A.i. watermark removers are popping up like mushrooms. These are trained a.i. models that recognize and remove watermarks, even those never seen before.
After some testing Francesco realized how almost everything seems to depend simply on the contrast between pixels.
After some testing Francesco realized how almost everything seems to depend simply on the contrast between pixels.
His knowledge in rendering generation (and about the quality settings f the final rendering) allowed him to understand that primarily the whole process of these watermark remover, was nothing more than a pixel-per-pixel contrast analysis and patching.
Having understood this, the a.i. process can be easily broken.
It’s just needed to prevent A.i. from finding "valid contrasts” as a clue as where to act.
Therefore: reduce the contrast of shapes, reduce the contrast of colors, and alter the repetitiveness of the pattern used.
It’s just needed to prevent A.i. from finding "valid contrasts” as a clue as where to act.
Therefore: reduce the contrast of shapes, reduce the contrast of colors, and alter the repetitiveness of the pattern used.
We will be doing an online forum soon where we will look deeper into the issue, figure out if there are simpler systems than total watermarking to protect oneself, and provide watermark templates to customize for those who were not too digitally savvy.
If you are interested follow us (on Facebook and instagram) to get all the details in the future.
Please if you have read this far, share with as many people as you can. This way we can save so many intellectual properties and artists’ works.
For prompters: This is adaptation.
Please if you have read this far, share with as many people as you can. This way we can save so many intellectual properties and artists’ works.
For prompters: This is adaptation.
#createdontscrape #aiban #noai #stopai #aitheft #stablediffusion #imagen #aiprotest #stableai #protectart #artistlife
• • •
Missing some Tweet in this thread? You can try to
force a refresh
