> 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/nx-ai-manager-v6.1.1/ai-models-support/introduction.md).

# Introduction

This section of our documentation describes how to create vision models that can be easily deployed to your edge devices running the Nx AI Manager. 

The main model categories with seamless integration are image classification models (for instance trained on [Google's Teachable Machine](/nx-ai-manager-v6.1.1/ai-models-support/importing-models/from-teachable-machine.md)) and object detection (for example trained using [Ultralytics](/nx-ai-manager-v6.1.1/ai-models-support/importing-models/from-ultralytics.md)). However, integrating any vision model is possible with a few tweaks.

## High-level process

Our standard process for creating and uploading your models to the Nx AI Cloud is to:

1. Create a model using your favorite training tools. You can create an ONNX model from scratch or import a model using one of the training tools we integrate with.
2. Once you have your model ready, you can upload it to the Nx AI Cloud platform; it will automatically be converted it to several different device-type (see the [AI Accelerators section](/nx-ai-manager-v6.1.1/ai-accelerators-support/introduction-to-oaxs.md)) optimized versions and ensure that it can be deployed to any edge device running the Nx AI manager efficiently.