[tmp65535]

This app, now almost 5 years old (warning, NSFW):

http://driftwheeler.com

uses a custom brute force search in CUDA, based on bitonic sort (https://en.m.wikipedia.org/wiki/Bitonic_sorter) and a fractional norm distance metric (f=0.5, i.e., sqrt):

https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.23...

In 2017, on a low-end GPU, the indexing took about 10 minutes of 100% utilization, for a dozen patches covering each of 50,000 images (feature vectors were 1,024 32-bit floats).

After that, the app just queries a precomputed list (256 precomputed matches per query) depending on where in the image the user pressed. Even with hundreds of simultaneous users, it can hardly keep a $5 Linode busy.

Good times...

[nnoitra]

What's the relation between Similarity Search and generating pictures of naked women using Neural Nets?

[tmp65535]

The app allows you to search through a large collection of images by "pressing" parts of an image.

The images are not generated.