ComfyUI Node: 🎨 Color Match To Reference

🎨 Color Match To Reference:

The ColorMatchToReference node is designed to adjust the color tones of a set of input images to match those of a reference image. This is achieved through a process that involves converting the images to the LAB color space, where the mean and standard deviation of the reference image's color channels are used to align the color distribution of the input images. By doing so, the node ensures that the input images adopt the color characteristics of the reference image, which can be particularly useful in scenarios where a consistent color palette is desired across multiple images or frames in a video. The node provides a flexible approach by allowing you to control the strength of the color matching effect, making it a powerful tool for enhancing visual consistency in your projects.

🎨 Color Match To Reference Input Parameters:

images

This parameter represents the batch of images whose colors you want to adjust. The images are processed in batches, and each image is converted to the LAB color space to facilitate color matching. The input should be in the form of a tensor, and the images are expected to be in RGB format.

reference_image

The reference image is the image whose color characteristics you want to apply to the input images. It serves as the standard for color matching, and its mean and standard deviation in the LAB color space are used to adjust the input images. The reference image should also be in RGB format and is processed similarly to the input images.

match_strength

This parameter controls the intensity of the color matching effect. It is a floating-point value ranging from 0.0 to 1.0, where 0.0 means no color matching is applied, and 1.0 means full color matching to the reference image. The default value is 1.0, allowing for complete color alignment by default.

batch_size

The batch size determines how many images are processed at a time. This can impact the performance and memory usage of the node. The parameter is an integer with a default value of 4, and it can range from 0 to 500. Adjusting the batch size can help optimize processing based on your system's capabilities.

🎨 Color Match To Reference Output Parameters:

IMAGE

The output is a batch of images that have been color-matched to the reference image. Each image in the output retains the original content but with adjusted color tones that reflect the reference image's color characteristics. The output images are in RGB format and are clamped to ensure valid color values.

🎨 Color Match To Reference Usage Tips:

• To achieve subtle color adjustments, consider setting the match_strength to a value less than 1.0. This allows for a blend between the original and reference colors, providing a more natural look.
• Experiment with different batch_size values to find the optimal performance for your system. Larger batch sizes may speed up processing but require more memory.

🎨 Color Match To Reference Common Errors and Solutions:

"CUDA out of memory"

• Explanation: This error occurs when the GPU does not have enough memory to process the images, especially with large batch sizes.
• Solution: Reduce the batch_size to decrease memory usage or ensure that other GPU-intensive applications are closed to free up resources.

"Invalid image format"

• Explanation: This error may arise if the input or reference images are not in the expected RGB format.
• Solution: Ensure that all images are correctly formatted as RGB before inputting them into the node.