Explore CLIP embeddings of Wikimedia images

This system lets you do simple math on CLIP embeddings with prefixes like "-" to subtract CLIP vectors and "+" to add them.

• zebra -stripes +spots - Animals that look kinda like zebras but with spots instead of stripes.
• zebra -mammal +fish - Animals that are like zebras but fish instead of mammals.
• zebra -animal +car - Objects colored like zebras but more cars than animals.
• zebra -"black and white" - Baby zebras (brown & white) and a Greater Kudu (a brown & white striped 4-legged animal). Of course you could also find the same baby zebra searching for zebra -big +small or even more simply, just baby zebra.
• furry black and white striped animal - zebras, lemurs, and other furry black and white animals.
• striped horse-like animal - more zebras (and horses with stripes)
• zebra habitat -zebra - places that look like zebras might live there.

It can also do a search based on the difference between the CLIP embeddings of two images directly. For example, CLIP considers this image of a spider on a purple flower minus this image of the same kind of spider on a white flower to be this set of pictures which is mostly purple flowers without the spider.