image-ndd-lsh VS dupeguru

You might look into locally sensitive hashing. Here's some software I found with a quick search

What would be nice is something that used locality-sensitive hashing to bin very similar files together for further examination.

Dupeguru

Posted link appears be misspelled

This appears to be actual link:

https://dupeguru.voltaicideas.net/

I used to use DupeGuru which has some photo-specific dupe detection where you can fuzzy match image dupes based on content: https://dupeguru.voltaicideas.net/

But I switched over to czkawka, which has a better interface for comparing files, and seems to be a bit faster: https://github.com/qarmin/czkawka

Unfortunately, neither of these are integrated into Photoprism, so you still have to do some file management outside the database before importing.

I also haven't used Photoprism extensively yet (I think it's running on one of my boxes, but I haven't gotten around to setting it up), but I did find that it wasn't really built for file-based libraries. It's a little more heavyweight, but my research shows that Nextcloud Memories might be a better choice for me (it's not the first-party Nextcloud photos app, but another one put together by the community): https://apps.nextcloud.com/apps/memories

If your photos are exact duplicates you can also use the freeware dupeGuru app.

If you want a some other GUI options, AllDup or DupeGuru might be of interest. AllDup has a rather weird interface, though, imo.

I used DupeGuru (https://dupeguru.voltaicideas.net/) in the past but I'm not sure it's the best solution for you. Try it, it's open-source.

dupeGuru

dupeGuru is a graphical application available for macOS that can scan multiple drives and identify duplicate files based on various criteria like name, size, and content https://dupeguru.voltaicideas.net/