I’ve only heard that running images through a VAE just once seems to break the Nightshade effect, but no one’s really published anything yet.
You can finetune models on known bad and incoherent images to help it to output better images if the trained embedding is used in the negative prompt. So there’s a chance that making a lot of purposefully bad data could actually make models better by helping the model recognize bad output and avoid it.
So there’s a chance that making a lot of purposefully bad data could actually make models better by helping the model recognize bad output and avoid it.
I’ve only heard that running images through a VAE just once seems to break the Nightshade effect, but no one’s really published anything yet.
You can finetune models on known bad and incoherent images to help it to output better images if the trained embedding is used in the negative prompt. So there’s a chance that making a lot of purposefully bad data could actually make models better by helping the model recognize bad output and avoid it.
VAE?
Think they mean a Variational AutoEncoder
Variable. But no running it through that will not break any effect
This would be truly ironic
If users have verry much control and we can coordinate then you could gaslight the AI into a screwed up alternate reality