GLIDE

Training compute

4.7×10²² FLOP

Parameters

3.5B

Published

Dec 20, 2021

GLIDE is an AI model developed by OpenAI (United States), first published in December 2021. It works in the image generation domain, on tasks such as image generation and text-to-image.

Training it took an estimated 4.7×10²² FLOP of compute (estimation method: comparison with other models). The model has 3,500,000,000 parameters. It was trained on roughly 7.6T datapoints.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 4,722 citations. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Image generation
Task: Image generation, Text-to-image
Training compute: 4.7×10²² FLOP
Compute estimation method: Comparison with other models
Parameters: 3,500,000,000
Dataset size: 7.6T
Numerical format: FP16
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 4,722
Epoch confidence: Speculative