Visit ComfyUI Online for ready-to-use ComfyUI environment
Merge high/low-frequency image components in HSV color space for precise brightness/contrast control, ideal for AI artists.
The FrequencyCombinationHSV node is designed to merge high-frequency and low-frequency components of images using the HSV (Hue, Saturation, Value) color space. This node is particularly useful for AI artists who want to blend different frequency details of images to achieve specific visual effects. By focusing on the Value channel in the HSV color space, this node allows for precise control over the brightness and contrast of the combined image, resulting in a more natural and visually appealing output. The main goal of this node is to provide a seamless way to recombine images that have been separated into high and low-frequency components, ensuring that the final image retains the desired details and overall appearance.
The high_freq
parameter represents the high-frequency component of the image, which contains the fine details and textures. This input should be an image tensor with the shape (batch, height, width, channels). The high-frequency component is typically obtained through a frequency separation process and is crucial for preserving the intricate details in the final combined image.
The low_freq
parameter represents the low-frequency component of the image, which contains the overall color and lighting information. This input should also be an image tensor with the shape (batch, height, width, channels). The low-frequency component is essential for maintaining the general appearance and color balance of the final combined image.
The output parameter is an image tensor that represents the combined result of the high-frequency and low-frequency components. This combined image retains the fine details from the high-frequency input while preserving the overall color and lighting from the low-frequency input. The output tensor has the shape (batch, height, width, channels) and is ready for further processing or display.
high_freq
and low_freq
inputs have the same dimensions to avoid any shape mismatch errors.{i}
does not have 3 channels© Copyright 2024 RunComfy. All Rights Reserved.