ComfyUI  >  Nodes  >  KJNodes for ComfyUI >  Batch Crop From Mask

ComfyUI Node: Batch Crop From Mask

Class Name


kijai (Account age: 2192 days)
KJNodes for ComfyUI
Latest Updated
Github Stars

How to Install KJNodes for ComfyUI

Install this extension via the ComfyUI Manager by searching for  KJNodes for ComfyUI
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter KJNodes for ComfyUI in the search bar
After installation, click the  Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Batch Crop From Mask Description

Facilitates cropping images based on masks for AI artists, streamlining workflow with high accuracy.

Batch Crop From Mask:

The BatchCropFromMask node is designed to facilitate the cropping of images based on provided masks, making it an essential tool for AI artists who need to isolate specific regions of interest within their images. This node processes batches of masks and corresponding images, identifying non-zero regions within the masks to determine the bounding boxes for cropping. By doing so, it ensures that only the relevant parts of the images are retained, which can be particularly useful for tasks such as object detection, segmentation, and other image analysis applications. The node also handles cases where masks are empty, ensuring robust and error-free operation. Overall, BatchCropFromMask streamlines the workflow of cropping images based on masks, saving time and effort while maintaining high accuracy.

Batch Crop From Mask Input Parameters:


This parameter expects a batch of masks, where each mask is used to identify the regions of interest within the corresponding image. The masks should be in a tensor format, and each mask should have non-zero values in the areas that need to be retained. The node will process these masks to determine the bounding boxes for cropping.


This parameter takes a batch of original images that correspond to the provided masks. Each image in this batch should align with the respective mask in terms of dimensions and content. If the number of images does not match the number of masks, the node will issue a warning and ignore the images. This parameter is optional but recommended for accurate cropping.


This parameter is a multiplier that adjusts the size of the bounding box used for cropping. By increasing this value, you can enlarge the cropped area around the region of interest, which can be useful if you need additional context around the detected objects. The default value is typically set to 1, meaning no additional scaling is applied.


This parameter controls the smoothing of the bounding box edges. A higher value will result in smoother transitions and less abrupt edges, which can be beneficial for certain applications where a more natural-looking crop is desired. The default value is usually set to a moderate level to balance between sharpness and smoothness.

Batch Crop From Mask Output Parameters:


This output provides the batch of images that have been cropped based on the provided masks. Each image in this batch corresponds to the region of interest identified by the respective mask, ensuring that only the relevant parts of the images are retained.


This output contains the batch of masks that have been cropped to match the regions of interest in the original images. These cropped masks can be used for further processing or analysis, as they align perfectly with the cropped images.


This output provides a single image that combines all the cropped regions from the batch into one composite image. This can be useful for visualizing the results of the cropping operation in a single view.


This output contains a single mask that combines all the cropped regions from the batch into one composite mask. This combined mask can be used for further analysis or visualization purposes.

Batch Crop From Mask Usage Tips:

  • Ensure that the number of original images matches the number of masks to avoid warnings and ensure accurate cropping.
  • Adjust the crop_size_mult parameter to include more context around the region of interest if needed.
  • Use the bbox_smooth_alpha parameter to control the smoothness of the bounding box edges for a more natural-looking crop.

Batch Crop From Mask Common Errors and Solutions:

[WARNING] ignore input: original_images, due to number of original_images ({imgs_num}) is not equal to number of masks ({masks_num})

  • Explanation: This warning occurs when the number of original images does not match the number of masks provided.
  • Solution: Ensure that the batch of original images has the same number of elements as the batch of masks to avoid this warning and ensure accurate cropping.

Empty masks detected

  • Explanation: This error occurs when one or more masks in the batch are empty, meaning they contain no non-zero values.
  • Solution: Check the masks to ensure they correctly identify the regions of interest. Replace or correct any empty masks to proceed with the cropping operation.

Batch Crop From Mask Related Nodes

Go back to the extension to check out more related nodes.
KJNodes for ComfyUI

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.