Segment Anything Model with Matting Integrated Elegantly
Please add a Github Star if you find it useful!
Sammie-Roto 2 is an easy-to-use, cross-platform desktop application for AI assisted masking of video clips. It has 3 primary functions:
- Video Segmentation using SAM2
- Video Matting using MatAnyone, MatAnyone 2, and VideoMaMa
- Video Object Removal using MiniMax-Remover
Sammie-Roto 2 is free and open source, but runs models produced by several external projects and organizations. Some models may have restrictions on commercial usage. Please check with the relevant model provider if you have questions regarding licensing.
Full Changelog can be seen under releases
- [03/27/2026] 2.3.0 - Added VideoMaMa model, added option to combine objects when matting, fixed major segmentation bug, and more.
- [03/08/2026] 2.2.0 - Added MatAnyone2 model.
- [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.
*This video does not cover new features and changes added since version 2.0
- 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 & MatAnyone2
- Wan2GP (for optimized MatAnyone code)
- VideoMaMa
- MiniMax-Remover
- Some icons by Yusuke Kamiyamane

