Remove–AI–Watermarks – CLI and library for removing AI watermarks from images

site-packages1

I don't know I really like the definitive indicator that something is AI so I can completely ignore anything else that comes from them.

Tiberium

This 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

> 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.

akersten

There'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) [0]: https://news.ycombinator.com/item?id=48200060

grebc

What’s wrong with showing off AI bro? Why the shame?

tamimio

Amaze amaze amaze - Rocky

gbraad

I 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.

sscaryterry

Yin and yang.

airstrike

Regardless 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.

a-dub

watermarking 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.

redox99

There's quite a bit of difference in the before and after. I hope they can find a way that better preserves details.

yalogin

This is brilliant pace. What I expected to see

UrbanNorminal

Can't we instead just use open source models?

b3ing

Watermarking 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

dostick

To remove Gemini watermark, open dev tools and block http request to watermark. It is overlaying logo in client.

cush

I love that this is exactly one position above OpenAI Adopts SynthID Watermarks

8cvor6j844qw_d6

Are there tools to apply SynthID to existing images? e.g., make AI watermarks unreliable for those relying on it

digitaltrees

Why? Don’t do this. Society is built on an implicit assumption of trust. You will erode the foundation that enables any success you might have in the short term.

xyzal

I want to add an AI watermark to my human content. Is there any way?