nano-banana-imagegen

Nano Banana Image Generation

Generate and edit images using Google's Gemini image models via the nano-banana CLI.

Prerequisites

• GEMINI_API_KEY environment variable must be set
• The CLI is installed via npx @the-focus-ai/nano-banana

Quick Reference

# Generate a new image
npx @the-focus-ai/nano-banana "a serene mountain landscape at sunset"
 
# Edit an existing image
npx @the-focus-ai/nano-banana "add a hot air balloon to the sky" --file photo.jpg
 

Workflow

Step 1: Understand the Request

Before generating, clarify:

• Subject: What should be in the image?
• Style: Photorealistic, illustration, cartoon, abstract?
• Mood: Bright, dark, moody, cheerful?
• Composition: Close-up, wide shot, specific aspect ratio?
• Use case: Hero image, icon, social media, print?

Step 2: Craft an Effective Prompt

See prompting-guide.md for comprehensive guidance.

Key principles:

1. Be specific and descriptive
2. Include style references
3. Specify what you DON'T want
4. Describe composition and framing

Example - Weak prompt:

Example - Strong prompt:

Step 3: Generate the Image

Default output: output/generated-<timestamp>.png

Step 4: Iterate

If the result isn't right:

1. Refine the prompt - Add more detail or constraints
2. Edit the image - Use --file to modify the generated image
3. Try a different model - Some models handle certain styles better

Commands

Text-to-Image Generation

Image Editing

Edit instructions should describe the change:

• "Remove the background and replace with a gradient"
• "Add sunglasses to the person"
• "Change the sky to sunset colors"
• "Make it look like a watercolor painting"

Options

Best Practices

For Better Results

1. Start with composition: Describe the layout first, then details
2. Use artistic references: "in the style of Studio Ghibli", "like a National Geographic photo"
3. Specify lighting: "golden hour lighting", "dramatic chiaroscuro", "soft diffused light"
4. Include negative guidance: Describe what to avoid in the prompt itself
5. Consider aspect ratio: The model generates square by default; describe wide/tall if needed

For Editing

1. Be specific about changes: "Add a blue butterfly to the top-left corner"
2. Preserve what works: "Keep the background unchanged, only modify the foreground"
3. Iterative refinement: Make one change at a time for better control

For Consistency

When creating multiple related images:

1. Create a style guide in your prompt
2. Use the same style descriptors across prompts
3. Reference the first image when editing subsequent ones

Example Prompts

See the examples/ directory for full prompt examples.

Header/Hero Images

Product Photography Style

Illustrations

Icons and Logos

Troubleshooting

"No image in response"

• Prompt may have triggered safety filters
• Try rephrasing with less ambiguous terms
• Check if the model supports image generation

Poor quality results

• Add more specific style guidance
• Use a more capable model (gemini-2.5-flash-image)
• Be more explicit about what you want

Image doesn't match description

• Be more explicit about composition
• Add negative constraints ("no X, no Y")
• Try breaking complex prompts into simpler parts

Environment Setup

Ensure GEMINI_API_KEY is set:

Or create a .env file in your project: