To use the Nano Banana AI model, follow these step-by-step instructions that work for most users, including both simple prompt editing and developer API access.
Quick Start for Non-Developers
Open Google AI Studio at aistudio.google.com and sign in with a Google account.
Select “Nano Banana” (often listed as “Gemini 2.5 Flash Image”) from the model picker.
Upload the image you want to edit, or directly start with a text prompt for image generation.
Write a clear natural language prompt describing what you want (e.g., “blend these two photos,” or “make me look like a princess holding flowers.”).
Click “Generate” and review the result. You can re-edit or refine your prompt to improve output.
Steps for Developers (API Access)
Obtain an API key by registering your project on Google AI Studio and enabling billing.
Install the official SDK (Python: pip install google-genai, JavaScript/TypeScript: npm install @google/genai).
Authenticate your client with the API key you received.
For image generation:
from google import genai
client = genai.Client(api_key="YOUR_API_KEY")
prompt = "Create a photorealistic image of an orange cat with green eyes."
response = client.models.generate_content(
model="gemini-2.5-flash-image-preview",
contents=prompt,
)
Tips and Best Practices
Experiment with prompts for the most realistic outputs.
Nano Banana excels at blending images, character consistency, and natural scene edits.
Use Google AI Studio for prototyping before writing production code.
Image generation costs around $0.039 per 1024×1024px image via API.
Common Use Cases
Photo restoration and enhancement
Blending multiple images (e.g., for storytelling or design)
Virtual try-ons or product visualizations
Targeted transformations (“remove background,” “add bookshelf”)
By following these steps, Nano Banana can be used for both quick edits and integration into full-stack applications, delivering high-quality AI-powered image results.

