ComfyUI-ImgPatchEditor

A ComfyUI node for patching images using a difference detection algorithm. It detects changes between two images (original and patched), creates a mask of the differences, and merges them back together with configurable blending.

Features

• Automatic Patch Detection: Compares two images to find changed regions.
• Configurable Masking: Control region size, minimum area, threshold, and blur radius.
• Batch Support: Process multiple image pairs in a batch.
• Output: Returns both the merged image and the generated mask.

Installation

1. Clone this repository into your ComfyUI/custom_nodes/ directory.
2. Install dependencies:

   pip install -r requirements.txt
   

Usage

Add the Image Patch Editor node (Category: ImgPatch) to your workflow.

Inputs

• image_1: The original base image.
• image_2: The patched/modified image.
• region_size: Size of the blocks used for difference detection (default: 8).
• min_area_size: Minimum size of changed areas to keep (removes noise) (default: 4).
• threshold: Sensitivity threshold for difference detection (default: 10).
• blur_radius: Blur radius applied to the mask for smooth blending (default: 3.0).

Outputs

• IMAGE: The final merged image.
• MASK: The mask representing the patched areas.