A 100KB text-to-image AI model?

Researchers at NVidia are showing off Perfusion, a text-to-image model they say is 100KB in size and takes four minutes to train. What could possibly go wrong? (ᔥ Hackaday)

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.