Detect Regions (VLM)

🤖 AI Drafted (Not reviewed)

Use this when: Apple Vision misses regions on hard material (archaic hands, damaged pages) and you want a vision LLM to find the text regions instead. Uses whatever model you pick at run time — compare providers by running this next to the Apple Vision preset.

Folder	/Detect Regions
Steps	2
Tags	preset, regions, bboxes, layout, vlm

Steps, in run order

1. Files

Tool: Files — Pass through input files from workflow context

2. Detect Regions (VLM)

Tool: Detect Regions — Finds WHERE the words are, on-device and free. Apple Vision reads the page locally to locate line and word boxes, so it does produce text — that text is a by-product of finding the boxes, not a transcription: it never replaces the page’s transcript, and no model is called. Runs before a transcriber so every box exists up front.

Settings this step uses:

Option	Value
language	auto
provider	vlm
thinking_mode	medium