DALL·E 2

Training compute

3.4×10²³ FLOP

Parameters

3.5B

Published

Apr 6, 2022

DALL·E 2 is an AI model developed by OpenAI (United States), first published in April 2022. It works in the image generation domain, on tasks such as text-to-image and image generation.

Training it took an estimated 3.4×10²³ FLOP of compute (estimation method: third-party estimation). The model has 3,500,000,000 parameters. It was trained on roughly 167.1B datapoints.

Access: API access. Its weights are not openly released. The reference paper has 8,200 citations. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Image generation
Task: Text-to-image, Image generation
Training compute: 3.4×10²³ FLOP
Compute estimation method: Third-party estimation
Parameters: 3,500,000,000
Dataset size: 167.1B
Model accessibility: API access
Open weights: No
Citations: 8,200
Epoch confidence: Speculative