ComfyUI Custom Node for "Golden Noise for Diffusion Models: A Learning Framework" and most of the code is adapted from here. This node refines the initial latent noise in the diffusion process, enhancing both image quality and semantic coherence.

Installation

Navigate to your ComfyUI's custom_nodes directory:

cd ComfyUI/custom_nodes

Clone this repository:

git clone https://github.com/LucipherDev/ComfyUI-Golden-Noise

Install requirements:

cd ComfyUI-Golden-Noise
pip install -r requirements.txt

Or Install using ComfyUI Manager

Usage

Download Safetensors of the pre-trained NPNet weights of Stable Diffusion XL, DreamShaper-xl-v2-turbo, and Hunyuan-DiT from Huggingface LucipherDev/Golden-Noise-NPNets and put them in the models/npnets folder.

The node can be found in "sampling/custom_sampling/noise" category as "GoldenNoise".

Look at the example workflow for more info.

Inputs

noise: Noise output from RandomNoise node
conditioning: Prompt conditioning
model_id: "SDXL", "DreamShaper", "DiT"
npnet_model: Pretrained NPNet model
device: "cuda", "cpu"

Citation

Original Paper.

@misc{zhou2024goldennoisediffusionmodels,
      title={Golden Noise for Diffusion Models: A Learning Framework}, 
      author={Zikai Zhou and Shitong Shao and Lichen Bai and Zhiqiang Xu and Bo Han and Zeke Xie},
      year={2024},
      eprint={2411.09502},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2411.09502}, 
}