MosaicML Diffusion

Training compute

1.1×10²² FLOP

Parameters

1.3B

Published

Apr 28, 2023

MosaicML Diffusion is an AI model developed by Databricks (United States), first published in April 2023. It works in the image generation domain, on tasks such as image generation and text-to-image.

Training it took an estimated 1.1×10²² FLOP of compute (estimation method: hardware). The model has 1,289,952,427 parameters. It was trained on roughly 790M datapoints. Training ran on 128 NVIDIA A100 for about 186 hours.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Databricks
Country of organization: United States
Domain: Image generation
Task: Image generation, Text-to-image
Training compute: 1.1×10²² FLOP
Compute estimation method: Hardware
Parameters: 1,289,952,427
Dataset size: 790M
Training hardware: NVIDIA A100
Chips used: 128
Training time: 186 h
Training power draw: 102.0 kW
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident