Generating Consistent Imagery with Gemini Nano Banana

1. Overview

In this lab, you will learn to build a prompt-based generation pipeline for your image library.

You will complete the following steps:

• 1️⃣ Start with an archive image
• 2️⃣ Extract a character to create a brand-new reference image
• 3️⃣ Generate a series of consistent illustrations using only prompts and the new assets

Here is a summary of what you'll achieve:

What you'll learn

• How to generate new consistent images from images and prompts
• How to create a character sheet
• How to use descriptive or imperative prompts
• How to benefit from Gemini's spatial understanding
• How to build an asset graph

What you'll need

• Familiarity running Python in a notebook (in Colab or any other Jupyter environment)
• A Google Cloud project or a Gemini API key with billing enabled

ℹ️ The total cost to run this lab on Google Cloud is less than 0.40 USD.

Let's get started...

2. Before you begin

To use the Gemini API, you have two main options:

1. Via Agent Platform (formerly Vertex AI) with a Google Cloud project
2. Via Google AI Studio with a Gemini API key

🛠️ Option 1 - Gemini API via Agent Platform

Requirements:

• A Google Cloud project
• The Agent Platform API must be enabled for this project

Enable the Agent Platform API

🛠️ Option 2 - Gemini API via Google AI Studio

Requirement:

• A Gemini API key

Learn more about getting a Gemini API key from Google AI Studio.

3. Run the notebook

Choose your preferred tool to open the notebook:

🧰 Tool A - Open the notebook in Colab

Open in Colab

💡 This is the most straightforward tool to run the notebook directly from your browser (zero configuration required), easily save and manage it in your Google Drive.

🧰 Tool B - Open the notebook in Colab Enterprise or Workbench

Open in Colab Enterprise Open in Workbench

💡 This might be preferred if you already have a Google Cloud project configured with a Colab Enterprise or Workbench instance.

🧰 Tool C - Get the notebook from GitHub and run it in your own environment

Get the notebook

⚠️ You will need to get the notebook from GitHub (or clone the repository) and run it in your own Jupyter environment.

🗺️ Notebook table of contents

For easier navigation, make sure to expand and use the table of contents. Example:

🏁 Run the notebook

You are ready. You can now follow and run the notebook. Have fun!...

4. Congratulations!

Congratulations on completing the codelab!

Learn more

• Complete the Detecting and Editing Visual Objects with Gemini and Nano Banana codelab.
• Check out the Nano Banana recipes notebook for more practical examples.
• Explore additional use cases in the Agent Platform Prompt Gallery.
• Stay updated by following the Agent Platform Release Notes.