StyleGAN

Training compute

3.9×10¹⁶ FLOP

Parameters

26.2M

Published

Dec 12, 2018

StyleGAN is an AI model developed by NVIDIA (United States), first published in December 2018. It works in the image generation domain, on tasks such as image generation.

Training it took an estimated 3.9×10¹⁶ FLOP of compute. The model has 26,200,000 parameters. It was trained on roughly 50M datapoints. Training ran on 8 NVIDIA V100 for about 168 hours.

Access: Open weights (non-commercial). Its weights are openly available. The reference paper has 14,496 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: NVIDIA
Country of organization: United States
Domain: Image generation
Task: Image generation
Training compute: 3.9×10¹⁶ FLOP
Parameters: 26,200,000
Dataset size: 50M
Training hardware: NVIDIA V100
Chips used: 8
Training time: 168 h
Training power draw: 5.0 kW
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Citations: 14,496
Epoch confidence: Confident