Browse Code
Update 5.0
NEO Engine: Advanced diagnostic subsystem that scans VRAM, RAM, and CPU topology to generate optimal configuration recommendations in real-time.
Centralized Preferences Panel: Provides a quick-access Settings Button that opens a comprehensive panel for system management:
UI Control: Customize the Theme (Light/Dark), Interface Scaling, and Window Opacity.
Hardware Configuration: Adjust the VRAM limit, select the preferred GPU device, and configure \texttt{tiling} parameters based on NEO Engine data.
Maintenance: Tools to clear the model cache, manage error logs, and perform online update checks.
Integrated Console: A GUI terminal that intercepts sys.stdout and sys.stderr to display inference logs, errors, and warnings with syntax highlighting for instant debugging.
Native Drag & Drop: Direct support for dragging and dropping image and video files from the operating system explorer.
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 2×, 4×, or 8× 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.
Project Samples
