The Roboflow Inference API Schemas has several routes dedicated to core CV models that can be served with the Roboflow inference server. These are foundational CV models that are general and can be used on a wide variety of data without the need for training or fine tuning. The core models currently supported on Roboflow Inference Servers are:
- CLIP: A machine learning model that 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.
- SAM: A machine learning model capable of locating arbitrary objects in images. It can also accept prompts to narrow in on specific objects, built by Meta AI.