It's copy-pasting parts of the training images over and over.
In figure 8 of the technical report [0], compare the hair in images (0,0), (2,0), (3,0), (3,3), (4,4).
The paper suggests their method generates copyright-free images, yet they are very obviously derived from the input images and you can identify the parts of individual input images that are mashed together to form the output.
All in all their method seems to be performing "obfuscated memorization," in the sense that the generated images are scrambled up enough to fool their plagiarsim-detector loss function.
In figure 8 of the technical report [0], compare the hair in images (0,0), (2,0), (3,0), (3,3), (4,4).
The paper suggests their method generates copyright-free images, yet they are very obviously derived from the input images and you can identify the parts of individual input images that are mashed together to form the output.
All in all their method seems to be performing "obfuscated memorization," in the sense that the generated images are scrambled up enough to fool their plagiarsim-detector loss function.
[0] http://make.girls.moe/technical_report.pdf