This thread shows that there are outliers that are non-duplicated in the trainin...

		yunwal on Feb 1, 2023 \| parent \| context \| favorite \| on: Extracting training data from diffusion models This thread shows that there are outliers that are non-duplicated in the training set that still show up in results. https://twitter.com/alexjc/status/1620466058565132288 Specifically, this post confirms cases of a single image in the training set being "memorized" https://twitter.com/Eric_Wallace_/status/1620475626611421186...

Ah I see the section on this in the paper now, the 2nd half of 7.1 on page 14.