Repository navigation
directml
- Website
- Wikipedia
An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.
This repository contains a pure C++ ONNX implementation of multiple offline AI models, such as StableDiffusion (1.5 and XL), ControlNet, Midas, HED and OpenPose.
Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)
A simple Windows / Xbox app for generating AI images with Stable Diffusion.
GUI for upscaling ONNX models with NVIDIA TensorRT and Vapoursynth
GPU-accelerated javascript runtime for StableDiffusion. Uses modified ONNX runtime to support CUDA and DirectML.
EmbeddedLLM: API server for Embedded Device Deployment. Currently support CUDA/OpenVINO/IpexLLM/DirectML/CPU
a lightweight C++ cross-platform vision inference library,support YOLOv10 YOLOv11 PaddleOCR EasyOCR ,using ONNXRuntime/TVM with multiple exectuion providers.QQ群:364057904
Little console app to run an ONNX model through ONNX Runtime via the DirectML execution provider.
This tutorial covers creating an object detection plugin for a Unity game engine project using ONNX Runtime and DirectML.
export any your YOLOv7 model to TensorFlow, TensorFlowJs, ONNX, OpenVINO, RKNN,...
Desktop2Stereo: 2D desktop to 3D for VR/AR (Support AMD/NVIDIA/Intel/Qualcomm GPUs and Apple Silicon Chips, powered by Depth AI Models)
An Image Classification Project model built using PyTorch and DirectML backend. Secondary purpose is to draw attention to AMD+DirectML and perform benchmarks on AMD GPUs.
RL Forex Bot with PPO AI-powered trading bot using PPO, dynamic position sizing, AMD GPU acceleration (DirectML/OpenCL), and MetaTrader 5 integration. Features auto data from Dukascopy, Optuna tuning, W&B tracking. Research-grade, live-ready.
NN tool for Windows for neural network training using DirectML and raw C++