# Introduction to Gemini's Image Generation Request Parameters | CodeSignal Learn

# Introduction to Gemini's Image Generation Request Parameters | CodeSignal Learn

Introduction to Gemini's Image Generation Request Parameters

Welcome to the second lesson of our course, "Creating Images with Gemini's Image Generation and Symfony." In this course, you will explore the fascinating world of AI-driven image generation using Google's Gemini API and its native image generation model. This lesson builds upon our previous lesson where we built the GeminiImageGenerator wrapper class. Now, we'll focus on using this wrapper to generate images with various configurations and parameters. We'll also explore Symfony, a powerful PHP web framework that will help us integrate and display our generated images.

Setting Up the Environment

Before we dive into generating images, it's crucial to set up our environment correctly. First, ensure you have PHP installed on your system (PHP 8.1 or higher is required for this setup). You'll need Composer, PHP's dependency manager, to install the required packages. On CodeSignal, many libraries come pre-installed; however, it's good practice to know how to install them on your own device. For this lesson, we'll use Symfony's HTTP Client component to make API requests and handle environment variables. You can install these dependencies using Composer : Shell composer require symfony/http-client symfony/dotenv If you're setting up a complete Symfony project, you can use: Shell composer create-project symfony/skeleton my-image-generator cd my-image-generator composer require symfony/http-client symfony/dotenv Next, you should create a .env file in your project root to store your Gemini API key and base URL. The code in this course reads both values, so a local project must define each one: GEMINI_API_KEY=your_api_key_here GEMINI_BASE_URL=https://generativelanguage.googleapis.com/ Make sure to add .env to your .gitignore file to prevent accidentally committing your API key to version control.

Using the GeminiImageGenerator Wrapper

With the environment set up, the next step is to use the GeminiImageGenerator wrapper we built in the first lesson. Let's load our environment variables and instantiate the wrapper: PHP<?php // Load Symfony's autoloader require_once __DIR__ . '/vendor/autoload.php'; require_once __DIR__ . '/GeminiImageGenerator.php'; // Use Symfony's environment variables component to load .env use Symfony\Component\Dotenv\Dotenv; // Load environment variables from .env file if it exists if (file_exists(__DIR__ . '/.env')) { (new Dotenv())->load(__DIR__ . '/.env'); } // Create our image generator $imageGenerator = new GeminiImageGenerator();

Sign up

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

Now, let's generate a simple image using the Gemini image model. We'll start by defining a prompt, which is a textual description of the image you want to create. In this example, the prompt is "A serene sunset over a mountain range."

PHP

<?php
// Define the prompt for image generation
$prompt = "A serene sunset over a mountain range";

try {
    $imageDataList = $imageGenerator->generateImages($prompt, [
        'sampleCount' => 1,
        'aspectRatio' => GeminiImageGenerator::RATIO_16_9,
    ]);
} catch (\Exception $e) {
    echo "Error: " . $e->getMessage() . "\n";
    exit;
}

The sampleCount parameter in our wrapper defaults to 1. Because Gemini's image model returns a single image per request, our wrapper sends one request per sample, so a sampleCount of 2 will make two calls and return two images. The aspectRatio parameter offers several options, such as 1:1 (square), 4:3 (fullscreen), 3:4 (portrait fullscreen), 16:9 (widescreen), and 9:16 (portrait). Each aspect ratio serves different purposes, from social media posts to cinematic landscapes.

Once the image is generated, the next step is to process and save it. Our GeminiImageGenerator wrapper returns an array of binary image data that we can save directly to files:

PHP

<?php
// Check if we have a valid response with image data
if (count($imageDataList) > 0) {
    $output_path = './public/images/generated_image.png';
    $dir = dirname($output_path);
    if (!is_dir($dir)) {
        mkdir($dir, 0755, true);
    }

    if (file_put_contents($output_path, $imageDataList[0]) === false) {
        echo "Failed to write image to file: $output_path\n";
        exit;
    }

    echo "Image successfully saved to $output_path\n";
} else {
    echo "Error: No image data in the response\n";
}

This code snippet creates the necessary directories if they don't exist and saves the image to the specified path. This approach is straightforward and doesn't require additional image processing libraries for simple save operations.