Pass IndexThe State of AISign in

pattern-diffusion

Compared to a full-scale diffusion model such as SDXL or FLUX, unet diffusion models require significantly less data and compute to train when all images have repeating patterns/features.

text → image · made by Arrexel

Sold by

Nobody in the catalogue publishes a price for this yet.

About

pattern-diffusion — an images model from Arrexel.

It takes text and returns images. It was published in August 2025. The catalogue files it under image. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.

Every current figure

Maker
Arrexel
Register
model
Takes
text
Returns
image
Published
August 2025
Parameters
866 million · read from its own weights
Licence
apache-2.0

Known as 1 name

Arrexel/pattern-diffusion