diff --git a/README.md b/README.md index c471405..75b8fad 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@ ### _AI Media Enhancement Suite_ [![Build Status](https://img.shields.io/badge/Build-Stable_Release-0A192F?style=for-the-badge&logo=github&logoColor=FFD700)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases) -[![Version](https://img.shields.io/badge/Version-4.1--08.01-FF8C00?style=for-the-badge&logo=git&logoColor=white)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases/tag/4.1) +[![Version](https://img.shields.io/badge/Version-4.2-FF8C00?style=for-the-badge&logo=git&logoColor=white)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases/tag/4.2) [![License](https://img.shields.io/badge/License-MIT-6A0DAD?style=for-the-badge&logo=open-source-initiative&logoColor=white)](LICENSE) [![Downloads](https://img.shields.io/github/downloads/Ivan-Ayub97/Warlock-Studio/total?style=for-the-badge&color=FFD700&logo=download&logoColor=black)](https://github.com/Ivan-Ayub97/Warlock-Studio/releases) @@ -19,14 +19,14 @@ _Transform your media with cutting-edge AI technology_ --- -**Warlock-Studio** is an open source desktop application for **Windows**, designed to integrate state-of-the-art AI models for **image and video enhancement**. +**Warlock-Studio** is an open-source desktop application for **Windows**, designed to integrate state-of-the-art AI models for **image and video enhancement**. Inspired by [Djdefrag](https://github.com/Djdefrag) tools such as **QualityScaler** and **FluidFrames**, Warlock-Studio provides a unified, high-performance platform for **upscaling, restoration, denoising, and frame interpolation**. -Version **4.1** introduces **enhanced GPU utilization**, **robust ONNX model loading**, and multiple **stability and compatibility improvements**, ensuring a smoother, faster, and more reliable user experience. +Version **4.2** introduces a **full offline installer**, an **advanced ONNX Runtime engine** with CUDA support, and significant **packaging optimizations**, ensuring the most reliable and performant experience yet. --- -## πŸ“₯ Download Installer (v4.1) +## πŸ“₯ Download Installer (v4.2) Get the latest stable release from: @@ -38,7 +38,7 @@ Get the latest stable release from: - + Download from GitHub @@ -54,127 +54,110 @@ Get the latest stable release from: ## ✨ Key Features -- **AI Upscaling & Restoration** – Utilize **Real-ESRGAN, BSRGAN, and IRCNN** models for denoising, super-resolution, and detail recovery. -- **Face Restoration (GFPGAN)** – Recover facial details from low-resolution or blurry images and video frames. -- **Frame Interpolation (RIFE)** – Smooth motion or generate slow-motion content with **2Γ—, 4Γ—, or 8Γ— interpolation**. -- **Modern UI** – Redesigned interface in v4.0 for **intuitive workflow and streamlined navigation**. -- **Batch Processing** – Process multiple media files simultaneously, saving time and effort. -- **Custom Workflows** – Fine-grained control over models, resolution, output formats, and quality parameters. -- **Open-Source & Extensible** – Fully MIT licensed, for contributors and developers. +- **AI Upscaling & Restoration** – Utilize **Real-ESRGAN, BSRGAN, and IRCNN** models for denoising, super-resolution, and detail recovery. +- **Face Restoration (GFPGAN)** – Recover facial details from low-resolution or blurry images and video frames. +- **Frame Interpolation (RIFE)** – Smooth motion or generate slow-motion content with **2Γ—, 4Γ—, or 8Γ— interpolation**. +- **Advanced Hardware Acceleration** – Intelligent provider selection prioritizes **CUDA**, falls back to **DirectML**, and finally **CPU** for maximum compatibility and performance. +- **Batch Processing** – Process multiple media files simultaneously, saving time and effort. +- **Custom Workflows** – Fine-grained control over models, resolution, output formats, and quality parameters. +- **Open-Source & Extensible** – Fully MIT licensed, for contributors and developers. --- -## πŸ†• What’s New in v4.1 +## πŸ†• What’s New in v4.2 -- πŸ”§ **Removed outdated SuperResolution-10 model** to streamline