• Subject Visual Segmenter

    Pixel-level accuracy for selecting objects in images. The Subject Visual Segmenter automatically selects the main subject of an image.

    Talk to an expert



  • Information

    Model ID: 6a3dc529acf3f720a629cdc8c6ad41a9

    Model Name: subject

    Model Type: visual-segmenter

    Model Type ID: embedding-classifier

    Owner: Clarifai

  • Concepts:




The Subject Visual Segmenter returns an object mask for the identified subject and non-subject in an image, as well as the percentage of pixels of the image that the concept has.

Endless possibilities with Computer Vision and AI

Gather valuable business insights from images, text and data using machine learning, natural language processing and computer vision.

  • Ready-to-use Models


The Room Type Model is an "embedding-classifier" which means that you will need to insert the model into a workflow and feed it embeddings from an embedding model for it to work. We recommend that you start with the embeddings from our general model.

Learn more about making Mesh Workflow predictions in our API Guide.

  • Ready to get started?

    Whether you are a start-up or a Fortune 500, we would love to chat about our products and make a personalised plan that fits your business.

    Learn more about Clarifai

    Find the right solution for your needs

    Schedule a demo

  • or
    Start now for free


    1,000 free operations per month.

  • Already a customer?

    If you are encountering a technical or payment issue, the customer support team will be happy to assist you.

    Contact support