Segment Anything Model with Matting Integrated Elegantly
Sammie-Roto 2 is a full-featured, cross-platform desktop application for AI assisted masking of video clips. It has 3 primary functions:
- Video Segmentation using SAM2
- Video Matting using MatAnyone
- Video Object Removal using MiniMax-Remover
Please add a Github Star if you find it useful!
Full Changelog can be seen under releases
- [01/18/2026] 2.1.1 - Rebuilt the export dialog, slightly faster application startup, bug fixes.
- [12/16/2025] 2.1.0 - Added In/Out markers. Modifying points no longer deletes tracking data. Enabled half-precision for much faster segmentation. Added EfficientTAM model.
- [11/23/2025] 2.0.0 - First stable release. Includes several new features and bugfixes. New quick-start video tutorial and Discord server.
- [10/31/2025] Release of Sammie-Roto 2 Beta.
- Download latest version from releases
- Extract the zip archive to any location that doesn't restrict write permissions (so not in Program Files)
- Run 'install_dependencies.bat' and follow the prompt.
- Run 'run_sammie.bat' to launch the software.
Everything is self-contained in the Sammie-Roto folder. If you want to remove the application, simply delete this folder. You can also move the folder.
- MacOS users: Make sure Homebrew is installed.
- Ensure Python is installed (version 3.10 or higher, 3.12 recommended)
- Download latest version from releases
- Extract the zip archive.
- Open a terminal and navigate to the Sammie-Roto folder that you just extracted from the zip.
- Execute the following command:
bash install_dependencies.shthen follow the prompt. - MacOS users: double-click "run_sammie.command" to launch the program. Linux users:
bash run_sammie.commandor execute the file however you prefer.
- SAM 2
- EfficientTAM
- MatAnyone
- MiniMax-Remover
- Wan2GP (for optimized MatAnyone)
- Some icons by Yusuke Kamiyamane