# Moondream Detection

Canonical page: https://fuser.studio/models/moondream-detection

Moondream Detection in Fuser finds objects in an image from a text query and returns boxes and points. Use the output to crop or mask the next step.

## Specs

| Spec | Value |
| --- | --- |
| Inputs | Image, Detection Prompt (text) |
| Output | image, text |
| Cost | 7 credits per run |

Pinpoint bounding boxes, track human gaze vectors, and localize interface elements with instant spatial vision

Creator: Moondream (Vikhyat Korrapati)

Also known as: MoondreamNext

[Analyze image coordinates](https://app.fuser.studio)

## How Moondream Detection works

Three straightforward steps to extract bounding boxes, target points, or gaze vectors from your imagery.

### Upload source image

Provide a high-contrast image containing the objects, interfaces, or human subjects you want to localize.

### Specify target and mode

Choose between bounding box, point centroid, or gaze detection, and enter a direct descriptive label.

### Retrieve spatial coordinates

Receive an annotated visualization with color-coded overlays alongside normalized coordinate data.

## What Moondream Detection is good at

Engineered with custom spatial tokenizers to deliver low-latency coordinate extraction and attention tracking.

### Gaze Direction Tracking

Traces directional vectors from human eyes to identify focus points across visual frames, supported by custom spatial tokenizers.

### Precise Point Centroids

Identifies exact centroid coordinates and sharp crosshair markers for interface buttons, hardware switches, or small physical artifacts without requiring bounding margins.

### Object Boundary Localization

Emits crisp, color-coded boundary boxes fitted to targeted items using specialized coordinate and size tokens without clumsy text generation.

### Monte Carlo Ensemble Mode

Averages flipped image encodings and Monte Carlo predictions on complex static compositions when absolute line-of-sight precision is critical.

## Made with Moondream Detection

Spatial overlays, centroid targeting, and line-of-sight vectors generated across high-contrast visual scenes.

### High-fashion gaze vector tracking

### Architectural centroid and bounding box detection

### Sporting equipment point localization

### Documentary gaze analysis

## What people build with Moondream Detection

Built for engineers and researchers who require fast spatial parsing without the overhead of heavy vision-language models.

### Driver Attention Monitoring

Track driver line-of-sight, head orientation, and mirror checks in automotive cabin safety feeds with sub-second turnaround.

### UI Element Targeting

Extract button coordinates, form fields, and navigation icons to automate visual testing and build interaction heatmaps.

### Athletic Gaze Analytics

Analyze athlete visual focus and target tracking during competitive play to evaluate decision-making speed.

### Robotic Pick-and-Place

Detect precise part centroids and perimeter boundaries to guide automated robotic grippers and sorting systems.

### Interactive Media Installations

Create interactive museum installations and digital displays that respond in real time to where visitors direct their eyes.

## Frequently Asked Questions

### What is MoondreamNext?

MoondreamNext is the experimental release branch of the Moondream small vision-language model, introducing dedicated gaze tracking and refined spatial point detection alongside standard bounding boxes.

### What detection tasks can Moondream Detection perform?

Moondream Detection performs three primary spatial vision tasks: rectangular object localization (`bbox_detection`), centroid coordinate pinpointing (`point_detection`), and human eye-gaze vector tracking (`gaze_detection`).

### When should I enable the ensemble method?

Enable `use_ensemble` only for static, complex images where extreme gaze accuracy is necessary. Turning on ensemble mode performs flipped image encodings and Monte Carlo predictions to refine coordinate estimations, which increases precision while compounding inference latency.

### What are the main limitations of Moondream Detection?

Moondream is not built for pixel-level semantic segmentation masks, dense scenes containing hundreds of tiny objects, high-resolution document OCR, or multi-turn conversational reasoning.

### Who created Moondream?

Moondream was created by Vikhyat Korrapati (Moondream/M87 Labs) as an ultra-efficient small vision-language model designed for low-latency spatial understanding on resource-constrained hardware.

## Try Moondream Detection on Fuser

Pinpoint bounding boxes, track human gaze vectors, and localize interface elements with instant spatial vision

[Analyze image coordinates](https://app.fuser.studio)

## Related models

- [Gemini Image](https://fuser.studio/models/gemini-image.md)
- [GPT Image](https://fuser.studio/models/gpt-image.md)
- [Seedream](https://fuser.studio/models/seedream.md)
- [FLUX.3 Image](https://fuser.studio/models/flux-3-image.md)
- [FLUX.2](https://fuser.studio/models/flux-2.md)
- [ESRGAN Upscaler](https://fuser.studio/models/esrgan-upscaler.md)

Node reference: [Moondream Detection docs](https://docs.fuser.studio/docs/nodes/image/moondream-detection.md)