Mine StableDiffusion 🎨

The most powerful multiplatform Stable Diffusion client
Generate stunning AI art locally on Android & Desktop

---

✨ What is Mine StableDiffusion?

Mine StableDiffusion is a native, offline-first AI art generation app that brings the power of Stable Diffusion models to your fingertips. Built with modern Kotlin Multiplatform technology and powered by the blazing-fast stable-diffusion.cpp engine, it delivers desktop-class performance on both Android and Desktop platforms.

🎯 Why Choose This App?

• 🚀 Native Performance - C++ backend with JNI bindings for maximum speed
• 🔒 Privacy First - 100% offline, all processing happens on your device
• 🎨 Modern UI - Beautiful Compose Multiplatform interface
• 📱 True Multiplatform - Shared codebase for Android & Desktop
• 🔧 Model Flexibility - Support for FLUX, SDXL, SD3, and many more
• ⚡ Hardware Accelerated - Vulkan 1.2+ (Android/Linux/Windows) & Metal (macOS)

---

📸 Screenshots

🤖 Android	💻 Desktop

---

🎲 Supported Models

Mine StableDiffusion supports a wide range of state-of-the-art generative models:

🔥 Popular Models

• ✅ FLUX.1-dev / FLUX.1-schnell - Next-gen image generation
• ✅ FLUX.2-dev - Latest FLUX iteration
• ✅ SDXL / SDXL-Turbo - High-quality 1024x1024 images
• ✅ SD3 / SD3.5 - Stability AI's latest architecture
• ✅ SD1.x / SD2.x - Classic Stable Diffusion models
• ✅ SD-Turbo - Lightning-fast generation

🌈 Specialized Models

• 🎨 Chroma / Chroma1-Radiance - Vibrant color generation
• 🖼️ Z-Image - Advanced image synthesis
• 🧠 Qwen Image - Alibaba's multimodal model
• 👁️ Ovis-Image - Vision-language model

Tip

For model-specific documentation, check the docs folder

---

🌟 Key Features

Text-to-Image Generation

Generate stunning images from text descriptions with various models

Input: "A serene mountain landscape at sunset, digital art"
Output: High-quality AI-generated image

Custom Model Support

• Load your own fine-tuned models
• Support for GGUF format models
• VAE and LoRA customization
• Flexible model switching

Advanced Controls

• Customizable generation parameters (steps, CFG scale, sampler)
• Multiple aspect ratios
• Seed control for reproducible results
• Batch generation support

---

📱 Platform Support

Platform	Status	Requirements
🤖 Android	✅ Supported	Android 11+ (API 30+)
🪟 Windows	✅ Supported	Windows 10+ with Vulkan 1.2
🐧 Linux	✅ Supported	Vulkan 1.2+ drivers
🍎 macOS	✅ Supported	Metal support required
📱 iOS	⏳ Planned	Coming soon

Note

iOS support is under development and will be available in future releases

---

🏗️ Architecture & Tech Stack

Core Technologies

graph TB
    A[Compose Multiplatform UI] --> B[Kotlin ViewModels]
    B --> C[Koin DI]
    C --> D[JNI Bridge]
    D --> E[C++ Native Layer]
    E --> F[stable-diffusion.cpp]
    F --> G[Vulkan/Metal Backend]

Loading

Technology Stack

• Language: Kotlin Multiplatform
• UI Framework: Compose Multiplatform
• Dependency Injection: Koin v4.1.1
• Navigation: Jetpack Navigation Compose
• Networking: Ktor 3.2.3 + Sandwich 2.1.2
• Image Loading: Coil3 v3.3.0
• Concurrency: Kotlin Coroutines
• Native Engine: stable-diffusion.cpp
• LLM Support: llama.cpp

---

🚀 Getting Started

Prerequisites

• Android: Android 11+ device with Vulkan 1.2 support
• Desktop: Windows/Linux/macOS with compatible graphics drivers
• Development: Android Studio Ladybug or later / IntelliJ IDEA

Installation

Option 1: Download Pre-built Release

1. Visit Releases
2. Download the appropriate package for your platform
3. Install and launch

Option 2: Build from Source

# Clone the repository
git clone https://github.com/Onion99/KMP-MineStableDiffusion.git
cd KMP-MineStableDiffusion

# Build for Desktop
./gradlew :composeApp:run

# Build for Android
./gradlew :composeApp:assembleDebug

First Run

1. Launch the app
2. Load your Stable Diffusion model (GGUF format)
3. Enter your text prompt
4. Click generate and watch the magic happen! ✨

---

📚 Documentation

• 📝 Changelog - Version history

---

🤝 Contributing

Contributions are welcome! Whether it's:

• 🐛 Bug reports
• 💡 Feature requests
• 📝 Documentation improvements
• 🔧 Code contributions

Please read our Contributing Guidelines before submitting PRs.

---

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

---

🙏 Acknowledgments

Special thanks to:

• leejet/stable-diffusion.cpp - Awesome C++ SD implementation
• ggerganov/llama.cpp - LLM inference framework
• JetBrains Compose Multiplatform - UI framework
• The entire Stable Diffusion community 💜

---

💙 Support This Project

If you find this project useful:

• ⭐ Star this repository
• 🐛 Report bugs and suggest features
• 🔀 Fork and contribute
• 📢 Share with others

---

📬 Contact

• Issues: GitHub Issues
• Discussions: GitHub Discussions

---