Skip to content

Griffon

Describe a chosen region in a high-resolution image

Visit official site

What Griffon is

The model is described as a high-resolution LVLM above 1K with localisation ability, able to describe all content in a region you care about.

What you can do with it

  • Describe everything inside a region of interest
  • Detect and count objects in an image
  • Work on REC, phrase grounding and REG tasks

Pros & cons

✓ What we like

  • Input can be an image or some descriptions
  • A free trial is listed

! What to watch out for

  • Tasks are centred on the named localisation abilities
  • The described input is an image or some descriptions

FAQ

What resolution is named?

The material describes a high-resolution LVLM above 1K.

Is there a trial?

The material lists a free trial as the pricing note.

Last reviewed: 2026-11-15

More LLM API platform tools

View all →

How we review