🎬 The Anime Scripter (TAS)

High-performance AI video enhancement toolkit for creators

📋 Overview

TheAnimeScripter (TAS) is a cutting-edge AI-powered video enhancement toolkit specialized for anime and general video content. It seamlessly integrates with Adobe After Effects while also offering standalone functionality, bringing professional-grade AI upscaling, interpolation, and restoration to creators.

Table of Contents

• Key Features
• 🖥️ User Interfaces
• 🛠️ Installation Guide
• 📚 Command Reference
• 📁 Supported Models
• 📈 Performance Benchmarks
• 👨‍ Contributors
• ⭐ Project Growth
• 🎥 Demo & Examples

🚀 Key Features

🎞️ Video Enhancement Motion Interpolation: Create buttery-smooth animation with advanced frame interpolation AI Upscaling: Enhance resolution with AI-powered upscaling (2x) Smart Deduplication: Optimize file size and interpolation by removing redundant frames	🎭 Advanced Editing Background-Foreground Segmentation: Precise automatic rotobrushing Depth Map Generation: 3D-ready depth maps for creative effects Automatic Scene Detection: Intelligent clip splitting at scene changes
🔧 Workflow Optimization After Effects Integration: Seamless plugin for AE workflow Model Chaining: Combine multiple effects in a single processing pass In-Memory Processing: Efficient frame handling without redundant disk operations	🧠 AI Flexibility Multi-Backend Support: CUDA, TensorRT, DirectML, and NCNN acceleration Custom Model Support: Import your own trained models Restoration Options: Denoise, dejpeg, sharpen, and line enhancement

🖥️ User Interfaces

Adobe After Effects Integration

Currently being enhanced with new features and optimizations

Adobe plugin provides seamless integration directly within your AE workflow, enabling AI-powered video enhancement without leaving your editing environment.

Windows Standalone

Under active development - coming soon

The native Windows application will provide a dedicated environment optimized for batch processing and advanced customization options.

🛠️ Getting Started

Adobe After Effects Plugin

System Requirements:

• After Effects 2020 (v17.5) or higher
• Compatible GPU recommended

Installation Steps:

1. Download the TAS-AdobeEdition from the releases page
2. Extract the .zip file to a location of your choice
3. Follow the installation tutorial to add TAS to After Effects

Need help? Watch the video tutorial

Standalone Application

Development Status: Currently in active development. Join the Discord for development updates.

Command Line Interface

Get the most powerful and flexible version of TAS with the command-line interface:

• ⬇️ Stable Release — Recommended for production work
• ⬇️ Nightly Builds — Latest features (may contain bugs)

📚 Available Inputs

All available parameters for interacting with the CLI or directly with main.py can be found in the Parameters guide.

📁 Available Models

🆙 Upscaling Models

Model	CUDA	TensorRT	DirectML	NCNN
ShuffleCugan	✅	✅	❌	✅
Span	✅	✅	✅	✅
SRVGGNet (Compact)	✅	✅	✅	❌
SRVGGNet (Ultra)	✅	✅	✅	❌
SRVGGNet (SuperUltra)	✅	✅	✅	❌
OpenProteus	✅	✅	✅	❌
AniScale 2	✅	✅	✅	❌
RTMOSR	❌	✅	✅	❌
Custom (Spandrel)	✅	❌	❌	❌

⏱️ Interpolation Models (RIFE)

Version	CUDA	TensorRT	DirectML	NCNN
4.6	✅	✅	❌	✅
4.15	✅	✅	❌	✅
4.15-lite	✅	✅	❌	✅
4.16-lite	✅	❌	❌	✅
4.17	✅	✅	❌	✅
4.18	✅	✅	❌	✅
4.20	✅	✅	❌	✅
4.21	✅	✅	❌	✅
4.22	✅	✅	❌	✅
4.22-lite	✅	✅	❌	✅
4.25	✅	✅	❌	❌
4.25-heavy	✅	✅	❌	❌
Rife_Elexor (mod 4.7)	✅	✅	❌	❌

🔧 Restoration Models

Model	CUDA	TensorRT	DirectML	NCNN
SCUNet (Denoise)	✅	✅	❌	❌
NAFNet (Denoise)	✅	❌	❌	❌
DPIR (Denoise)	✅	❌	❌	❌
Real-Plksr (DeJpeg)	✅	❌	❌	❌
Anime1080fixer	✅	✅	✅	❌
FastLineDarken	✅	✅	❌	❌
GaterV3	✅	❌	✅	❌

🌊 Depth Map Models

Model	CUDA	TensorRT	DirectML	NCNN
"Faster" Depth-Anything v2 Models
Small v2	✅	✅	✅	❌
Base v2	✅	✅	✅	❌
Large v2	✅	✅	✅	❌
"Faster" Distilled Models
Distill Small v2	✅	❌	❌	❌
Distill Base v2	✅	❌	❌	❌
Distill Large v2	✅	❌	❌	❌
Original Implementation Models
OG Small v2	✅	❌	❌	❌
OG Base v2	✅	❌	❌	❌
OG Large v2	✅	❌	❌	❌
OG Distill Small v2	✅	❌	❌	❌
OG Distill Base v2	✅	❌	❌	❌
OG Distill Large v2	✅	❌	❌	❌

🙏 Project Contributors

🧠 Model & Algorithm Contributors

Contributor	Contribution	Repository
SUDO	ShuffleCugan & ONNX models	VSGAN-tensorrt-docker
HZWER	RIFE interpolation framework	Practical-RIFE
the-database	SRVGGNet model variants	mpv-upscale-2x_animejanai
SkyTNT	Anime segmentation models	anime-segmentation
DepthAnything	Depth map generation	Depth-Anything-V2
Hongyuanyu	SPAN upscaling technology	span
Sirosky	Open-Proteus & AniScale 2	Upscale-Hub
Elexor	Custom RIFE modifications	Modded Rife Experiment(s)
Zarxrax	Anime1080Fixer restoration	GitHub
umzi	RTMOSR & GaterV3 Models	GitHub

---

🛠️ Framework & Tool Contributors

Contributor	Contribution	Repository
FFmpeg Group	Video processing framework	FFmpeg
YT-DLP Team	Media download capabilities	yt-dlp
Breakthrough	Scene detection algorithms	PySceneDetect
Chainner-org	Neural network architecture	spandrel
TNTWise	RIFE ONNX/NCNN optimizations	GitHub
Hyperbrew	Adobe integration framework	bolt-cep
moi15moi	Accurate inpoint and outpoint handling	VideoTimeStamps

🌟 TAS Collaborators

Contributor	Contribution
Trentonom0r3	TAS Adobe Edition
Adegerard	Project architecture & optimization suggestions

📧 Missing contributor? Please contact me at [email protected] or open a Github Issue!

🌟 Star History

🎥 Promo Video