Abstract Image Noise Layer is a ComfyUI node in the AbstractImage/Layers category from ComfyUI-AbstractImaGen. Inputs: image, seed, randomize, num_layers…

ComfyUI node for [a/Abstract Image Generation](https://github.com/wakattac/ComfyUI-AbstractImaGen/). This node is designed to create unique abstract base images on the fly within your ComfyUI workflows, which can then be used as input for VAE encoding, image-to-image generation, or other creative processes.

ComfyUI-AbstractImaGen

image

seed

randomize

num_layers

noise_color_mode

noise_color_hex

alpha

shape_position

blend_mode

feather_layer

feather_sigma_min

feather_sigma_max

AbstractImageNoise

IMAGE

Abstract Image Noise Layer

Name	Type	Default	Description
image	IMAGE		—
seed	INT	00–18446744073709550000	Seed for noise pattern randomness.
randomize	BOOLEAN	false	If true, randomize noise scale, colors, position, and blend mode using the seed.
num_layers	INT	11–10	Number of noise layers to add.
noise_color_mode	COMBO	random	Color selection mode for noise. 'random' uses implicit RGB.
noise_color_hex	STRING		Hex code for noise color (used if Noise Color Mode is 'hex').
alpha	INT	2550–255	Alpha (transparency) for noise (0 is fully transparent, 255 is fully opaque).
shape_position	COMBO	full	Restrict noise pattern to a specific position/quadrant.
blend_mode	COMBO	normal	Blending mode to composite the noise layer onto the base image.
feather_layer	BOOLEAN	false	Apply Gaussian blur to the alpha channel of the noise layer.
feather_sigma_min	FLOAT	1.00–20	Minimum sigma for feathering (if applied).
feather_sigma_max	FLOAT	6.00–20	Maximum sigma for feathering (if applied).

Abstract Image Noise Layer

Inputs (12)

Outputs (1)