Was this an oversight? Or did their new image generation model generate an image that was essentially a copy of an existing image?
magick image-l.webp image-r.jpg -compose difference -composite -auto-level -threshold 30% diff.png
There is definitely enough empirical validation that shows image models retain lots of original copies in their weights, despite how much AI boosters think otherwise. That said, it is often images that end up in the training set many times, and I would think it strange for this image to do that.
Regardless, great find.