Sign in

Nodes Browser

ComfyDeploy: How ComfyUI-Tensor-Operations works in ComfyUI?

What is ComfyUI-Tensor-Operations?

This repo contains nodes for ComfyUI that implement some helpful operations on tensors, such as normalization.

How to install it in ComfyDeploy?

Head over to the machine page

  1. Click on the "Create a new machine" button
  2. Select the Edit build steps
  3. Add a new step -> Custom Node
  4. Search for ComfyUI-Tensor-Operations and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine

ComfyUI Tensor Operations Nodes

This repo contains nodes for ComfyUI that implement some helpful operations on tensors, such as normalization.

Updates

June 12th, 2024

  • Added Fast Image to Noise node, which generates a new image that is effectively a remix of the pixels in a source image.
  • This is all done on the GPU and is lightning fast in comparison with the WAS Node Suite Image to Noise node.

February 2nd, 2024

  • Initial release. Added Image Match Normalize and Latent Match Normalize nodes.

Nodes

Image Match Normalize

This node returns a normalized version of the target image using the mean and standard deviation of each color channel of the source image. If you want the color and brightness of your image to match the colour and brightness of another image, this is the node for you.

Latent Match Normalize

This node returns a normalized version of the target latent using the mean and standard deviation of each channel of the source latent. Latents encode color information differently than images and you may find that normalizing an image by instead normalizing its latent representation results in a "better" result that is closer to the coloring of the source.

Fast Image to Noise

Generates a new image by remixing the pixels of the source image randomly, optionally altering the brightness and making other tweaks. This node is intended to match the functionality of the Image to Noise node in the WAS Node Suite but for some reason results aren't identical.