ComfyUI Custom Node - Dimensional Latent Perlin Noise

Description

Dimensional Latent Perlin is a custom node for ComfyUI that generates Perlin noise in the latent space. This node is designed to work seamlessly with various diffusion models and can be used as an alternative or complement to standard random noise generators in image generation pipelines.

Features

• Generate Perlin noise that matches the latent space of diffusion models

• Adjustable parameters for fine-tuning the noise generation

• Compatible with different model architectures and latent space dimensions

• Can adapt to existing latent images or model specifications

• Supports batch processing

Installation

1. Clone this repository into your ComfyUI custom nodes directory via ComfyUI Manager or:

git clone https://github.com/neuralsamurai/ComfyUI-Dimensional-Latent-Perlin.git

1. Restart ComfyUI or reload custom nodes.

Usage

After installation, the Dimensional Latent Perlin node will be available in the ComfyUI interface under the "latent/noise" category.

You can also download the workflow I made which has this node included in the image2image group: https://civitai.com/models/622830/flux-all-in-one-t2i-i2i-image-prompting-upscale-qol

Input Parameters

• seed: Seed for random number generation (for reproducibility)

• width: Width of the output image

• height: Height of the output image

• batch_size: Number of images to generate in a batch

• detail_level: Controls the level of detail in the Perlin noise

• downsample_factor: Downsampling factor for the latent space

Optional Inputs (if neither is given defaults to 4 dimensions)

• latent_image: An existing latent image to match dimensions

• model: A diffusion model to match latent space specifications

Output

• LATENT: A latent representation of the generated Perlin noise