logoalt Hacker News

himata4113yesterday at 11:11 PM3 repliesview on HN

if you tell it to generate the AI image with a black background you can visually see the synthid with a good enough monitor, it's just a repeating fuzzy pattern, nothing special.

I have found great success of getting rid of it by masking every 2nd pixel, regenerating missing pixels and then once again masking every 2nd pixel offset by 1.

Used an off the shelf model to fill in the pixels, but I also exported a depthmap first (before any alternations) and denoised it so generated masked pixels comform to the original content. The result was obviously not 100% perfect, but with more time and a model fine tuned for this specific use-case would be able to remove any kind of ai watermarking without too many issues.


Replies

teravortoday at 12:07 AM

i wouldn't have any confidence in being able to remove a 0.5 bit watermark (presence/absence). what you see is probably a functional decoy.

show 1 reply
userbinatortoday at 12:36 AM

but with more time and a model fine tuned for this specific use-case would be able to remove any kind of ai watermarking without too many issues.

Always amusing to see AI used against itself.

tantaloryesterday at 11:18 PM

But why

show 1 reply