Tiny classifier
SafeSocial
A multilabel image classifier that flags social-comparison triggers in Instagram images and video covers, so WebBrain can blur, hide, dim or warn. You can always reveal the image. Also available as an Android app.
13.6 MBEfficientNet-Lite0 model
8trigger categories
0servers: everything runs on the device
Offby default; you choose threshold and action
Why it matters
Not every decision needs a large model. A narrow job like this belongs to a tiny model that runs instantly, offline and privately.
What it looks for
Eight categories: romance and jealousy, social FOMO, luxury and status, travel and lifestyle, body and beauty, achievement and success, popularity, exclusivity and access. The threshold and what happens on a match are yours to set.
On Android (Google Play: com.esokullu.safesocial) it samples video frames and offers Light, Aggressive and Custom modes, with no classification server.
Models
-
safesocial-trigger-classifierEfficientNet-Lite0 trigger classifier 0 downloads · 0 likes
Caveats
- Not a safety guarantee and not a clinical or moderation tool: a personal filtering aid, intentionally experimental.
- No accuracy numbers have been published yet.
Read more on the blog
- Jev and SafeSocial arrive in WebBrain 36.8.02026-09-20
- SafeSocial is now on Google Play2026-10-05