Nano Banana Pro — AI Image Generation via Gemini

Generate images from text descriptions directly in your chat. Powered by Google Gemini. Create covers, illustrations, logos, and more.

February 8, 2026

Generate images directly in your messenger. Describe what you want, get an image. Powered by Google Gemini.

Features

  • 🎨 Text-to-image generation
  • ✏️ Edit existing images with instructions
  • 🖼️ Multiple resolutions (1K, 2K)
  • 🎭 Any style: photo-realistic, artistic, 3D, anime
  • 📐 Multi-image compositions

Install

clawhub install nano-banana-pro

🔑 Requires: GEMINI_API_KEY

Usage Examples

Simple generation:

"Generate an image: sunset over the ocean in vaporwave style"
"Draw a programmer cat working at a laptop"

Content creation:

"Create a cover image for a blog post about CSS Grid"
"Make an app icon for a weather tracking app"

Image editing:

"Remove the background from this photo"
[attach image] "Add neon glow effects"

Style prompts:

"In the style of Pixar animation"
"Cyberpunk aesthetic, neon city at night"
"Minimalist flat design on white background"

Setup

1. Get a Google AI API Key

  1. Go to Google AI Studio
  2. Sign in with your Google account
  3. Click Get API Key
  4. Create a new key

2. Add It to OpenClaw

nano ~/.openclaw/openclaw.yaml
env:
  GEMINI_API_KEY: "your-api-key-here"

Pricing

Google Gemini includes a free tier. For most personal use cases, the free limits are more than sufficient:

  • Free tier: 60 image generations per minute
  • Standard pricing applies beyond the free tier

Tips for Better Results

  • Be specific — the more detail in your description, the better the output
  • Specify style explicitly — “in the style of X” goes a long way
  • For logos: add “on transparent background”
  • For photos: add “photorealistic, DSLR quality, 4K”
  • English prompts tend to produce better results than other languages
  • Negative prompts work too: “no text, no watermarks, no people”
Back to OpenClaw Hub