Skip to content
Discussion options

You must be logged in to vote

From the settings page, it's under Machine Learning. It looks like it uses the Smart Search vector embedding of each photo and then does a similarity search on that. The default distance is 0.01 which is quite close but you can change that yourself if you want it to be even more similar or open out to be a bit more fuzzy.

I've had some photos from burst shots that have come up as duplicates because they are so, so similar but not quite the same, e.g. eyes looking slightly different direction. Personally I'm happy with how that bit works.

I also think that the file hash is used to prevent exact duplicate files to be uploaded. If you've uploaded some files and try and do it again they get h…

Replies: 2 comments

Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Answer selected by DdHms
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
3 participants