coreml

High performance, cross-platform machine learning for Unity Engine.

Here is a collection of high-quality ONNX models for Windows ML

LiveTalk is a unified, high-performance talking head generation system that combines the power of LivePortrait and MuseTalk open-source repositories. The PyTorch models from these projects have been ported to ONNX format and optimized for CoreML to enable efficient on-device inference in Unity.

A Xamarin.Forms app for UWP, Android & iOS showcasing how to use Custom Vision Service with either online and offline models.

Hardware-agnostic machine learning infrastructure for .NET. Implements high-performance neural network layers in C# that are transpiled to run on WebGPU, CUDA, OpenCL, WebGL, CPU, and Wasm via SpawnDev.ILGPU. Optimized for Blazor WebAssembly and native GPU execution.

Sample code of converting CoreML MobileNet into Windows Machine Learning

A sample app showcasing the use of Cognitive Services within UWP & Xamarin apps: Vision, Face and Custom Vision.

Sample Xamarin.Forms app used on an episode of the AI Show

A comprehensive .NET MAUI plugin for ML inference with ONNX Runtime, CoreML, and platform-native acceleration support

Xamarin.iOS CoreML Demo app

Unity package for on-device Qwen3-TTS (12Hz) inference: VoiceDesign and Base ICL voice cloning via ONNX Runtime.

Demo using Custom ML model to do app logic

Use Customvision.AI service in Xamarin Form project

Counts the points of a Swiss Jass game with the phone camera: an on-device YOLO11 detector, trained only on synthetic images, recognises the top card of a pile. iOS and Android apps, the synthetic data generator, the training pipeline and the CAS thesis (HSLU).