Welcome to PixZen 🧠💫 — a powerful, cross-platform AI toolkit that restores and enhances your 🖼️ images and 🎞️ videos with precision.
It combines a sleek Graphical User Interface (GUI) 🖥️ for ease of use and a robust Command-Line Interface (CLI) ⚙️ for automation.

🚀 Powered by intelligent hardware acceleration — NVIDIA (CUDA) 🧩, AMD/Intel (DirectML) 💪, and Apple Silicon (CoreML) 🍎 — PixZen ensures lightning-fast performance through an optimized ONNX backend.

See PixZen’s magic in action! 🪄
The AI enhances fine details and restores facial features like never before.

🧾 Original (512x512)	⚡ PixZen Enhanced (1024x1024)
🎭 Face Restoration & Detail Enhancement
🧩 General Purpose Upscaling

• ⚡ Universal GPU Acceleration: Auto-selects CUDA, DirectML, or CoreML for best performance.
• 🧑‍🎨 AI Face Restoration: Brings old portraits and low-res faces back to life with GFPGAN.
• 🧱 Just-In-Time Optimization: Models auto-convert to ONNX for blazing-fast inference.
• 🧬 Versatile Model Library: Choose from General, Anime, or Face-Specific enhancement sets.
• 🖼️ Tiled Processing: Effortlessly upscale 4K–8K images with minimal VRAM use.
• 🧰 Dual Interface: Beautiful GUI 🪟 and robust CLI 💻 — your choice, your flow.
• 📂 Batch Processing: Enhance entire folders of images and videos automatically.
• 💾 Smart Caching: Avoid redundant reprocessing and save precious compute time.

📋 Requirements:
Python 3.12 🐍, Git 🧩, npm 📦, and Anaconda/Miniconda/Miniforge Prompt 🧪.

1. ⬇️ Clone the Repository

   git clone https://github.com/rootLocalGhost/PixZen.git
   cd PixZen
   

2. 🐍 Create & Activate Conda Environment

   conda create -n PixZen python=3.12 -y
   conda activate PixZen

3. 📦 Install Dependencies

   pip install -r requirements.txt

4. 💥 GPU Acceleration (Optional, but Highly Recommended) Run ONE of the following:

   # ⚙️ NVIDIA GPUs (CUDA)
   pip install -U onnxruntime-gpu
   
   # 🧠 AMD & Intel (DirectML)
   pip install -U onnxruntime-directml

5. 🖼️ GUI Setup

   cd gui
   npm install
   cd ..

Launch the elegant GUI:

python pixzen.py --gui

Perfect for automation lovers and batch processors.

🖼️ Processing a folder of images.

🎞️ Processing a video with the --video flag.

✨ Basic Enhancement

python pixzen.py

🔍 Upscale a Single Image (4×)

python pixzen.py -i path/to/my_photo.jpg -s 4

🎬 Process Videos

python pixzen.py --video

Run python pixzen.py -h for full help 🧾.

💡 Got ideas? Contributions are always welcome! Fork 🍴 the repo, branch 🌿 out, commit 💬, and open a PR 🚀. Help shape the next evolution of AI-powered image restoration.

Licensed under the MIT License 🧾 — see LICENSE for full details.