![Warlock-Studio banner](Assets/banner.png)
### _AI Media Enhancement Suite_ [![Build Status](https://img.shields.io/badge/build-Stable_Release-blue?style=for-the-badge)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases) [![Version](https://img.shields.io/badge/Version-4.1--08.01-darkred?style=for-the-badge)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases/tag/4.1) [![License](https://img.shields.io/badge/License-MIT-purple?style=for-the-badge)](LICENSE) [![Downloads](https://img.shields.io/github/downloads/Ivan-Ayub97/Warlock-Studio/total?style=for-the-badge&color=gold)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases) _Transform your media with cutting-edge AI technology_ --- **Warlock-Studio** is a powerful, open-source desktop application for Windows that integrates state-of-the-art AI models for video and image enhancement. Inspired by the work of [Djdefrag](https://github.com/Djdefrag) on tools like **QualityScaler** and **FluidFrames**, this suite provides a unified, high-performance interface for upscaling, restoration, and frame interpolation. Version 4.1 builds on previous improvements with enhanced GPU utilization, comprehensive compatibility fixes, and optimization of model loading processes to provide a robust, reliable, and high-performance AI media enhancement experience. --- ### β–Ί Download Installer (v4.1) Get the latest stable release from any of the following platforms:
Download Warlock-Studio Download from GitHub Download from itch.io
--- ## Key Features - **State-of-the-Art AI Models** A comprehensive suite including Real-ESRGAN, BSRGAN, IRCNN, **GFPGAN**, and **RIFE** for denoising, resolution enhancement, detail restoration, upscaling, and smooth frame interpolation. - **AI Face Restoration** Restore and enhance faces in old, blurry, or low-quality photos and videos with the integrated GFPGAN model, bringing cherished memories back to life. - **High-Quality Upscaling Models** Real-ESRGAN and BSRGAN models provide excellent upscaling capabilities for various image types, from anime to photorealistic content. - **AI Frame Interpolation & Slow Motion** Generate new in-between frames using RIFE to create ultra-smooth **2x, 4x, or 8x** motion or dramatic slow-motion effects. - **Modern & Intuitive Interface** Completely redesigned and refined in v4.0 for a clean, efficient, and user-friendly experience for both beginners and professionals. - **Batch Processing** Simultaneously process multiple images or videosβ€”ideal for large-scale media projects. - **Customizable Workflows** Choose your preferred AI model, output resolution, format (PNG, JPEG, MP4, etc.), and quality settings for full creative control. - **Open-Source & Extensible** Licensed under the MIT License. Contributions are welcome! Additional usage terms can be found in the `NOTICE.md` file. --- ## What's New in Version 4.1 - πŸ”§ **Model Optimization:** Removed SuperResolution-10 model to improve overall performance and reduce complexity. For extreme upscaling needs, we recommend using Real-ESRGAN or BSRGAN models which provide excellent results. - βœ… **Enhanced AI Architecture:** Implemented robust ONNX model loading, GPU acceleration support, and comprehensive error handling. - βœ… **Code Quality Improvements:** Fixed critical import errors, consolidated duplicate code sections, and improved type annotations for better maintainability. - βœ… **Improved Error Handling:** Added graceful degradation mechanisms that prevent crashes and provide meaningful error messages during processing. - βœ… **Streamlined Model Integration:** Optimized model integration in the UI and processing pipeline for better performance. - 🟒 **Enhanced GPU Utilization**: Improved provider selection logic for better model execution