lucataco / pixart-xl-2

PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5

  • Public
  • 44.5K runs
  • GitHub
  • Paper
  • License



Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 13 seconds. The predict time for this model varies significantly based on the inputs.


This is an implementation of PixArt-alpha/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.

Source code is available at

Model Description

  • Developed by: Pixart-α
  • Model type: Diffusion-Transformer-based text-to-image generative model
  • License: CreativeML Open RAIL++-M License
  • Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Transformer Latent Diffusion Model that uses one fixed, pretrained text encoders (T5)) and one latent feature encoder (VAE).
  • Resources for more information: Check out our GitHub Repository and the Pixart-α report on arXiv.

Model Sources

For research purposes, we recommend our generative-models Github repository (, which is more suitable for both training and inference and for which most advanced diffusion sampler like SA-Solver will be added over time. Hugging Face provides free Pixart-α inference.



Training Efficiency

PixArt-α only takes 10.8% of Stable Diffusion v1.5’s training time (675 vs. 6,250 A100 GPU days), saving nearly $300,000 ($26,000 vs. $320,000) and reducing 90% CO2 emissions. Moreover, compared with a larger SOTA model, RAPHAEL, our training cost is merely 1%. alt text



The chart above evaluates user preference for Pixart-α over SDXL 0.9, Stable Diffusion 2, DALLE-2 and DeepFloyd. The Pixart-α base model performs comparable or even better than the existing state-of-the-art models.