capabilities.work

Detect objects and bounding boxes in an image

One step with Hugging Face. We can help you get access.

Get something done

Detect objects and bounding boxes in an image

with Hugging Face · Vision

Use Hugging Face: its Hugging Face Inference Computer Vision API lets you detect objects and bounding boxes in an image in a single step (POST /models/{model_id}/object-detection). capabilities.work can help you get signed up and connected.

  • Can a Hugging Face model find every object in a photo and tell me where each one is?
  • Which inference task returns bounding boxes with labels rather than a single category?
Say it to your AI assistant
  • Detect the objects in this photo using model {model_id} and give me their bounding boxes.
  • Run object detection with {model_id} and list each label it finds with its box.
For your developer

POST /models/{model_id}/object-detection in Hugging Face Inference Computer Vision API. Full spec on APIs.io.

More you can do with Hugging Face

Classify an image into categoriesGet a chat completion via the inference routerPreview the first rows of a dataset splitPage through rows of a dataset splitList Inference Endpoints in a namespaceDeploy a new Inference EndpointGet an Inference Endpoint's detailsChange an endpoint's model, hardware or scalingPermanently delete an Inference EndpointPause an endpoint to stop compute costsResume a paused endpointScale an endpoint down to zero replicas