DEPLOYMENT_GUIDE.md

🚀 Hugging Face Deployment Guide

Quick Deploy to Hugging Face Spaces

1. Create New Space

• Go to Hugging Face Spaces
• Click "Create new Space"
• Choose SDK: Gradio
• Set visibility: Public

2. Upload Files

Upload these essential files:

• app.py (main application)
• requirements.txt (dependencies)
• config.yaml (space configuration)
• README.md (documentation)
• packages.txt (system dependencies)
• Dockerfile (optional)

3. Configure Secrets

In Space settings, add:

• GEMINI_API_KEY: Your Google AI API key
• ELEVENLABS_API_KEY: Your ElevenLabs API key (optional)

4. Space Configuration (config.yaml)

title: "🍌 Nano Banana: Dynamic Image Creation"
emoji: 🍌
colorFrom: yellow
colorTo: orange
sdk: gradio
sdk_version: "4.44.0"
app_file: app.py

5. API Keys Setup

Gemini API Key (Required)

1. Visit Google AI Studio
2. Create new API key
3. Add to Space secrets as GEMINI_API_KEY

ElevenLabs API Key (Optional)

1. Sign up at ElevenLabs
2. Get API key from dashboard
3. Add to Space secrets as ELEVENLABS_API_KEY

6. Deployment Process

1. Upload files to Space
2. Add API keys in Settings > Variables and secrets
3. Space will automatically build and deploy
4. Access your live demo at the Space URL

7. Edge Cases Handled

• ✅ Missing API keys (graceful degradation)
• ✅ Rate limiting (automatic retry with backoff)
• ✅ Large images (automatic resizing)
• ✅ Network timeouts (retry mechanism)
• ✅ Invalid prompts (validation)
• ✅ Optional features fallback

8. Performance Optimizations

• Image compression and resizing
• Rate limiting compliance (20 images/minute)
• Efficient memory usage
• Error recovery mechanisms

9. Competition Compliance

• Gemini 2.5 Flash Image as primary model
• Optional enhancements (YOLO, ElevenLabs)
• Public accessibility without login
• Video demo ready interface