🎯 Features
|
|
|
|
- **Professional HDR Processing**: Implements the industry-standard Debevec Algorithm for HDR image creation
|
|
- **Two Processing Modes**:
|
|
- **3-Stop Processor**: Merges EV+2, EV+0, EV-2 exposures
|
|
- **5-Stop Processor**: Merges EV+4, EV+2, EV+0, EV-2, EV-4 exposures
|
|
- **16-bit Output**: Preserves maximum dynamic range in the final image
|
|
- **Automatic Camera Response Function**: Estimates and applies camera response curves
|
|
- **Fallback Safety**: Gracefully handles errors with fallback to middle exposure
|
|
- **ComfyUI Integration**: Seamless integration with ComfyUI workflows
|
|
|
|
## 📋 Requirements
|
|
|
|
- ComfyUI (includes NumPy and PyTorch)
|
|
- Python 3.8+
|
|
- OpenCV (cv2) >= 4.8.0
|
|
|
|
## 🚀 Installation
|
|
|
|
1. **Clone or Download** this repository to your ComfyUI custom nodes directory:
|
|
```bash
|
|
# Method 1: Clone directly into ComfyUI custom nodes directory
|
|
cd ComfyUI/custom_nodes/
|
|
git clone https://github.com/sumitchatterjee13/Luminance-Stack-Processor.git luminance-stack-processor
|
|
|
|
# Method 2: Download ZIP and extract to:
|
|
# ComfyUI/custom_nodes/luminance-stack-processor/
|
|
```
|
|
|
|
2. **Install Dependencies**:
|
|
|
|
**For ComfyUI Portable (Recommended)**:
|
|
```bash
|
|
# Navigate to your ComfyUI portable directory and use embedded Python
|
|
cd path/to/ComfyUI_windows_portable
|
|
python_embeded\python.exe -m pip install opencv-python>=4.8.0
|
|
```
|
|
|
|
**For Standard ComfyUI Installation**:
|
|
```bash
|
|
# Use your system Python or ComfyUI's virtual environment
|
|
pip install opencv-python>=4.8.0
|
|
```
|
|
|
|
**Or install from requirements.txt**:
|
|
```bash
|
|
# For portable version
|
|
python_embeded\python.exe -m pip install -r requirements.txt
|
|
|
|
# For standard installation
|
|
pip install -r requirements.txt
|
|
```
|
|
|
|
3. **Restart ComfyUI** to load the new nodes
|
|
|
|
## 🎨 Usage
|
|
|
|
### Luminance Stack Processor (3 Stops)
|
|
|
|
Perfect for standard HDR bracketing with 3 exposures:
|
|
|
|
**Inputs:**
|
|
- `ev_plus_2`: Overexposed image (+2 EV)
|
|
- `ev_0`: Normal exposure image (0 EV)
|
|
- `ev_minus_2`: Underexposed image (-2 EV)
|
|
- `exposure_step`: (Optional) EV step size (default: 2.0)
|
|
|
|
**Output:**
|
|
- `hdr_image`: Merged 16-bit HDR image
|
|
|
|
### Luminance Stack Processor (5 Stops)
|
|
|
|
For extended dynamic range with 5 exposures:
|
|
|
|
**Inputs:**
|
|
- `ev_plus_4`: Most overexposed image (+4 EV)
|
|
- `ev_plus_2`: Overexposed image (+2 EV)
|
|
- `ev_0`: Normal exposure image (0 EV)
|
|
- `ev_minus_2`: Underexposed image (-2 EV)
|
|
- `ev_minus_4`: Most underexposed image (-4 EV)
|
|
- `exposure_step`: (Optional) EV step size (default: 2.0)
|
|
|
|
**Output:**
|
|
- `hdr_image`: Merged 16-bit HDR image
|
|
|
|
## 🔬 How It Works
|
|
|
|
The nodes implement the **Debevec Algorithm** (Paul E. Debevec, Jitendra Malik, 1997) which:
|
|
|
|
1. **Analyzes Multiple Exposures**: Takes differently exposed images of the same scene
|
|
2. **Estimates Camera Response Function**: Determines how the camera sensor responds to light
|
|
3. **Recovers Scene Radiance**: Calculates the actual light values in the scene
|
|
4. **Merges to HDR**: Combines all exposures into a single high dynamic range image
|
|
5. **Tone Maps for Output**: Converts to 16-bit format for maximum compatibility
|
|
|
|
## 📸 Best Practices
|
|
|
|
### For Capturing Source Images:
|
|
- Use a **tripod** for perfect alignment
|
|
- Keep the **same white balance** across all exposures
|
|
- Use **manual focus** to prevent focus shifts
|
|
- Capture in **RAW format** when possible
|
|
- Use **exposure compensation** or **manual mode**
|
|
|
|
### EV (Exposure Value) Guidelines:
|
|
- **3-Stop**: +2, 0, -2 EV (4x range)
|
|
- **5-Stop**: +4, +2, 0, -2, -4 EV (16x range)
|
|
- Adjust `exposure_step` parameter if using different increments
|
|
|
|
## ⚙️ Technical Details
|
|
|
|
- **Algorithm**: Debevec & Malik HDR reconstruction
|
|
- **Input Format**: ComfyUI IMAGE tensors (0-1 float range)
|
|
- **Output Format**: 16-bit images for extended dynamic range
|
|
- **Processing**: OpenCV's `createCalibrateDebevec()` and `createMergeDebevec()`
|
|
- **Memory**: Efficient processing with automatic cleanup
|
|
- **Error Handling**: Graceful fallbacks with detailed logging
|
|
|
|
## 🔧 Troubleshooting
|
|
|
|
### Common Issues:
|
|
|
|
1. **"Module not found" error**:
|
|
- Ensure all dependencies are installed: `pip install -r requirements.txt`
|
|
- Restart ComfyUI completely
|
|
|
|
2. **Poor HDR results**:
|
|
- Ensure input images are properly exposed (not all over/under)
|
|
- Check that images are aligned (use tripod)
|
|
- Verify EV differences match your capture method
|
|
|
|
3. **Memory issues**:
|
|
- Process smaller images first
|
|
- Ensure adequate RAM available
|
|
- Close unnecessary applications
|
|
|
|
### Debug Information:
|
|
The nodes provide detailed logging. Check your ComfyUI console for processing information and error details.
