ComfyUI > Nodes > ComfyUI-Image-Filters > Frequency Separate

ComfyUI Node: Frequency Separate

Class Name

FrequencySeparate

Category
image/filters
Author
spacepxl (Account age: 295days)
Extension
ComfyUI-Image-Filters
Latest Updated
2024-06-22
Github Stars
0.08K

How to Install ComfyUI-Image-Filters

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

Frequency Separate Description

Isolate high-frequency image components to enhance details, using subtraction or division methods for texture and edge analysis.

Frequency Separate:

The FrequencySeparate node is designed to help you isolate the high-frequency components of an image by separating it from its low-frequency counterpart. This process is particularly useful in image processing tasks where you need to enhance or analyze specific details within an image. By using either subtraction or division methods, the node allows you to effectively highlight the finer details (high-frequency components) while minimizing the broader, smoother areas (low-frequency components). This can be beneficial for tasks such as texture analysis, edge detection, or any scenario where distinguishing fine details from the overall image is crucial.

Frequency Separate Input Parameters:

original

This parameter represents the original image that you want to process. It serves as the primary input from which the high-frequency components will be extracted. The image should be in a format compatible with the node's processing capabilities.

low_frequency

This parameter is the low-frequency version of the original image. It is used as a reference to separate the high-frequency components. The low-frequency image typically contains the smoother, less detailed parts of the original image.

mode

The mode parameter determines the method used to separate the high-frequency components from the original image. It can take one of two values: subtract or divide. When set to subtract, the node will subtract the low-frequency image from the original image and add a constant value of 0.5. When set to divide, the node will divide the original image by the low-frequency image, adjusted by a small epsilon value, and then scale the result by 0.5. This parameter allows you to choose the most suitable method for your specific image processing task.

eps

The eps parameter is a small constant value used to prevent division by zero when the mode is set to divide. It ensures numerical stability during the division process. The default value is 0.1, with a minimum value of 0.01 and a maximum value of 0.99. Adjusting this parameter can help fine-tune the separation process, especially in images with very low-intensity values.

Frequency Separate Output Parameters:

high_frequency

The high_frequency output is the result of the separation process. It contains the high-frequency components of the original image, highlighting the finer details and textures. This output can be used for further image analysis, enhancement, or any other processing tasks that require a focus on the detailed aspects of the image.

Frequency Separate Usage Tips:

  • To enhance fine details in an image, use the subtract mode for a straightforward separation of high-frequency components.
  • When working with images that have very low-intensity values, adjust the eps parameter to ensure numerical stability and avoid artifacts in the output.
  • Experiment with both subtract and divide modes to see which method provides the best results for your specific image processing task.

Frequency Separate Common Errors and Solutions:

Image size mismatch

  • Explanation: The original and low-frequency images must be of the same size for the separation process to work correctly.
  • Solution: Ensure that both input images have the same dimensions before passing them to the node.

Division by zero

  • Explanation: When using the divide mode, very low values in the low-frequency image can cause division by zero errors.
  • Solution: Adjust the eps parameter to a slightly higher value to prevent division by zero and ensure numerical stability.

Unsupported image format

  • Explanation: The node may not support certain image formats.
  • Solution: Convert your images to a compatible format before using the node. Common formats like PNG or JPEG are usually supported.

Frequency Separate Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-Image-Filters
RunComfy

© 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.