About

Building Mim, an experimental iOS SNS that transmits meaning instead of raw images. Using on-device AI (Stable Diffusion, Core ML, SigLIP), we compress photos into semantic representations and reconstruct them locally. Exploring the future of semantic communication. AI enthusiast learning in public from Japan.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

TASUKU Kato

11d ago

Mim - Transmit meaning, not pixels — Privacy-first AI SNS

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.
View more