Documentation & Guides
Everything you need to know to get started with Tameta Textile AI
Complete Technical Workflow
Step-by-Step Process:
User Input (Frontend)
You upload a fabric image and select garment type (dress, kurta, shirt, etc.). The system constructs a detailed prompt based on your selections.
Prompt Generation
A specialized prompt is automatically created: "Create a [garment type] using this fabric pattern. The design should be [style details]..."
Backend Processing
Your fabric image and prompt are securely sent to our Node.js/Python backend server. The server validates inputs and prepares the API request.
Google Gemini API Call
Backend forwards the fabric image and prompt to Google's Gemini multimodal AI model using their official API with your API key.
AI Image Generation
Gemini AI analyzes the fabric pattern, understands the prompt, and generates a realistic garment design with the fabric applied to the selected style.
Response & Display
The generated image is returned to backend, then sent to your browser. You can now view, download, or regenerate with different options.
Security Note: All data transfers are encrypted, and your images are processed securely. API keys are never exposed to the frontend.
Google Gemini API - Models & Pricing
Gemini 2.5 Models - Pricing (Pay-as-you-go):
💡 Free tier available with usage limits. Pricing shown for paid tier. 1 USD ≈ ₹85 INR (approx)
Gemini 2.5 Flash-Lite
💰 CheapestFast, small, and cheapest - Quick sketches & thumbnail drafts
Gemini 2.5 Flash
⭐ RecommendedBalanced speed & quality - Perfect for textile, fashion, and home décor designs
Gemini 2.5 Pro
🏆 Best QualityHigh-end multimodal model - HD or photorealistic image generation
📸 Image Generation (Output)
Per 1024×1024 image (≈1,290 tokens)
Backend API Implementation:
Get Your API Key:
- 1.Visit Google AI Studio
- 2.Sign in with your Google account
- 3.Click "Get API Key" and create a new key
- 4.Add the key to your backend environment variables as
GEMINI_API_KEY
Model Selection Guide:
| Goal | Recommended Model | Why |
|---|---|---|
| Fast idea prototyping | Gemini 2.5 Flash-Lite | Generates textile previews quickly & cheaply |
| Balanced quality + cost | Gemini 2.5 Flash | Perfect for POC or catalog generation |
| High-detail photo realism | Gemini 2.5 Pro | Final product mockups or marketing visuals |
💡 Production Recommendation: Use Gemini 2.5 Flash for production - it offers the best balance of quality and cost for textile/fashion design generation. For high-volume testing, start with Flash-Lite.
How It Works - AI Technology
- •🤖 Powered by Google Gemini API - Advanced multimodal AI model
- •📝 Prompts are crafted based on your garment type and fabric selection
- •🔄 Frontend sends your images and prompt to our secure backend server
- •☁️ Backend processes and forwards the request to Google Gemini API
- •🎨 Gemini AI model analyzes the fabric pattern and generates the design
- •⚡ Generated images are returned through backend to your browser
- •💾 Results are stored securely and can be downloaded or shared
Getting Started
- •Sign up with your Google account
- •Upload your first fabric pattern
- •Select a person image for try-on
- •Choose garment type and options
- •Generate and download your visualization
Image Requirements
- •Person images: Clear, front-facing photos work best
- •Fabric images: High-resolution patterns (min 1000x1000px)
- •Supported formats: JPG, PNG, WebP
- •Maximum file size: 10MB per image
- •Avoid blurry or low-light images
Best Practices
- •Use consistent lighting in person photos
- •Ensure fabric patterns are properly aligned
- •Test different garment types for best results
- •Save successful combinations to history
- •Use the prompt helper for better results
Advanced Features
- •Custom garment templates (Pro plan)
- •API access for bulk processing
- •High-resolution exports up to 4K
- •Batch processing multiple designs
- •Integration with design tools