Has anyone used stable diffusion for face obfuscation? So you look like yourself - but face recognition models don't recognize you. So you can safely use those images on social networks without the fear of being doxed. What are the best tools for that? Is Foocus UI a good choice for it?

[martinenkoEduard]

Has anyone used stable diffusion for face obfuscation? So you look like yourself - but face recognition models don't recognize you. So you can safely use those images on social networks without the fear of being doxed. What are the best tools for that? Is foocus UI a good choice?

Can you share your experience with it - what Loras did you use, prompts, and so on?

[Woisek]

Not quite sure, what you are trying to archive, but face recognition for identity approval and face model creation are two completely different things.
Even if a face can't be identified, you still can train a face model from it.
Unless I didn't get what you mean. 🤔

[martinenkoEduard]

The goal is to modify your own face so you look like yourself, and can share this image on social networks, but you can't be found (doxed) by using face search algorithms.

[Woisek]

And you don't think, that search algorithms won't adapt this new information found on those social networks and combine the information with this new image? 🤪
It seems, you totally missed the point of face recognition and what you are trying to do, will not prevent anything.