-
Smooth Motion Interpolation: Elevate video quality with seamless frame interpolation for fluid motion.
-
Crystal-Clear Upscaling: Immerse audiences in enhanced resolution, delivering sharper, more detailed visuals.
-
Optimal Video Size Deduplication: Streamline videos by intelligently removing redundant frames, optimizing file size.
-
Effortless Background-Foreground Segmentation: Simplify rotobrushing tasks with precision and ease.
-
3D Wizardry - Depth Map Generation: Unlock advanced editing possibilities with detailed depth maps for immersive 3D effects.
-
Auto Clip Cutting with Scene Change Filter: Boost productivity by automatically cutting clips with a Scene Change Filter.
-
Seamless After Effects Integration: Enhance After Effects projects effortlessly with our seamless integration.
-
Multi-Effect Magic - Model Chaining: Combine features seamlessly within After Effects, running Deduplication, Upscaling, and Interpolation in one go.
-
Efficient In-Memory Processing: Experience swift transformations without additional frame extraction cycles.
-
Custom Model Support for Creativity: Unleash your creativity by incorporating your own trained models effortlessly.
-
Graphical User Interface: Navigate through our user-friendly interface designed for both beginners and professionals, ensuring a smooth editing workflow from start to finish.
Empower your video editing journey with these robust, efficient features designed to elevate your content to new heights.
Windows:
- Download one of the latest releases from here
Linux:
- GUI / CLI is N/A yet. Refer to manual usage and the Parameters guide
For Windows:
- Git clone the repository or use the source code from one of the releases.
- Download and install Python 3.11 from here (add to System Path).
- Open a terminal inside the folder.
- Run
pip install -r requirements-dev.txt - Run:
python build.py
For Linux:
- N/A
- Open
File -> Scripts -> Install ScriptUI Panel. - Choose
TheAnimeScripter.jsxfile from the folder. - Restart After Effects when prompted.
- After reopening, go to
Window -> TheAnimeScripter.jsx. - Dock the panel wherever you prefer.
In the settings panel:
- Set the folder to the same directory as The Anime Scripter.
- Specify the output location.
All of the available parameters for interacting with the CLI or directly with main.py can be found in the Parameters guide.
Officially Supported:
- Cugan ( CUDA, DirectML and NCNN versions )
- ShuffleCugan ( CUDA, TensorRT, and NCNN )
- Span ( CUDA, TensorRT, DirectML and NCNN versions)
- RealESRGan ( CUDA and NCNN versions)
- OmniSR ( CUDA only )
- SRVGGNet (Available in Compact, UltraCompact, SuperUltraCompact, and their respective TensorRT and DirectML versions)
Unofficially Supported:
- Custom models compatible with Spandrel can be used via the
--custom_modelparameter.
- Rife CUDA (Versions: 4.6, 4.15, 4.15-lite, 4.16-lite )
- Rife TensorRT (Versions: 4.15 )
- Rife NCNN ( Versions: 4.6, 4.15, 4.15-lite, 4.16-lite )
- GMFSS ( Available for CUDA )
- SCUNet
- NAFNet
- DPIR
- SPAN (1x pretrain model)
Both internal and user generated benchmarks can be found here.
| Name and Link | For |
|---|---|
| SUDO | Shufflecugan and many more ONNX models |
| HZWER | Rife |
| AILAB | Cugan |
| JingyunLiang | SwinIR |
| Xintao | Realesrgan, Compact architectures |
| the-database | Compact, UltraCompact, SuperUltraCompact models |
| SkyTNT | Anime Segmentation |
| LiheYoung | Depth Anything |
| 98mxr | GMFSS Fortuna Union |
| FFmpeg Group | FFmpeg |
| YT-DLP | YT-DLP |
| Hongyuanyu | SPAN |
| Phhofm | Cugan, OmniSR Models |
| Francis0625 | OmniSR |
| Breakthrough | Automated Scene Detection |
| Chainner-org | Spandrel, easy to use arch implementations |
| Kim2091 | Span 1x Model |
| Kiteretsu77 | APISR |
| cszn | DPIR |
| Sirosky | RealESRGAN Model |
| TNTWise | For Rife ONNX and NCNN models |
| WolframRhodium | For Rife V2 models |
