> For the complete documentation index, see [llms.txt](https://nx.docs.scailable.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-models-support/introduction.md).

# Models Overview

This section describes how to create vision models that deploy to edge devices running the AI Manager.

The main model categories with seamless integration are image classification models (for instance trained on [Google's Teachable Machine](/ai-manager-v6.1.4/ai-models-support/importing-models/from-teachable-machine.md)) and object detection (for example trained using [Ultralytics](/ai-manager-v6.1.4/ai-models-support/importing-models/from-ultralytics.md)). However, integrating any vision model is possible with a few tweaks.

## High-Level Process

The standard process for creating and uploading models to the AI Manager Cloud is:

1. Create a model using a preferred training tool. Create an ONNX model from scratch, or import one using a supported training tool.
2. Upload the finished model to the AI Manager Cloud platform. The platform automatically converts it into several device-type (see the [AI Accelerators section](/ai-manager-v6.1.4/ai-accelerators-support/introduction-to-oaxs.md)) optimized versions and ensures it deploys efficiently to any edge device running the AI Manager.