efficiency across different hardware configurations. - πŸš€ **Compatibility Fixes**: Addressed critical module compatibility by ensuring consistent runtime environment for NumPy and OpenCV libraries. - πŸ“¦ **Performance and Stability**: Refined memory and resource management, with enhanced error messaging and fallback strategies to ensure robust application performance under varying conditions. - βœ… **User Experience Enhancements**: Improved startup reliability and user notifications for smooth interaction and feedback. --- ## 🌐 Smart Model Distribution System Version 4.0 introduces a revolutionary approach to AI model distribution: ### 🎯 **Lightweight Installation** - **Installer Size:** Reduced from 1.4GB to ~450MB (68% size reduction) - **First Launch:** AI models (~400MB) download automatically with progress tracking - **Bandwidth Friendly:** Users with limited internet can get started faster ### πŸ›‘οΈ **Reliability Features** - **Integrity Validation:** Downloaded models are verified for completeness - **Graceful Degradation:** Application provides clear feedback if models aren't available - **Offline Mode:** Users can manually place model files if needed --- ## Interface Previews ### πŸ”Ή Main View (v4.1) ![Screenshot of Warlock-Studio's main interface](rsc/Capture.png) ### πŸ”Ή RIFE Option ![Screenshot of Warlock-Studio showing RIFE options](rsc/CaptureRIFE.png) --- ## How to Use 1. **Run as Administrator** (optional but recommended for optimal performance). 2. **Load Your Media**: Select your images and videos to import them into the app. 3. **Configure Settings**: - Select an **AI Model** (e.g., Real-ESRGAN, BSRGAN, GFPGAN, RIFE). - Set the **input/output resolution**, **file format**, and toggle features like **interpolation** or **blending**. 4. **Start Processing**: Click **"Make Magic"** to begin the enhancement. 5. **Retrieve Your Files**: Processed outputs will be saved in your chosen destination folder. --- ## Quality Comparison **Comparison of an enhanced image using the BSRGANx2 model** ![Quality Comparison](rsc/image_comparison.png) --- ## Model Comparison | Model File | Recommended Use Case | Speed | Quality | Notes | |------------------------------------|------------------------------------------------------|---------|---------|-------| | **GFPGANv1.4.fp16.onnx** | Face restoration and enhancement | High | High | Specializes in restoring blurry or low-quality faces in images and videos | | **BSRGANx2_fp16.onnx** | Noise removal and detail preservation (2Γ— upscale) | Medium | Very High | Good for lightly degraded images where only moderate upscaling is needed | | **BSRGANx4_fp16.onnx** | Noise removal and detail preservation (4Γ— upscale) | Low | Very High | Best for heavily degraded images needing significant enlargement | | **RIFE_fp32.onnx** | Frame interpolation and smooth motion generation | High | High | Standard version with maximum quality for slow-motion or FPS increase | | **RIFE_Lite_fp32.onnx** | Frame interpolation with faster performance | Very High | Medium | Optimized for speed, ideal for lower-end hardware or quick previews | | **RealESRGANx4_fp16.onnx** | General-purpose high-quality image upscaling (4Γ—) | Medium | High | Works well for real-world photos and most content types | | **RealESRNetx4_fp16.onnx** | High-quality restoration without strong sharpening | Medium | High | Preserves natural look with minimal artifacts, good for subtle enhancement | | **RealSRx4_Anime_fp16.onnx** | Anime and line-art upscaling (4Γ—) | Medium | High | Designed for clean edges and solid colors, great for animations and comics | | **IRCNN_Lx1_fp16.onnx** | Light noise removal (no scaling) | High | Medium | Ideal for mild compression artifacts or grain reduction | | **IRCNN_Mx1_fp16.onnx** | Medium noise removal (no scaling) | High | Medium | Stronger denoising for moderately degraded images | | **RealESR_Animex4_fp16.onnx** | Anime-focused upscaling (4Γ—) | Medium | High | Alternative anime model with different training data from RealSR | | **RealESR_Gx4_fp16.onnx** | General-purpose upscaling with balanced sharpness | Medium | High | Balanced output, suitable for a wide variety of image types | --- ## Installation To get started with Warlock-Studio: 1. **Download the installer** from the links at the top of this document. 