News for hackers. Stuff that matters.
Re:Compressing Images with Stable Diffusion by cantaloupe on Wednesday August 31, 2022 @11:31PM (#32671599)
This technique needs to be adopted everywhere immediately. With infinite gains over jpeg, how could we delay?

The commentary gave me a good chuckle, but I was actually pretty impressed with some of the results. I wonder if using stock images is playing to the strength of the model, because they may have actually been part of training.

Re:Compressing Images with Stable Diffusion by stavros on Thursday September 01, 2022 @05:31AM (#32674039)
I think that's actually the case, yeah. I think it mostly "remembered" these images, as it had been trained on them.