Source (Via Xcancel)
Text
At first glance I thought this **** was just posting my work and claiming it as their own… and I was a bit angry. On closer examination, this is AI generated, and “angry” doesn’t come close to describing how I feel.
The second image is the original, just for reference.
Followup tweet:
it still is, which is why shit like this is so crazy because it happens a lot.
the model keeps basically nothing of the original image, less than a single bit per work it ingests on (the LAION-B dataset is almost 6 billion images, most models have more than double the input data, the models are 5-6 GB, and each image is 1024x1024 pixels), so the image can't be in there. and yet most of these models can manage to stitch together their input data almost perfectly. it's like the model splits images into their constituent parts and builds them back the same.
from a technical standpoint it's amazingly unlikely. from a human perspective it's scummy. from a legal perspective it's 100% plagiarism.
Extremely lossy compression with unspecified codeword encryption.
yeah and the artefacts are in the shape of the deepdream dog faces
I kind of miss the ol slugdogs. At least back then no one was trying to tell us it was coming for our jobs.