Segmentation - RunAnywhere Documentation

Segmentation outlines objects in an image and labels them. Where a vision model describes a picture in words, segmentation gives you the regions themselves: a mask per object, with a class and a confidence.

import { ImageInputs } from '@runanywhere/core'

const result = await RunAnywhere.segmentation.segment(ImageInputs.file(path), {
  includeDiagnosticImage: true,
})

Building the input

ImageInputs.file(path)
ImageInputs.bytes(data)
ImageInputs.base64(value)
ImageInputs.rawRgb(data, width, height)
ImageInputs.rawRgba(data, width, height)

Note the plural name. Every other SDK calls this ImageInput.

Options

Field	Default	Meaning
`includeDiagnosticImage`	`false`	Return a rendered overlay alongside the regions

Turn the diagnostic image on while you are building the feature: it shows you what the model actually found, which is much faster than reasoning about mask arrays. Turn it off in production, since rendering it costs time and memory you do not have on a phone.

What comes back

A SegmentationResult holds the regions found. Each carries its class label, a confidence, and the mask itself, so you can draw an outline, crop to the object, or count instances.

Segmentation or a vision model

You want	Use
A sentence about the picture	VLM
”Is there a dog in this”	VLM
The exact pixels of the dog	Segmentation
Object counts, or a crop	Segmentation
Anything you will draw on the image	Segmentation

Availability

Segmentation needs a registered segmentation model and a backend that serves it. The namespace existing does not mean the catalog has an entry.