Google Nano Banana (Image Gen)

Integrate Google’s Nano Banana (Gemini 3 Pro) image generation into your Noah projects. Generate and edit images conversationally using text prompts — all handled by Noah.

What You Can Build

• AI image generators from text descriptions
• Image editing tools (add, remove, or modify elements)
• Logo and poster creators with accurate text rendering
• Product mockup generators
• Multi-turn image refinement workflows

Key Capabilities

Feature	Details
Text-to-Image	Generate images from text descriptions
Image Editing	Upload an image + text prompt to modify it
Multi-Turn Editing	Refine images conversationally over multiple turns
Text Rendering	Accurate, legible text in generated images (logos, posters)
High Resolution	Up to 4K output quality
Reference Images	Use up to 14 reference images for consistency
Aspect Ratios	1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9

All generated images include a SynthID watermark.

Prerequisites

1. Enable Supabase

   Image generation uses Supabase Edge Functions to securely handle your API key. Make sure Supabase is enabled in your project. See the Supabase setup guide if you haven’t connected it yet.

2. Get Your Gemini API Key

   Visit Google AI Studio to create or copy your API key.

3. Add Your API Key

   Add your Gemini API key as a secret in Supabase. See Secrets Management for how to add secrets from the Cloud tab.

How to Integrate

Describe what you want in the chat. Noah sets up everything automatically.

Text-to-Image Generation

Generate images from text descriptions:

Add an AI image generator where users type a prompt and get a generated image using Gemini

Build a product mockup tool that generates images from descriptions using Google Nano Banana

Image Editing

Let users upload images and edit them with text prompts:

Create an image editor where users upload a photo and describe changes they want using AI

Build a tool where users can upload an image and ask AI to remove the background or change elements

Multi-Turn Refinement

Build iterative image editing workflows:

Add a conversational image editor where users can keep refining their image with follow-up prompts

Logo & Text-Heavy Images

Generate images with accurate text rendering:

Build a logo generator that creates logos with custom text, colors, and styles using Gemini

Create a poster maker tool that generates event posters with accurate text placement

Prompt Cookbook

Use Case	Prompt
Image Generator	Add an AI image generator that creates images from text descriptions using Gemini
Photo Editor	Build a photo editing tool where users upload images and describe edits in plain text
Logo Creator	Create a logo generator that renders custom text and icons in different styles
Product Mockups	Build a mockup generator for product images from text descriptions
Avatar Maker	Add an AI avatar generator where users describe their character and get an image
Poster Designer	Create an event poster generator with accurate text placement using Gemini
Style Transfer	Build a tool that applies art styles to uploaded photos using AI image generation
Infographic Creator	Add an infographic generator that creates visual data summaries from text input
Background Remover	Build a background removal and replacement tool using Gemini image editing
Meme Generator	Create a meme generator that adds text to AI-generated images

Tips

• Be specific in prompts — detailed descriptions with style, colors, and composition produce better results.
• Use multi-turn editing — instead of regenerating from scratch, refine iteratively for best results.
• Text rendering works best when you specify font style, placement, and size in your prompt.
• High-res output costs more — 4K images use more tokens than standard resolution.
• API billing is separate from Noah — Google charges based on token usage. Check Google AI pricing for rates.
• Noah handles the backend — you don’t need to write Edge Functions or API calls manually. Just describe what you want.