PIXART-α

Training compute

1.5×10²¹ FLOP

Parameters

600M

Published

Sep 30, 2023

PIXART-α is an AI model developed by Huawei Noah's Ark Lab, The University of Hong Kong and Hong Kong University of Science and Technology (HKUST) (China and Hong Kong), first published in September 2023. It works in the image generation domain, on tasks such as image generation and text-to-image.

Training it took an estimated 1.5×10²¹ FLOP of compute (estimation method: hardware,comparison with other models). The model has 600,000,000 parameters. It was trained on roughly 626B datapoints. Training ran on NVIDIA V100.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Huawei Noah's Ark Lab, The University of Hong Kong, Hong Kong University of Science and Technology (HKUST)
Country of organization: China, Hong Kong
Domain: Image generation
Task: Image generation, Text-to-image
Training compute: 1.5×10²¹ FLOP
Compute estimation method: Hardware, Comparison with other models
Parameters: 600,000,000
Dataset size: 626B
Training hardware: NVIDIA V100
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident

SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.

← All ai models