Skip to content

Releases: EricRollei/Eric_Image_Processing_Nodes

v1.0.0 - Initial Release

19 Nov 06:06
@EricRollei EricRollei
v1.0.0
647d9db

Choose a tag to compare

View all tags
v1.0.0 - Initial Release Latest
Latest

Release v1.0.0 - Initial Release

🎉 Initial Release of Eric's Advanced Image Processing Nodes for ComfyUI

A comprehensive collection of 40+ advanced image processing nodes featuring state-of-the-art denoising, enhancement, and restoration techniques with GPU acceleration.

✨ Major Features

🎬 Film Grain Processing (GPU-Accelerated)

  • Automatic grain analysis and classification
  • Intelligent detection of authentic film grain, digital noise, and synthetic overlays
  • Specialized denoising strategies for each grain type
  • GPU-accelerated wavelet transforms via CuPy
  • Fine-grained preservation controls (0-100%)
  • Multi-stage processing pipelines

🔧 Denoising Algorithms

  • GPU Wavelet Denoising: Hardware-accelerated with multiple thresholding methods (BayesShrink, VisuShrink, SureShrink)
  • BM3D: Block-matching 3D collaborative filtering
  • Non-Local Means: Texture-preserving denoising
  • DnCNN, SwinIR, SCUNet: Pre-trained AI denoisers
  • NAFNet: Neural Architecture with Fast Fourier Convolutions

🎨 Advanced Processing

  • Frequency domain processing (FFT, homomorphic filtering)
  • Richardson-Lucy deconvolution
  • Wiener filtering with PSF modeling
  • CLAHE contrast enhancement
  • Unsharp masking and edge enhancement
  • Multi-scale pyramidal processing

💻 Performance & Reliability

  • GPU acceleration with automatic CPU fallback
  • Intelligent memory management
  • Batch processing support
  • Comprehensive error handling
  • Progress tracking and feedback

📋 Node Categories

  • Denoising: 15+ specialized denoising nodes
  • Enhancement: Sharpening, contrast, and detail enhancement
  • Restoration: Deconvolution and blur removal
  • Frequency Domain: FFT-based processing
  • Film Grain: Specialized grain analysis and processing
  • Analysis: Image quality metrics and grain detection

🔧 Installation

cd ComfyUI/custom_nodes
git clone https://github.com/EricRollei/Eric_Image_Processing_Nodes.git
cd Eric_Image_Processing_Nodes
pip install -r requirements.txt

# Optional GPU acceleration
pip install cupy-cuda12x  # or cupy-cuda11x for CUDA 11

📚 Documentation

Comprehensive documentation available in Docs/ directory:

  • Feature guides and usage examples
  • GPU acceleration setup
  • Model weights information
  • Technical implementation details

⚠️ Requirements

  • ComfyUI
  • Python 3.8+
  • PyTorch
  • NumPy, SciPy, OpenCV, scikit-image, PyWavelets
  • Optional: CuPy for GPU acceleration

🐛 Bug Fixes

  • Fixed syntax error in advanced_film_grain_node.py preventing node loading

📝 License

See LICENSE file for details. Various components use MIT, BSD 3-Clause, and Apache 2.0 licenses.

Instructions for Publishing on GitHub

  1. Go to: https://github.com/EricRollei/Eric_Image_Processing_Nodes/releases/new
  2. Tag version: v1.0.0
  3. Release title: v1.0.0 - Initial Release
  4. Copy the content above (everything before "Instructions for Publishing") into the description
  5. Check "Set as the latest release"
  6. Click "Publish release"
Assets 2
Loading