|
|
|
|
## 🏗️ Development
|
|
|
|
### Project Structure:
|
|
```
|
|
luminance-stack-processor/
|
|
├── __init__.py # ComfyUI registration
|
|
├── luminance_stack_processor.py # Main node implementations
|
|
├── requirements.txt # Dependencies
|
|
└── README.md # Documentation
|
|
```
|
|
|
|
### Contributing:
|
|
1. Fork the repository
|
|
2. Create a feature branch
|
|
3. Test with various HDR image sets
|
|
4. Submit a pull request
|
|
|
|
## 📝 Changelog
|
|
|
|
See [CHANGELOG.md](CHANGELOG.md) for version history and detailed release notes.
|
|
|
|
## 🔧 Development
|
|
|
|
### Version Management
|
|
|
|
This project uses [Semantic Versioning](https://semver.org/). To bump version:
|
|
|
|
```bash
|
|
# Install bumpversion
|
|
pip install bump2version
|
|
|
|
# Bump patch version (1.0.0 -> 1.0.1)
|
|
bump2version patch
|
|
|
|
# Bump minor version (1.0.0 -> 1.1.0)
|
|
bump2version minor
|
|
|
|
# Bump major version (1.0.0 -> 2.0.0)
|
|
bump2version major
|
|
```
|
|
|
|
### Project Structure
|
|
```
|
|
luminance-stack-processor/
|
|
├── __init__.py # ComfyUI node registration & version info
|
|
├── luminance_stack_processor.py # Main HDR processing nodes
|
|
├── version.py # Centralized version management
|
|
├── pyproject.toml # Modern Python packaging configuration
|
|
├── requirements.txt # Runtime dependencies
|
|
├── README.md # Documentation
|
|
└── CHANGELOG.md # Version history
|
|
```
|
|
|
|
## 📚 References
|
|
|
|
- **Debevec, P. E., & Malik, J.** (1997). Recovering high dynamic range radiance maps from photographs. *ACM SIGGRAPH Computer Graphics*, 31(Annual Conference Series), 367-378.
|
|
- **OpenCV HDR Documentation**: https://docs.opencv.org/4.x/d3/db7/tutorial_hdr_imaging.html
|
|
- **ComfyUI Custom Node Guidelines**: https://docs.comfy.org/custom-nodes/
|
|
- **Semantic Versioning**: https://semver.org/
|
|
|
|
## 📜 License
|
|
|
|
MIT License - Feel free to use and modify for your projects.
|
|
|
|
## 🤝 Support
|
|
|
|
For issues, questions, or contributions:
|
|
- **GitHub Issues**: [Report bugs or request features](https://github.com/sumitchatterjee13/Luminance-Stack-Processor/issues)
|
|
- **GitHub Discussions**: [Ask questions or share workflows](https://github.com/sumitchatterjee13/Luminance-Stack-Processor/discussions)
|
|
- Check the troubleshooting section above
|
|
- Review ComfyUI console logs for detailed error information
|
|
- Check [CHANGELOG.md](CHANGELOG.md) for version-specific issues
|
|
- Ensure all dependencies are properly installed
|
|
|
|
### Contributing
|
|
We welcome contributions! Please:
|
|
1. Fork the repository
|
|
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
|
|
3. Commit your changes (`git commit -m 'Add some amazing feature'`)
|
|
4. Push to the branch (`git push origin feature/amazing-feature`)
|
|
5. Open a Pull Request
|
|
|
|
---
|
|
|
|
**Happy HDR Processing!** 📸✨ | **Version 1.0.0**
|