---
title: capit
emoji: 🔎
colorFrom: red
colorTo: gray
sdk: docker
app_port: 7860
pinned: false
short_description: A glass-box image captioner (Show, Attend and Tell) vs BLIP.
---

# capit — backend

Side-by-side captioning API: a from-scratch *Show, Attend and Tell* model (glass box —
per-word attention + rejected beams) and BLIP (closed box). Code:
https://github.com/Bukunmi2108/capit