Mim is a privacy-first experimental SNS that shares the “meaning” of images instead of pixels. Images are never uploaded; on-device AI extracts semantic data, and the receiver reconstructs visuals locally using Stable Diffusion. This enables low-data, private visual communication. Reconstructed images may differ from originals. Features include privacy modes, Pro mode (fidelity, time, memory), social functions, and full on-device processing. Open source, built with Swift and Core ML.

getviktor.com — An AI coworker that actually does the work

An AI coworker that actually does the work

Hey everyone! 👋 I'm the solo developer behind Mim. Mim is an experimental iOS app that lets you share the "meaning" of an image instead of the actual pixels. On-device AI extracts semantics, and the receiver reconstructs it locally with Stable Diffusion. This means strong privacy and very little data transfer. It's still very much experimental — reconstructed images won't be pixel-perfect, but that's part of the fun and the research. I built this because I wanted a more private way to share visuals without sending full photos to the cloud. Fully open source on GitHub, built with Swift + Core ML. Would love your honest feedback: - Does the concept make sense? - How's the reconstruction quality for you? - What features would you like to see next? Thank you for checking it out! 🙏