2. **Run the installer** and follow the setup instructions. 3. **Launch the application** from the Start Menu or desktop shortcut. Warlock-Studio uses [PyInstaller](https://www.pyinstaller.org/) and [Inno Setup](http://www.jrsoftware.org/isinfo.php) for a seamless packaging and installation experience. ### Installation Window Previews ![Screenshot of the installer window](rsc/Installation_window.png) ![Screenshot of the installer window part 2](rsc/Installation_window2.png) ![Screenshot of the installer window part 2](rsc/Installation_window3.png) --- ## System Requirements - **Operating System:** Windows 10 or later (64-bit) - **Memory (RAM):** 8 GB or more recommended - **Graphics Card:** NVIDIA or DirectML-compatible GPU highly recommended for performance - **Storage:** Sufficient disk space for input and output media files --- ## Development Status β€” v4.1-08.01 | Component | Status | Notes | | :---------------------------------- | :-------------- | :----------------------------------------------------------------------------------- | | **Upscaling Models (ESRGAN, IRCNN,,RealESRGANetc.)** | 🟒 **Stable** | Fully integrated with dynamic VRAM recovery for enhanced stability. | | **Optimized Model Suite** | 🟒 **Enhanced** | Streamlined AI models for optimal performance and reliability. | | **Face Restoration (GFPGAN)** | 🟒 **Stable** | High-quality face enhancement and restoration capabilities. | | **Frame Interpolation (RIFE)** | 🟒 **Stable** | Includes slow-motion and intermediate frame generation capabilities. | | **Batch Processing** | 🟒 **Stable** | Reliable processing with improved error handling and resource management. | | **User Interface (UI/UX)** | 🟒 **Refined** | Enhanced interface with complete model integration and improved information dialogs. | | **GPU Management** | 🟒 **Enhanced** | Improved AI architecture with robust model loading and graceful degradation. | | **Code Quality** | 🟒 **Improved** | Fixed import errors, consolidated code structure, and enhanced type annotations. | | **Installer and Packaging** | 🟒 **Stable** | Easy-to-use installer for Windows platforms. | --- ## Project Structure
``` Warlock-Studio/ β”œβ”€β”€ AI-onnx/ # Pre-trained ONNX models for AI processing β”‚ β”œβ”€β”€ BSRGANx2_fp16.onnx β”‚ β”œβ”€β”€ BSRGANx4_fp16.onnx β”‚ β”œβ”€β”€ GFPGANv1.4.fp16.onnx β”‚ β”œβ”€β”€ IRCNN_Lx1_fp16.onnx β”‚ β”œβ”€β”€ IRCNN_Mx1_fp16.onnx β”‚ β”œβ”€β”€ RealESR_Animex4_fp16.onnx β”‚ β”œβ”€β”€ RealESR_Gx4_fp16.onnx β”‚ β”œβ”€β”€ RealESRGANx4_fp16.onnx β”‚ β”œβ”€β”€ RealESRNetx4_fp16.onnx β”‚ β”œβ”€β”€ RealSRx4_Anime_fp16.onnx β”‚ β”œβ”€β”€ RIFE_fp32.onnx β”‚ └── RIFE_Lite_fp32.onnx β”‚ β”œβ”€β”€ Assets/ # App assets and third-party binaries β”‚ β”œβ”€β”€ banner.png β”‚ β”œβ”€β”€ clear_icon.png β”‚ β”œβ”€β”€ exiftool.exe β”‚ β”œβ”€β”€ ffmpeg.exe β”‚ β”œβ”€β”€ info_icon.png β”‚ β”œβ”€β”€ logo.ico β”‚ β”œβ”€β”€ logo.png β”‚ β”œβ”€β”€ stop_icon.png β”‚ β”œβ”€β”€ upscale_icon.png β”‚ β”œβ”€β”€ wizard-image.bmp β”‚ └── wizard-small.bmp β”‚ β”œβ”€β”€ rsc/ # UI images, workflows, and branding β”‚ β”œβ”€β”€ badge-color.png β”‚ β”œβ”€β”€ Capture.png β”‚ β”œβ”€β”€ CaptureRIFE.png β”‚ β”œβ”€β”€ google_drive-logo.png β”‚ β”œβ”€β”€ WorkflowBSRGAN.png β”‚ β”œβ”€β”€ WorkflowIRCNN.png β”‚ β”œβ”€β”€ WorkflowRealESRGAN.png β”‚ β”œβ”€β”€ WorkflowRIFE.png β”‚ └── Installation_window2.png β”‚ β”œβ”€β”€ Manual/ # LaTeX sources and generated manuals β”‚ β”œβ”€β”€ Manual_EN.tex β”‚ β”œβ”€β”€ Manual_ES.tex β”‚ β”œβ”€β”€ Manual_EN.pdf β”‚ └── Manual_ES.pdf β”‚ β”œβ”€β”€ Warlock-Studio.py # Main application script β”œβ”€β”€ Warlock-Studio.spec # PyInstaller spec file β”œβ”€β”€ Setup.iss # Inno Setup installer script β”‚ β”œβ”€β”€ README.md # Project overview (this file) β”œβ”€β”€ requirements.txt β”œβ”€β”€ CHANGELOG.md # Version history β”œβ”€β”€ LICENSE # License info (standard) β”œβ”€β”€ License.txt β”œβ”€β”€ NOTICE.md # Notices and attributions β”œβ”€β”€ CODE_OF_CONDUCT.md # Contributor behavior guidelines β”œβ”€β”€ CONTRIBUTING.md # Contribution guide └── SECURITY.md # Security reporting policies ```
--- ## Integrated Technologies & Licenses | Technology | License | Author / Maintainer | Source Code / Homepage | | :------------ | :------------------------ | :-------------------------------------------------------- | :--------------------------------------------------------- | | QualityScaler | MIT | [Djdefrag](https://github.com/Djdefrag) | [GitHub](https://github.com/Djdefrag/QualityScaler) | | RealScaler | MIT | [Djdefrag](https://github.com/Djdefrag) | [GitHub](https://github.com/Djdefrag/RealScaler) | | FluidFrames | MIT | [Djdefrag](https://github.com/Djdefrag) | [GitHub](https://github.com/Djdefrag/FluidFrames) | | Real-ESRGAN | BSD 3-Clause / Apache 2.0 | [Xintao Wang](https://github.com/xinntao) | [GitHub](https://github.com/xinntao/Real-ESRGAN) | | GFPGAN | Apache 2.0 | [TencentARC / Xintao Wang](https://github.com/TencentARC) | [GitHub](https://github.com/TencentARC/GFPGAN) | | RIFE | Apache 2.0 | [hzwer](https://github.com/hzwer) | [GitHub](https://github.com/megvii-research/ECCV2022-RIFE) | | SRGAN | CC BY-NC-SA 4.0 | [TensorLayer Community](https://github.com/tensorlayer) | [GitHub](https://github.com/tensorlayer/srgan) | | BSRGAN | Apache 2.0 | [Kai Zhang](https://github.com/cszn) | [GitHub](https://github.com/cszn/BSRGAN) | | IRCNN | BSD / Mixed | [Kai Zhang](https://github.com/cszn) | [GitHub](https://github.com/cszn/IRCNN) | | Anime4K | MIT | [Tianyang Zhang (bloc97)](https://github.com/bloc97) | [GitHub](https://github.com/bloc97/Anime4K) | | ONNX Runtime | MIT | [Microsoft](https://github.com/microsoft) | [GitHub](https://github.com/microsoft/onnxruntime) | | PyTorch | BSD 3-Clause | [Meta AI](https://pytorch.org/) | [GitHub](https://github.com/pytorch/pytorch) | | FFmpeg | LGPL / GPL (varies) | [FFmpeg Team](https://ffmpeg.org/) | [Official Site](https://ffmpeg.org) | | ExifTool | Perl Artistic License | [Phil Harvey](https://exiftool.org/) | [Official Site](https://exiftool.org/) | | DirectML | MIT | [Microsoft](https://github.com/microsoft/) | [GitHub](https://github.com/microsoft/DirectML) | | Python | PSF License | [Python Software Foundation](https://www.python.org/) | [Official Site](https://www.python.org) | | PyInstaller | GPLv2+ | [PyInstaller Team](https://github.com/pyinstaller) | [GitHub](https://github.com/pyinstaller/pyinstaller) | | Inno Setup | Custom License | [Jordan Russell](http://www.jrsoftware.org/) | [Official Site](http://www.jrsoftware.org/isinfo.php) | --- ## Contributions We warmly welcome community contributions! 1. **Fork** this repository. 2. **Create a branch** for your feature or fix. 3. **Submit a Pull Request** with a detailed explanation of your changes. For bug reports, feature suggestions, or inquiries, contact us at: **[negroayub97@gmail.com](mailto:negroayub97@gmail.com)** --- ## License Β© 2025 IvΓ‘n Eduardo Chavez Ayub Distributed under the MIT License. Additional terms are available in the `NOTICE.md` file.