ComfyUI-Mosaic

ComfyUI-Mosaic
★ 2

图像处理马赛克风格化蒙版支持
用于在ComfyUI中检测图像马赛克并生成多种马赛克效果，支持方形/圆形/六边形/渐变样式及蒙版局部应用。
💡 对图像敏感区域进行马赛克检测与局部化处理。
🍴 2 Forks💻 Python🔄 2025-07-05
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/8f9eee5e2cdb
📦 requirements.txt
torch>=1.9.0
torchvision>=0.10.0
opencv-python>=4.5.0
pillow>=8.0.0
numpy>=1.21.0
ComfyUI-Mosaic
📄 README

ComfyUI-Mosaic

ComfyUI custom nodes for mosaic detection and creation.

Features

  • Mosaic Detection: Detect mosaic patterns in images using computer vision
  • Mosaic Creation: Create various mosaic effects (squares, circles, hexagons, gradients)
  • Pattern Types: Multiple mosaic patterns with customizable parameters
  • Mask Support: Apply effects to specific areas using masks

    • Installation

  • Navigate to your ComfyUI custom nodes directory:
    • cd ComfyUI/custom_nodes

  • Clone this repository:
    • git clone https://github.com/1038lab/ComfyUI-Mosaic.git

  • Install dependencies:
    • cd ComfyUI-Mosaic
pip install -r requirements.txt

  • Restart ComfyUI

    • Nodes

    MosaicCreator

    Create mosaic effects on images.

    Parameters:

  • image: Input image
  • mosaic_type: Pattern type (pixelation, blur, block_average, squares, circles, hexagons, gradient_horizontal, gradient_vertical)
  • block_size: Mosaic block size (2-100)
  • intensity: Effect intensity (0.0-1.0)
  • mask: Optional mask for selective application

    • Outputs:

  • image: Processed image
  • processing_mask: Applied mask

    • MosaicDetector

    Detect mosaic patterns in images.

    Parameters:

  • image: Input image
  • top_n: Number of top detections (1-20)
  • mask_expand: Mask expansion size (0-64)
  • mask_blur: Mask edge blur (0-64)
  • invert_mask: Invert final mask
  • overlay_color: Visualization color
  • overlay_opacity: Overlay transparency (0.0-1.0)

    • Outputs:

  • image: Original image
  • mask_overlay: Visualization overlay
  • mask: Detection mask

    • Usage

  • Add nodes to your ComfyUI workflow
  • Connect image inputs
  • Adjust parameters as needed
  • Process images

    • Requirements

  • ComfyUI
  • Python 3.8+
  • PyTorch ≥1.9.0
  • OpenCV ≥4.5.0
  • Pillow ≥8.0.0
  • NumPy ≥1.21.0

    • License

    GPLv3 License – see LICENSE file for details.