StyleGAN2

Parameters

30M

Published

Dec 3, 2019

StyleGAN2 is an AI model developed by NVIDIA and Aalto University (United States and Finland), first published in December 2019. It works in the image generation domain, on tasks such as image generation.

Epoch AI has no training-compute estimate for this model. The model has 30,000,000 parameters. It was trained on roughly 114M datapoints. Training ran on 8 NVIDIA V100 for about 2K hours.

Access: Open weights (restricted use). Its weights are openly available. The reference paper has 7,908 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: NVIDIA, Aalto University
Country of organization: United States, Finland
Domain: Image generation
Task: Image generation
Parameters: 30,000,000
Dataset size: 114M
Training hardware: NVIDIA V100
Chips used: 8
Training time: 2,016 h
Training power draw: 4.9 kW
Model accessibility: Open weights (restricted use)
Open weights: Yes
Citations: 7,908
Epoch confidence: Confident