ComfyUI  >  Nodes  >  BrushNet >  Blend Inpaint

ComfyUI Node: Blend Inpaint

Class Name


nullquant (Account age: 1174 days)
Latest Updated
Github Stars

How to Install BrushNet

Install this extension via the ComfyUI Manager by searching for  BrushNet
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter BrushNet 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

Blend Inpaint Description

Seamlessly integrate inpainted regions into images for smooth transitions without artifacts using advanced techniques.

Blend Inpaint:

BlendInpaint is a powerful node designed to seamlessly integrate inpainted regions into original images, ensuring a smooth and natural transition. This node is particularly useful for AI artists who need to repair or modify specific areas of an image without leaving noticeable artifacts. By leveraging advanced techniques such as Gaussian blurring and tensor manipulation, BlendInpaint ensures that the inpainted areas blend harmoniously with the surrounding pixels. This node is essential for tasks that require high-quality image restoration or creative modifications, providing a professional finish to your artwork.

Blend Inpaint Input Parameters:


The inpaint parameter is a tensor representing the inpainted image that you want to blend into the original image. This tensor should ideally have the shape [B, H, W, C], where B is the batch size, H is the height, W is the width, and C is the number of color channels. If the batch size is missing, it will be automatically added. This parameter is crucial as it contains the modified regions that need to be seamlessly integrated into the original image.


The original parameter is a tensor representing the original image before any inpainting was applied. This tensor should also have the shape [B, H, W, C]. The original image serves as the base onto which the inpainted regions will be blended, ensuring that the final output maintains the integrity and context of the original artwork.


The mask parameter is used to specify the regions of the original image that have been inpainted. It is a tensor that helps in identifying which parts of the image need blending. The mask ensures that only the inpainted areas are modified, leaving the rest of the image untouched. This parameter is essential for precise and controlled blending.


The kernel parameter defines the size of the kernel used for Gaussian blurring. It must be an odd integer to ensure proper blurring. The kernel size affects the smoothness of the transition between the inpainted regions and the original image. A larger kernel size results in a smoother blend but may also blur more of the surrounding area. The default value is typically set to an odd number to maintain the integrity of the blurring process.


The sigma parameter controls the standard deviation of the Gaussian blur. It determines the extent of the blurring effect. A higher sigma value results in a more pronounced blur, which can help in achieving a smoother transition but may also affect the sharpness of the image. The default value is chosen to balance between smooth blending and image clarity.


The origin parameter is an optional tensor that specifies the origin points for the inpainted regions. If provided, it helps in accurately placing the inpainted areas within the original image. This parameter is particularly useful when dealing with multiple inpainted regions or when precise placement is required.

Blend Inpaint Output Parameters:


The blended_image parameter is the resulting tensor after the inpainted regions have been seamlessly integrated into the original image. This output maintains the original image's context while incorporating the inpainted modifications in a natural and visually appealing manner. The blended image is ready for further processing or final use in your creative projects.

Blend Inpaint Usage Tips:

  • Ensure that the inpaint and original tensors have matching dimensions to avoid shape mismatches during blending.
  • Use an appropriate mask to precisely define the inpainted regions, ensuring that only the desired areas are modified.
  • Adjust the kernel and sigma parameters to achieve the desired level of smoothness in the blending process. Experiment with different values to find the optimal settings for your specific use case.
  • If dealing with multiple inpainted regions, provide the origin parameter to accurately place each region within the original image.

Blend Inpaint Common Errors and Solutions:

Blend Inpaint gets batch of original images (%d) but only (%d) inpaint images

  • Explanation: This error occurs when the batch size of the original images does not match the batch size of the inpaint images.
  • Solution: Ensure that the inpaint and original tensors have the same batch size. If necessary, adjust the batch sizes to match before passing them to the node.

Kernel size must be an odd integer

  • Explanation: The kernel size provided for Gaussian blurring is not an odd integer.
  • Solution: Adjust the kernel parameter to be an odd integer. This ensures proper functioning of the Gaussian blur.

Mask dimensions do not match original image dimensions

  • Explanation: The dimensions of the mask tensor do not match those of the original image tensor.
  • Solution: Ensure that the mask tensor has the same height and width as the original image tensor. Adjust the mask dimensions if necessary.

Blend Inpaint Related Nodes

Go back to the extension to check out more related nodes.

© 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.