image-masker-by-class — Masking AI Model

Image Masker by Class turns a segmentation or detection result into a clean black-and-white mask from the class names you pick — pixel-precise for segmentation, box-shaped for detectors. Feeds inpainting. CPU, instant.

Details

  • CategoryMasking
  • Year-1
  • License

Inputs & Outputs

  • ImageInput · image

    Upstream model's output image. For segmentation models (SAM2/SAM3/Maskformer/Segformer/DeepLabV3Plus), this is the colored overlay — its pixels are matched against the per-class colors in the text input to produce a pixel-precise mask. For object detectors (DETR/YOLO), only its width/height are used as the mask canvas size.

  • TextInput · string

    Line-separated metadata from an upstream segmentation or detection model. Each line carries a class label and (depending on the upstream) optional color tuple, score, and bbox — the parser auto-detects the format.

  • ImageOutput · image

    Generated mask image by detected class

Tags

  • mask-creation
  • detection-post-process
  • class-based

Alternatives in Image Masking