Gemini Image Generation (Nano Banana)

Generate and edit images using Google's Gemini API. The environment variable GEMINI_API_KEY must be set.

Available Models

Model	Alias	Resolution	Best For
gemini-2.5-flash-image	Nano Banana	1024px	Speed, high-volume tasks
gemini-3-pro-image-preview	Nano Banana Pro	Up to 4K	Professional assets, complex instructions, text rendering

Quick Start Scripts

Text-to-Image

python scripts/generate_image.py "A cat wearing a wizard hat" output.png

Edit Existing Image

python scripts/edit_image.py input.png "Add a rainbow in the background" output.png

Multi-Turn Chat (Iterative Refinement)

python scripts/multi_turn_chat.py

Core API Pattern

All image generation uses the generateContent endpoint with responseModalities: ["TEXT", "IMAGE"]:

import os
import base64
from google import genai

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

response = client.models.generate_content(
    model="gemini-2.5-flash-image",
    contents=["Your prompt here"],
)

for part in response.parts:
    if part.text:
        print(part.text)
    elif part.inline_data:
        image = part.as_image()
        image.save("output.png")

Image Configuration Options

Control output with image_config:

from google.genai import types

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[prompt],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        image_config=types.ImageConfig(
            aspect_ratio="16:9",  # 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
            image_size="2K"       # 1K, 2K, 4K (Pro only for 4K)
        ),
    )
)

Editing Images

Pass existing images with text prompts:

from PIL import Image

img = Image.open("input.png")
response = client.models.generate_content(
    model="gemini-2.5-flash-image",
    contents=["Add a sunset to this scene", img],
)

Multi-Turn Refinement

Use chat for iterative editing:

from google.genai import types

chat = client.chats.create(
    model="gemini-2.5-flash-image",
    config=types.GenerateContentConfig(response_modalities=['TEXT', 'IMAGE'])
)

response = chat.send_message("Create a logo for 'Acme Corp'")
# Save first image...

response = chat.send_message("Make the text bolder and add a blue gradient")
# Save refined image...

Prompting Best Practices

Photorealistic Scenes

Include camera details: lens type, lighting, angle, mood.

"A photorealistic close-up portrait, 85mm lens, soft golden hour light, shallow depth of field"

Stylized Art

Specify style explicitly:

"A kawaii-style sticker of a happy red panda, bold outlines, cel-shading, white background"

Text in Images

Be explicit about font style and placement. Use gemini-3-pro-image-preview for best results:

"Create a logo with text 'Daily Grind' in clean sans-serif, black and white, coffee bean motif"

Product Mockups

Describe lighting setup and surface:

"Studio-lit product photo on polished concrete, three-point softbox setup, 45-degree angle"

Advanced Features (Pro Model Only)

Google Search Grounding

Generate images based on real-time data:

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["Visualize today's weather in Tokyo as an infographic"],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        tools=[{"google_search": {}}]
    )
)

Multiple Reference Images (Up to 14)

Combine elements from multiple sources:

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[
        "Create a group photo of these people in an office",
        Image.open("person1.png"),
        Image.open("person2.png"),
        Image.open("person3.png"),
    ],
)

REST API (curl)

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "A serene mountain landscape"}]}]
  }' | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' | base64 --decode > output.png

Troubleshooting

API Quota Exhausted (429 Error)

When you encounter a ResourceExhausted or 429 error, it means your API quota limit has been reached. Important: The Gemini web interface (gemini.google.com) and the API have separate quota systems.

Fallback Workflow

When API quota is exhausted, all scripts will automatically display your optimized prompt in a copy-friendly format:

==============================================================
ERROR: API Quota Exhausted
==============================================================

Your optimized prompt:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Character sheet design. Professional cartoon illustration...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Fallback Instructions:
1. Visit https://gemini.google.com
2. Copy the prompt above and paste it in the web interface
3. For image editing: Upload your input image
4. The web interface has a SEPARATE quota from the API

Check API usage: https://ai.dev/usage?tab=rate-limit

Why This Works

• API quota: Limited for programmatic access, resets daily
• Web interface quota: More generous, designed for human interaction
• Same account, different buckets: Exhausting one doesn't affect the other

Script Behavior

All scripts (generate_image.py, edit_image.py, multi_turn_chat.py, compose_images.py) handle quota errors gracefully:

• Exit with status code 429 (instead of generic 1)
• Display your full prompt/instruction
• List any input images involved
• Provide step-by-step fallback instructions

Prevention

Monitor your API usage at https://ai.dev/usage?tab=rate-limit to track:

• Requests per day/minute limits
• Token consumption
• When quotas will reset

Notes

• All generated images include SynthID watermarks
• Image-only mode (responseModalities: ["IMAGE"]) won't work with Google Search grounding
• For editing, describe changes conversationally—the model understands semantic masking