ComfyUI Extension: Phase-Preserving Noise
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Generate phase-preserving structured noise for the input image.
Looking for a different extension?
Custom Nodes (0)
README
Structured Noise Generation
For ComfyUI
clone this repo into custom_nodes
For CLI
first install this repo
pip install .
Or for development mode:
pip install -e .
Usage:
python -m structured_noise.structured_noise_pytorch --path_in dog.jpg --path_out dog_structured_noise.png
refer to https://github.com/zengxianyu/PPD-examples for usage in training or inference
If you find this work useful, please cite:
@article{zeng2025neuralremaster,
title = {{NeuralRemaster}: Phase-Preserving Diffusion for Structure-Aligned Generation},
author = {Zeng, Yu and Ochoa, Charles and Zhou, Mingyuan and Patel, Vishal M and
Guizilini, Vitor and McAllister, Rowan},
journal = {arXiv preprint arXiv:2512.05106},
year = {2025}
}
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.