Generative Art Studio - Mobile AI Art Generator

Mobile-first AI art generator running locally with no cloud APIs. Generate stunning artwork from text prompts using Stable Diffusion Turbo.

Features

• Text-to-Art: Generate images from text descriptions
• 10 Style Presets: Digital Art, Anime, Oil Painting, Watercolor, Cyberpunk, Fantasy, Photography, Pixel Art, 3D Render, Sketch
• Mobile Optimized: Dark theme, touch-friendly, responsive design
• Gallery: View and download your creations
• No Cloud API: Model runs 100% locally
• Fast Generation: SD Turbo generates in 1-4 steps

Quick Start

1. Clone & Setup

git clone https://github.com/YOUR_USERNAME/generative-art-web.git
cd generative-art-web
python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows
pip install -r requirements.txt

2. Run Locally

python server.py

Open http://localhost:8000 on your phone browser.

3. Deploy with Ngrok

ngrok http 8000

Use the ngrok URL on any device.

Auto Deploy with GitHub Actions

1. Push to the main branch

2. GitHub Actions automatically:

   • Sets up Python environment
   • Downloads Stable Diffusion Turbo model (~4GB)
   • Starts the FastAPI server
   • Launches ngrok tunnel
   • Outputs the public URL

3. Find your URL in the Actions run summary.

Tech Stack

Component	Technology
Frontend	HTML5, CSS3, Vanilla JavaScript
Backend	Python FastAPI
AI Model	Stable Diffusion Turbo
Model Library	HuggingFace Diffusers
Deployment	Ngrok + GitHub Actions

Configuration

Set environment variables:

MODEL_PATH=./models/sd-turbo   # Where to cache the model
MODEL_ID=stabilityai/sd-turbo  # HuggingFace model ID
PORT=8000                       # Server port

API Endpoints

Endpoint	Method	Description
/	GET	Serve frontend
/api/status	GET	Check model status
/api/styles	GET	List style presets
/api/generate	POST	Generate art from prompt
/api/generate/async	POST	Async generation

License

MIT