Captions for images
Reads an image and returns written text about what it contains.
Describe a picture
Florence 2
Microsoft's compact vision-language model for dense image captioning, object detection, and visual grounding - reads an image and returns structured, accurate descriptions of what it contains.
Made by Microsoft10 creditsper run Free
Opens the Visual Analyzer tool with Florence 2 ready to use. You will need a free account to run it.
What Florence 2 makes, what it needs and what you get
What it makes
Describe a picture
Describes what is in a picture, or turns it into a prompt.
What you need
- The picture to describe
What you get
A written description
About Florence 2
Florence 2 is a compact model from Microsoft that reads an image and writes about it. You give it one image, and you get text back that describes what the image contains.
Florence 2 has no options to set. You add the image and run it. Each run takes a single file.
Use Florence 2 when you want a written caption for a picture you already have. It costs 10 credits.
Other models for this job
Same job: describe a picture. Compare before you choose.
What it does well
One image per run
Each run takes a single image.
How to use Florence 2
How It Works
How It Works
01
Add your image
Upload the one image you want described.
02
Run Florence 2
Start the run. It costs 10 credits.
03
Read the text
The description of your image comes back as text.
Tip To caption several pictures, run Florence 2 once per image. Each run costs 10 credits.
Good for
Captioning a single photo
Add a picture you already have and get a written caption for it.
Captioning a set of pictures
Work through a collection by running Florence 2 on each picture in turn.
Questions
Quick answers to help you get the most out of Florence 2 in FunAI Studio.
1. What do I need to provide?
2. What do I get back?
3. How much does Florence 2 cost?