Command-line Tools
This page describes the standalone StarNet and DeepSNR command-line packages. Use these files for command-line workflows, automation, integration with other image processing software, and standalone processing outside PixInsight.
Command-line tool releases
Command-line archives are for standalone processing, automation, and applications that call StarNet or DeepSNR executables directly. For example, Siril's StarNet integration uses the command-line StarNet installation path.
Release matrix
Current command-line packages are published for Linux x64, Windows x64, macOS x64, and macOS ARM64. StarNet2 and DeepSNR follow the same target lanes as the PixInsight modules, but command-line releases can move on their own schedule and are packaged as separate files for terminal use, scripts, and host applications that call external executables.
Current ORT/CoreML command-line packages are self-contained. Users do not install a separate TensorFlow, Torch, or backend-runtime package.
Current StarNet2 command-line release matrix
| Operating system | Architecture | Version | Backend | Release date |
|---|---|---|---|---|
| Linux | x64 | 2.5.2 | ONNX/ORT | 2026-06-06 |
| Windows | x64 | 2.5.2 | ONNX/ORT | 2026-06-06 |
| macOS | x64 | 2.5.2 | ONNX/ORT | 2026-06-06 |
| macOS | ARM64 | 2.5.2 | CoreML | 2026-06-06 |
Current DeepSNR command-line release matrix
| Operating system | Architecture | Version | Backend | Release date |
|---|---|---|---|---|
| Linux | x64 | 1.2.1 | ONNX/ORT | 2026-05-30 |
| Windows | x64 | 1.2.1 | ONNX/ORT | 2026-05-30 |
| macOS | x64 | 1.2.0 | ONNX/ORT | 2026-05-27 |
| macOS | ARM64 | 1.2.0 | CoreML | 2026-05-27 |
System and build information
Current command-line packages are self-contained. The table below separates what users need to run the package from the systems used to build and validate the release.
Current command-line system information
| Target | Runtime requirement | Built and validated on |
|---|---|---|
| Linux x64 | x86_64 Linux on a compatible glibc-based Linux distribution. | Ubuntu 24.04.2 LTS / WSL2. |
| Windows x64 | 64-bit Windows 10 or 11. | Windows 11 x64. |
| macOS x64 | macOS 13.1 or newer. Intel Mac, or Apple Silicon through Rosetta 2. | macOS 26.5 Tahoe on Apple Silicon. |
| macOS ARM64 | Apple Silicon Mac with macOS 13.1 or newer. | macOS 26.5 Tahoe on Apple Silicon. |
Updates in the latest releases
Recent command-line releases focus on current runtime backends, explicitly documented input/output behavior, and focused StarNet2 and DeepSNR updates:
- StarNet2 2.5.2 improves highlight protection in very bright image regions and fixes unscreen star-layer artifacts in saturated or near-saturated regions.
- DeepSNR 1.2.1 adds clearer backend/provider console reporting and an automatic CUDA-provider attempt with CPU fallback for ORT packages when advanced users supply compatible GPU runtime files.
- TIFF/TIF and PNG are the recommended tested input formats; JPEG/JPG and BMP might work through OpenCV but were not tested for this refresh.
- Supported inputs are 8-bit or 16-bit integer grayscale/RGB images. Unsupported inputs, including 32-bit floating-point images, alpha channels, and unsupported channel/depth layouts, are rejected.
- TIFF and PNG outputs are written as 16-bit images by default; use
--eightonly when an 8-bit output file is intentionally needed. TIFF outputs are saved with LZW compression. - StarNet2 includes
--unscreenfor an optional star-layer output alongside the existing starless output and optional subtractive mask. - macOS ARM64 command-line packages use native CoreML and are the recommended Apple Silicon lane for best performance.
Command-line download pages
- StarNet CLI tools Current StarNet command-line archives and previous recovery files
- DeepSNR CLI tools Current DeepSNR command-line archives
- Legacy Legacy releases