Remove–AI–Watermarks – CLI and library for removing AI watermarks from images
- akersten - 16013 sekunder sedanThere's an underappreciated comment in the other thread about SynthID and OpenAI [0] that captures what (IMO) the hacker ethos on this should be. We care about privacy, we should not accept tools that barcode our every digital move. (note that the counter of "well, they don't do that yet" is not particularly convincing)
- site-packages1 - 16768 sekunder sedanI don't know I really like the definitive indicator that something is AI so I can completely ignore anything else that comes from them.
- b3ing - 3245 sekunder sedanWatermarking images generated from trained data on stolen copyrighted material, I get why so they can try to tell if something is real or not but something seems wrong
- Tiberium - 16398 sekunder sedanThis is a bit misleading as for Gemini it only properly removes the visible watermark. To remove SynthID it has to regenerate the image at low noise with SDXL, which will likely destroy a lot of small details, plus won't work for higher res properly (NB2 and GPT Image 2 support up to 4K image outputs)
- j2kun - 16344 sekunder sedan> Use cases where the threat model fits: You are preserving art or historical record against false-positive "AI-generated" labels.
Sorry, how does using AI to generate images have anything to do with this? Image generators cannot insert watermarks into things they did not generate, and it seems highly unlikely that you will get a false-positive watermark on human-generated art, especially if, as the readme says, these watermarks have high enough fidelity to trace to a specific session id. Plus the modifications to the image needed to erase watermarks would necessarily change the thing being "preserved."
[edit]: the more I read the more I'm convinced, the claimed use cases in the README are bullshit and the real reason is to provide a tool that helps people bypass "AI-generated" labels on social media for AI slop.
- airstrike - 14235 sekunder sedanRegardless of one's opinion about this particular project, it seems obvious to me that the path forward is proving authenticity of non-AI resources rather than attempting to watermark all the AI-generated ones.
- UrbanNorminal - 4362 sekunder sedanCan't we instead just use open source models?
- a-dub - 13956 sekunder sedanwatermarking only really works when the scheme is secret.
putting cyphertext in high frequency noise is old news. in generative land would be far more interesting to use the generative flexibility to encode in macrostructure.
- - 3435 sekunder sedan
- redox99 - 12475 sekunder sedanThere's quite a bit of difference in the before and after. I hope they can find a way that better preserves details.
- yalogin - 10857 sekunder sedanThis is brilliant pace. What I expected to see
- - 15939 sekunder sedan
- sscaryterry - 14267 sekunder sedanYin and yang.
- gbraad - 14322 sekunder sedanI just saw the announcement about OpenAI or so going to use SynthID and all I thought was; what can d be read(located) can be removed. Seems the tool already exists, proving my point.
- tamimio - 14421 sekunder sedanAmaze amaze amaze
- Rocky
- grebc - 15123 sekunder sedanWhat’s wrong with showing off AI bro? Why the shame?
Nördnytt! 🤓