Molly

Analysis of Results

Surprisingly, these images were not really what we were looking for. The VQGAN image came back as a complex image whereas the human one was just a face with three eyes. Interestingly, when fed into the CLIP prefix captioning we can find out that it was able to detect that it was a closeup of a person with a red eye on its head, while for the hand drawn art it said it was a smiley face but didn't mention anything about the eye.