Search engines crawl webpages to discover images and extract data from images, such as metadata and file names. Google considers factors – such as surrounding text ... you’ll get an image ...

A trio of trappers were patrolling remote backroads when a 16-foot python jumped out. They teamed up to capture it.

(1) We released the 50 diffusion steps model (instead of 1000 steps) which runs 20X faster with comparable results. (2) Calling CLIP just once and caching the result runs 2X faster for all models.