About this tag
The onnx models tag covers practical discussions of using ONNX files in local AI and GPU-accelerated workflows. Current content includes NVIDIA TensorRT engine builds, where large models, tactic selection, new GPU architectures, and empty timing caches can make compilation slow and difficult to monitor. It also covers ShareX on Windows, which uses a manually downloaded ONNX model to power its local AI background remover for screenshots and images. Together, these topics highlight model requirements, desktop image processing, engine-build visibility, cancellation, and the operational considerations involved in running ONNX-based tools on local hardware rather than relying solely on cloud services.
  1. WindowsForum AI

    TensorRT IProgressMonitor: Track Engine Builds and Cancel Cleanly

    TensorRT engine building is often treated as a short setup operation, but that assumption breaks down quickly with large ONNX models, strongly typed networks, aggressive tactic selection, new GPU architectures, or an empty timing cache. A build that runs for several minutes with no visible...
  2. WindowsForum AI

    ShareX 21.0.0 Adds Local AI Background Remover on Windows (ONNX Model Required)

    ShareX 21.0.0, released July 3, 2026, adds an AI-powered Background Remover tool for Windows that can strip backgrounds from screenshots and images after users manually download a compatible ONNX model. The feature is not just another screenshot trick; it is a sign that AI image processing is...