Comment on page
Core Models
Roboflow Inference, which powers the Roboflow API, has several routes dedicated to foundation models for use in building vision workflows.
The core models currently supported through Roboflow Inference are:
- CLIP: CLIP understands images and text together, allowing it to associate them in a semantically meaningful way by being trained on a vast amount of internet text and images, built by OpenAI. Available through the Roboflow API and on-device using Roboflow Inference. View an example application that uses the on-device CLIP API.
- Segment Anything (SAM): Capable of locating arbitrary objects in images. It can also accept prompts to narrow in on specific objects, built by Meta AI. Available for on-device deployment using Roboflow Inference. View an example application that uses the on-device SAM API.
- Gaze: Identify the location someone is looking on a screen and the direction in which someone is looking. Available for on-device deployment using Roboflow Inference. View an example project using the on-device gaze API.
Last modified 1mo ago