falImage to imageComing soon

fal-ai/moondream-next/detection

Name: fal-ai/moondream-next/detection
Brand: fal

fal-ai/moondream-next/detection is an image to image tool from fal that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: image
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`image_url` required	URL or file	—	Image URL to be processed
`task_type` required	one of bbox_detection, point_detection, gaze_detection	—	Type of detection to perform
`detection_prompt` required	text	—	Text description of what to detect
`use_ensemble`	true or false	false	Whether to use ensemble for gaze detection
`combine_points`	true or false	false	Whether to combine points into a single point for point detection. This has no effect for bbox detection or gaze detection.
`show_visualization`	true or false	true	Whether to show visualization for detection

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/moondream-next/detection",
    "input": {
      "image_url": "https://llava-vl.github.io/static/images/monalisa.jpg",
      "task_type": "bbox_detection",
      "detection_prompt": "Person"
    }
  }'