ComfyUI Node: Frequency Combine

Frequency Combine:

The FrequencyCombine node is designed to merge two images by performing either an addition or multiplication operation on their pixel values. This node is particularly useful in image processing tasks where you want to blend or combine images in a controlled manner. By allowing you to choose between addition and multiplication, it provides flexibility in how the images are combined, enabling creative effects and enhancements. The node ensures that the resulting image maintains pixel values within a valid range, preventing any overflow or underflow issues. This capability is essential for artists and designers who wish to experiment with image blending techniques without delving into complex coding or mathematical operations.

Frequency Combine Input Parameters:

image1

image1 is the first image input for the combination process. It serves as one of the two primary sources of pixel data that will be merged using the specified operation. The dimensions of this image are crucial as they determine the target size for any necessary resizing of the second image. This parameter does not have specific minimum or maximum values, but it should be a valid image tensor with dimensions in the format [B, H, W, C], where B is the batch size, H is the height, W is the width, and C is the number of channels.

image2

image2 is the second image input that will be combined with image1. Like image1, it should be a valid image tensor with dimensions [B, H, W, C]. If image2 has slightly different dimensions from image1, it will be resized to match image1 to ensure a seamless combination. This resizing is automatically handled by the node if the size difference is within a 3-pixel threshold.

operation

The operation parameter determines the method used to combine the two images. It offers two options: "add" and "multiply". When "add" is selected, the pixel values of image1 and image2 are summed, and the result is clamped to ensure values remain within the [0, 1] range. When "multiply" is chosen, the pixel values are multiplied, naturally keeping the result within the valid range. This parameter allows you to control the blending effect, with "add" typically resulting in a brighter image and "multiply" often producing a more complex interaction of colors and intensities.

Frequency Combine Output Parameters:

result

The result is the output image obtained after combining image1 and image2 using the specified operation. This image retains the dimensions of image1 and contains the blended pixel values resulting from either the addition or multiplication process. The output is a single image tensor with values clamped to the [0, 1] range, ensuring it is suitable for further processing or display. This output is crucial for visualizing the effects of the combination and for use in subsequent image processing tasks.

Frequency Combine Usage Tips:

• Ensure that both input images are in the same format and have compatible dimensions to avoid unnecessary resizing and potential quality loss.
• Experiment with both "add" and "multiply" operations to achieve different artistic effects. "Add" can enhance brightness and contrast, while "multiply" can create more subtle and intricate blends.
• Use this node in conjunction with frequency separation techniques to combine specific frequency components of images for advanced image manipulation.

Frequency Combine Common Errors and Solutions:

Images size mismatch too large to process. Image1: {h1}x{w1}, Image2: {h2}x{w2}

• Explanation: This error occurs when the size difference between the two input images exceeds the allowable 3-pixel threshold in either dimension.
• Solution: Ensure that the input images have similar dimensions or manually resize them to be within the 3-pixel difference limit before using the node.

Low frequency radius must be smaller than medium frequency radius

• Explanation: This error is related to frequency separation and occurs when the specified low frequency radius is not smaller than the medium frequency radius.
• Solution: Adjust the frequency radii values to ensure that the low frequency radius is less than the medium frequency radius. This is crucial for proper frequency separation before combining images.