# 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](/ai-models-support/importing-models/from-teachable-machine.md)) and object detection (for example trained using [Ultralytics](/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](/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. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://nx.docs.scailable.net/ai-models-support/introduction.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.