← All models · ViT-GPT2

use case · practical

Practical: an alt-text generator

Every image on the web should have alt text, and almost none do. Drop an image, get a draft description, tidy it if you like, and copy a ready-to-paste <img> tag — a starting point for accessible markup, generated on your device.

Drop an image, or click to choose
Two cats on a couch A cozy bedroom A riverside at golden hour
Selected image

Copy-ready snippet:

<img src="…" alt="">

A model draft is a starting point, not a rubber stamp — always read it in context. Decorative images should get empty alt=""; informative ones deserve a human check.

← Back to ViT-GPT2 · Next: Wild →