resources. -- βœ… **Enhanced ONNX loading** with better GPU acceleration. -- βœ… **Fixed import and type annotation issues** for cleaner code execution. -- βœ… **Improved error handling** with graceful fallback mechanisms. -- 🟒 Optimized **GPU resource management** for faster processing. -- πŸš€ Compatibility fixes for **NumPy** and **OpenCV**. -- πŸ“¦ Stability and memory usage improvements for longer sessions. -- βœ… Increased startup reliability with enhanced user notifications. - ---- - -## 🌐 Smart Model Distribution System (v4.0+) - -### 🎯 Lightweight Installation -- Installer reduced from **1.4GB β†’ 450MB** (–68%) for faster downloads. -- Core AI models (~400MB) downloaded automatically on first launch. -- Bandwidth-friendly and modular setup for selective installation. - -### πŸ›‘οΈ Reliability -- **Integrity checks** on downloaded model files. -- **Graceful degradation** in case of missing models. -- **Offline support** allows manual placement of model files. +- πŸ“¦ **Full Offline Installer**: The application is now distributed as a single, self-contained offline installer. All AI models are included, eliminating the need for an internet connection during setup and ensuring a reliable installation. +- πŸš€ **Advanced ONNX Runtime Engine**: The model loading architecture was re-engineered to intelligently prioritize hardware acceleration providers (**CUDA** > **DirectML** > **CPU**), maximizing performance on capable hardware and ensuring stability via a robust fallback mechanism. +- βš™οΈ **Aggressive Packaging Optimization**: The final application size has been drastically reduced by aggressively pruning unnecessary dependencies from the PyInstaller build, resulting in a lighter and more efficient package. +- πŸ› **Enhanced Runtime Stability**: Added crucial hidden imports to the build process, preventing `ModuleNotFoundError` crashes and ensuring all components of `onnxruntime` and other libraries load correctly. +- πŸ–₯️ **Improved Debugging Experience**: The application now runs with an attached console window, providing real-time logs and error messages for easier troubleshooting. +- ✨ **Professional Splash Screen**: A new startup splash screen provides immediate visual feedback while the application initializes, improving the user experience. --- ## πŸ–ΌοΈ Interface Previews -**Main Window** +**Main Window** ![Main interface](rsc/Capture.png) -**RIFE Options** +**RIFE Options** ![RIFE Options](rsc/CaptureRIFE.png) --- ## πŸš€ How to Use -1. Run Warlock-Studio as **Administrator** (recommended for full GPU access). -2. **Load Media** – Import images or videos. -3. **Configure Processing Settings**: - - Select AI model (Real-ESRGAN, GFPGAN, etc.) - - Set resolution, format, frame interpolation, and quality. -4. **Start Processing** using **"Make Magic"**. -5. Retrieve the processed results from the designated output folder. +1. Run Warlock-Studio as **Administrator** (recommended for full GPU access). +2. **Load Media** – Import images or videos. +3. **Configure Processing Settings**: + - Select AI model (Real-ESRGAN, GFPGAN, etc.) + - Set resolution, format, frame interpolation, and quality. +4. **Start Processing** using **"Make Magic"**. +5. Retrieve the processed results from the designated output folder. --- ## πŸ–ΌοΈ Quality Comparison -Enhanced image using **BSRGANx2**: +Enhanced image using **BSRGANx2**: ![Comparison](rsc/image_comparison.png) --- ## πŸ“Š Model Comparison -| Model File | Use Case | Speed | Quality | Notes | -|--------------------------|----------------------------------------|---------|---------|-------| -| **GFPGANv1.4** | Face restoration | High | High | Optimal for portraits | -| **BSRGANx2** | 2Γ— upscale + denoising | Medium | Very High | Suitable for lightly degraded media | -| **BSRGANx4** | 4Γ— upscale + denoising | Low | Very High | For heavily degraded content | -| **RIFE** | Frame interpolation | High | High | Smooth motion, slow-motion support | -| **RIFE-Lite** | Lightweight interpolation | Very High | Medium | Faster, lower resource usage | -| **RealESRGANx4** | General 4Γ— upscaling | Medium | High | Balanced performance | -| **RealESRNetx4** | Subtle restoration | Medium | High | Preserves natural image texture | -| **RealSRx4_Anime** | Anime / line-art enhancement | Medium | High | Sharp edges for 2D art | -| **IRCNN_L** | Light denoising | High | Medium | Mild artifact removal | -| **IRCNN_M** | Medium denoising | High | Medium | Stronger artifact cleanup | +| Model File | Use Case | Speed | Quality | Notes | +| -------------------------- | ------------------------------ | --------- | --------- | ----------------------------------- | +| **GFPGANv1.4** | Face restoration | High | High | Optimal for portraits | +| **BSRGANx2** | 2Γ— upscale + denoising | Medium | Very High | Suitable for lightly degraded media | +| **BSRGANx4** | 4Γ— upscale + denoising | Low | Very High | For heavily degraded content | +| **RIFE** | Frame interpolation | High | High | Smooth motion, slow-motion support | +| **RIFE-Lite** | Lightweight interpolation | Very High | Medium | Faster, lower resource usage | +| **RealESRGANx4** | General 4Γ— upscaling | Medium | High | Balanced performance | +| **RealESRNetx4** | Subtle restoration | Medium | High | Preserves natural image texture | +| **RealSRx4_Anime** | Anime / line-art enhancement | Medium | High | Sharp edges for 2D art | +| **IRCNN_L** | Light denoising | High | Medium | Mild artifact removal | +| **IRCNN_M** | Medium denoising | High | Medium | Stronger artifact cleanup | --- ## βš™οΈ Installation -1. **Download installer** (see links above). -2. Run the **setup wizard** and follow prompts. -3. Launch via Start Menu or Desktop shortcut. +1. **Download the Full Offline Installer** (see links above). +2. Run the **setup wizard** and follow the prompts. +3. Launch via Start Menu or Desktop shortcut. -> Warlock-Studio is packaged using **PyInstaller** and deployed with **Inno Setup** for seamless installation. +> Warlock-Studio is packaged using **PyInstaller** and deployed with **Inno Setup** for a seamless, self-contained installation experience. ### Installer Previews -![Installer 1](rsc/Installation_window.png) -![Installer 2](rsc/Installation_window2.png) -![Installer 3](rsc/Installation_window3.png) +![Installer 1](rsc/Installation_window.png) +![Installer 2](rsc/Installation_window2.png) +![Installer 3](rsc/Installation_window3.png) --- ## πŸ–₯️ System Requirements -- **OS:** Windows 10 or higher (64-bit) -- **RAM:** 8GB+ recommended -- **GPU:** NVIDIA or DirectML-compatible GPU recommended -- **Storage:** Sufficient free space for input and processed media +- **OS:** Windows 10 or higher (64-bit) +- **RAM:** 8GB+ recommended +- **GPU:** NVIDIA (for CUDA), AMD, or Intel GPU with up-to-date drivers recommended +- **Storage:** Sufficient free space for input and processed media --- -## πŸ“Œ Development Status (v4.1-08.01) +## πŸ“Œ Development Status (v4.2) -| Component | Status | Notes | -|-----------------------------|------------|-------| -| Upscaling Models | 🟒 Stable | Includes VRAM recovery integration | -| Optimized Model Suite | 🟒 Enhanced | Streamlined and reliable | -| Face Restoration (GFPGAN) | 🟒 Stable | High-quality face reconstruction | -| Frame Interpolation (RIFE) | 🟒 Stable | Smooth motion and slow-motion support | -| Batch Processing | 🟒 Stable | Improved error handling and logging | -| User Interface (UI/UX) | 🟒 Refined | Clean, modern design with integrated models | -| GPU Management | 🟒 Enhanced | Robust ONNX handling and fallbacks | -| Code Quality | 🟒 Improved | Refactored, type-safe, maintainable | -| Installer & Packaging | 🟒 Stable | Smooth setup experience | +| Component | Status | Notes | +| ---------------------------- | ----------- | -------------------------------------------------------- | +| ONNX Runtime Engine | 🟒 Enhanced | Prioritizes CUDA > DirectML > CPU with automatic fallback. | +| Installer & Packaging | 🟒 Overhauled | Full offline installer; heavily optimized package size. | +| Upscaling Models | 🟒 Stable | Includes VRAM recovery integration. | +| Face Restoration (GFPGAN) | 🟒 Stable | High-quality face reconstruction. | +| Frame Interpolation (RIFE) | 🟒 Stable | Smooth motion and slow-motion support. | +| Batch Processing | 🟒 Stable | Improved error handling and logging. | +| User Interface (UI/UX) | 🟒 Refined | Clean, modern design with splash screen. | +| Code Quality | 🟒 Improved | Refactored, modular, and more maintainable. | --- @@ -244,27 +227,25 @@ Warlock-Studio/ ```
