Pass IndexThe State of AISign in

PixArt-XL-2-1024-MS

Pixart-α consists of pure transformer blocks for latent diffusion: It can directly generate 1024px images from text prompts within a single sampling process.

text → image · made by PixArt

Sold by

Nobody in the catalogue publishes a price for this yet.

About

PixArt-XL-2-1024-MS — an images model from PixArt.

It takes text and returns images. It was published in November 2023. The catalogue files it under image. Its weights are published under the openrail++ licence, which attaches conditions the plain open licences do not.

Every current figure

Maker
PixArt
Register
model
Takes
text
Returns
image
Published
November 2023
Parameters
612 million · read from its own weights
Licence
openrail++

Known as 1 name

PixArt-alpha/PixArt-XL-2-1024-MS