VQGAN + CLIP

Published

Dec 17, 2020

VQGAN + CLIP is an AI model developed by Heidelberg University (Germany), first published in December 2020. It works in the image generation domain, on tasks such as text-to-image.

Epoch AI has no training-compute estimate for this model. It was trained on roughly 252B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 4,226 citations.

Full record

Organization: Heidelberg University
Country of organization: Germany
Domain: Image generation
Task: Text-to-image
Dataset size: 252B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 4,226