+--- + ## πŸ“Š Integrated Technologies & Licenses -| Technology | License | Author / Maintainer | Source | -|-----------------|---------------------|------------------------------------------|--------| -| 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 | Xintao Wang | [GitHub](https://github.com/xinntao/Real-ESRGAN) | -| GFPGAN | Apache 2.0 | TencentARC / Xintao Wang | [GitHub](https://github.com/TencentARC/GFPGAN) | -| RIFE | Apache 2.0 | hzwer | [GitHub](https://github.com/megvii-research/ECCV2022-RIFE) | -| BSRGAN | Apache 2.0 | Kai Zhang | [GitHub](https://github.com/cszn/BSRGAN) | -| IRCNN | BSD / Mixed | Kai Zhang | [GitHub](https://github.com/cszn/IRCNN) | -| Anime4K | MIT | bloc97 | [GitHub](https://github.com/bloc97/Anime4K) | -| ONNX Runtime | MIT | Microsoft | [GitHub](https://github.com/microsoft/onnxruntime) | -| PyTorch | BSD 3-Clause | Meta AI | [GitHub](https://github.com/pytorch/pytorch) | -| FFmpeg | LGPL / GPL | FFmpeg Team | [Official Site](https://ffmpeg.org) | -| ExifTool | Artistic License | Phil Harvey | [Official Site](https://exiftool.org/) | -| DirectML | MIT | Microsoft | [GitHub](https://github.com/microsoft/DirectML) | -| Python | PSF License | Python Software Foundation | [Official Site](https://www.python.org) | -| PyInstaller | GPLv2+ | PyInstaller Team | [GitHub](https://github.com/pyinstaller/pyinstaller) | -| Inno Setup | Custom | Jordan Russell | [Official Site](http://www.jrsoftware.org/isinfo.php) | +| Technology | License | Author / Maintainer | Source | +| --------------- | ------------------- | ---------------------------------------- | ------------------------------------------------------------ | +| QualityScaler | MIT | [Djdefrag](https://github.com/Djdefrag) | [GitHub](https://github.com/Djdefrag/QualityScaler) | +| FluidFrames | MIT | [Djdefrag](https://github.com/Djdefrag) | [GitHub](https://github.com/Djdefrag/FluidFrames) | +| Real-ESRGAN | BSD 3-Clause / Apache | Xintao Wang | [GitHub](https://github.com/xinntao/Real-ESRGAN) | +| GFPGAN | Apache 2.0 | TencentARC / Xintao Wang | [GitHub](https://github.com/TencentARC/GFPGAN) | +| RIFE | Apache 2.0 | hzwer | [GitHub](https://github.com/megvii-research/ECCV2022-RIFE) | +| BSRGAN | Apache 2.0 | Kai Zhang | [GitHub](https://github.com/cszn/BSRGAN) | +| IRCNN | BSD / Mixed | Kai Zhang | [GitHub](https://github.com/cszn/IRCNN) | +| ONNX Runtime | MIT | Microsoft | [GitHub](https://github.com/microsoft/onnxruntime) | +| FFmpeg | LGPL / GPL | FFmpeg Team | [Official Site](https://ffmpeg.org) | +| ExifTool | Artistic License | Phil Harvey | [Official Site](https://exiftool.org/) | +| Python | PSF License | Python Software Foundation | [Official Site](https://www.python.org) | +| PyInstaller | GPLv2+ | PyInstaller Team | [GitHub](https://github.com/pyinstaller/pyinstaller) | +| Inno Setup | Custom | Jordan Russell | [Official Site](http://www.jrsoftware.org/isinfo.php) | --- @@ -272,26 +253,17 @@ Warlock-Studio/ We welcome contributions from the community: -1. **Fork** the repository. -2. **Create a branch** for your feature or bug fix. -3. **Submit a Pull Request** with detailed description and testing notes. +1. **Fork** the repository. +2. **Create a branch** for your feature or bug fix. +3. **Submit a Pull Request** with a detailed description and testing notes. -πŸ“§ Contact: **[negroayub97@gmail.com](mailto:negroayub97@gmail.com)** +πŸ“§ Contact: **[negroayub97@gmail.com](mailto:negroayub97@gmail.com)** --- ## πŸ“œ License -Β© 2025 IvΓ‘n Eduardo Chavez Ayub -Licensed under **MIT**. Additional terms and attributions are provided in `NOTICE.md`. +Β© 2025 IvΓ‘n Eduardo Chavez Ayub +Licensed under **MIT**. Additional terms and attributions are provided in `NOTICE.md`.
- - - - - - - - -