StarNet Software

AI-powered software for star removal and noise reduction in astrophotography.

PixInsight Modules

This page describes the StarNet and DeepSNR PixInsight modules: which repository to add, what changed in the current backend/runtime setup, and where the shared installation instructions live.

DeepSNR PixInsight module repo

Add the DeepSNR repository in PixInsight to install or update the current DeepSNR module. Current DeepSNR releases use a single repository. 

________                  ____________   _________ 
___  __ \___________________  ___/__  | / /__  __ \
__  / / /  _ \  _ \__  __ \____ \__   |/ /__  /_/ /
_  /_/ //  __/  __/_  /_/ /___/ /_  /|  / _  _, _/ 
/_____/ \___/\___/_  .___//____/ /_/ |_/  /_/ |_|  
                  /_/

Repository URL

  • DeepSNR repository
    https://pixinsight.deepsnrastro.com/
  • Deprecated TensorFlow/runtime repository

    TensorFlow/runtime repository usage is deprecated for the current DeepSNR PixInsight release path. Do not add the TensorFlow/runtime repository for new installs.

Current release

DeepSNR 1.2.2 supports DirectML acceleration for Windows ONNX Runtime packages. Linux and macOS DeepSNR packages remain on their current versions.

Windows packages support DirectML acceleration, but DirectML runtime libraries are not supplied with StarNet Software downloads. They are normally already present on supported Windows 10 and Windows 11 installations; missing DirectML components should be the exception. If DirectML components are missing, see Microsoft's DirectML version history and official DirectML package.

Installation steps

Use the shared Installation guide for the illustrated PixInsight repository setup flow.