ComfyUI - Mask Bounding Box
The ComfyUI Mask Bounding Box Plugin provides functionalities for selecting a specific size mask from an image. Can be combined with ClipSEG to replace any aspect of an SDXL image with an SD1.5 output.
ComfyUI - Mask Bounding Box

Overview
The ComfyUI Mask Bounding Box Plugin provides functionalities for selecting a specific size mask from an image. Can be combined with ClipSEG to replace any aspect of an SDXL image with an SD1.5 output.
Features
- Thresholding: Threshold by mask value
- Mask: Selects the largest bounded mask.
- Image: Applies the selected image to the bounded mask.
- Minimum width/height: centered as much as available around the bounding box.
Usage
- Add the 'Mask Bounding Box' plugin
- Attach a mask and image
- Output the resulting bounding box and resized mask/images.
ComfyUI masks keep their batch dimension. When a batch has multiple masks, the node returns one crop that includes the selected pixels from every mask. The right and bottom coordinates are exclusive for batched inputs.
Great for inpainting or selecting certain objects.
Feedback & Contributions
If you have feedback or would like to contribute to the development of this plugin, please submit a pull request.
Security updates
Use Python 3.11 or newer and install requirements.txt in the same ComfyUI environment, then restart ComfyUI. Pillow 13 includes the October 2026 image/font and native decoder fixes. This repository change does not update an already-running ComfyUI process.