News for hackers. Stuff that matters.
Re:Stable Attribution by louison11 on Monday February 06, 2023 @12:22AM (#34673687)
This. They probably simply used an “image similarity” algorithm, of which many are readily available and do not require much computing power. The credit at the bottom of the website for “Chroma”, a startup with no live product and hiring, suggests this could be a growth hack. Like “let’s ride the buzz of the moment with a barely useful tool quick to develop, hit front page of HN, and get some visibility.” Good for them, it worked, but yeah the product is probably bogus as you’ve demonstrated.
Re:Stable Attribution by bemmu on Monday February 06, 2023 @04:00AM (#34675036)
This will spread further than HN, as this is a current hot topic, and journalists are dying for more things to write about it.

Whether or not this tool works (assuming it does not, or at least I can’t see how it could), expect it to make the rounds on any tech publications that have previously written “stable diffusion bad” -type stories.

Re:Stable Attribution by chaostheory on Monday February 06, 2023 @10:06AM (#34678328)
It’s not for nothing. Like Twitter, the idea is so obvious, but only when someone introduces it to the masses.

This just needs to be done at the source. Ie whatever AI service is generating the image should generate attribution as part of the result

I was surprised that they even had a prototype. I thought this was just a really good CTA