VLM Caption & Annif Demo

How it works:

  1. Upload or take a photo in the input section below.
  2. The image is sent to a Visual Language Model to generate a caption.
  3. Annif suggests subjects based on the caption via the API of Finto AI.
  4. The prompt that instructs the VLM can be customized in the "VLM Prompt" section below.

Input
Output Language

Select the output language for caption and subject suggestions
Annif Project

Select the vocabulary from where subject suggestions are drawn (YSO, YKL, KAUNO)

Output