Find objects in a picture
MoonDreamNext Detection
MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.
Opens the Visual Analyzer tool with MoonDreamNext Detection ready to use. You can look around as a guest. Running it takes the Pro plan or higher.


What MoonDreamNext Detection makes, what it needs and what you get
What it makes
Find objects in a picture
Finds objects in a picture.
What you need
- The picture to work on
- What to find
You also make one choice about how it runs.
What you get
A written list of what it found
About MoonDreamNext Detection
MoonDreamNext Detection finds objects in a picture. It is made by Moondream.
To use it, you provide the picture to work on and what to find. You also make one choice about how it runs. You get a written list of what it found.
A 5 s result costs about 55 credits. Longer or shorter results cost in proportion, about 11 credits per second. It is included from the Pro plan and up. You run it in the Visual Analyzer tool, in your browser.
Best for
Typical uses for this kind of model.
- Counting or locating things in a picture
- Checking what a picture contains
- Guiding other edits
How to use MoonDreamNext Detection
- 1
Add the picture to work on
Upload your files, or pick them from your library, then write a line about what you want.
- 2
Make your choices
You also make one choice about how it runs. If you change an option, the cost updates and is shown before you generate.
- 3
Generate your reply
A written list of what it found. Your result appears in the studio, ready to download.