DEV Community

Manthan Ankolekar
Manthan Ankolekar

Posted on

Building an AI-Powered Image Generator with Google's Gemini API

#node #webdev #javascript #programming

Introduction

AI-powered image generation has taken creative applications to new heights, allowing users to generate stunning visuals from simple text prompts. In this blog, we will explore how I built a Gemini Image Generator, a Node.js application that leverages Google’s Generative AI (Gemini API) to create images based on user input.

Project Overview

The Gemini Image Generator is a lightweight REST API that allows users to send text prompts and receive AI-generated images. It is built using Node.js, Express, and Google’s Generative AI SDK.

Key Features:

✅ Accepts user text prompts to generate images.

✅ Uses Google Gemini API for AI-based image generation.

✅ Saves generated images on the server.

✅ REST API endpoints for easy integration with other applications.

Tech Stack

The project is built with:

  • Node.js - Backend runtime.
  • Express.js - Lightweight web framework.
  • Google Generative AI SDK - AI-powered image generation.
  • dotenv - Environment variable management.
  • cors - Cross-origin support.

Getting Started

1. Clone the Repository 

git clone https://github.com/manthanank/gemini-image-generator.git cd gemini-image-generator
Enter fullscreen mode Exit fullscreen mode

2. Install Dependencies 

npm install
Enter fullscreen mode Exit fullscreen mode

3. Configure Environment Variables

Create a .env file in the root directory and add:

GEMINI_API_KEY=your_google_gemini_api_key PORT=5000
Enter fullscreen mode Exit fullscreen mode

4. Start the Server 

npm start
Enter fullscreen mode Exit fullscreen mode

Your server will run at http://localhost:5000 🚀

API Endpoints

Generate an Image

📌 Endpoint: POST /api/image/generate

📌 Request Body:

{ "prompt": "a futuristic cityscape with neon lights" }
Enter fullscreen mode Exit fullscreen mode

📌 Response:

{ "message": "Image generated successfully", "imagePath": "temp/generated_image.png" }
Enter fullscreen mode Exit fullscreen mode

Project Structure 

gemini-image-generator/ ├── controllers/ # Business logic ├── routes/ # API routes ├── services/ # Google Gemini AI logic ├── temp/ # Generated images ├── server.js # Entry point ├── package.json # Dependencies └── .env # Environment variables
Enter fullscreen mode Exit fullscreen mode

Core Implementation

1. Setting Up the Express Server

The server.js file initializes the app and listens for requests:

const app = require("./app"); const { port } = require("./config/env"); app.listen(port, () => { console.log(`Server running on http://localhost:${port}`); });
Enter fullscreen mode Exit fullscreen mode

2. Handling Image Generation Requests

The imageController.js file manages requests:

const { generateImage } = require("../services/geminiService"); async function generateImageController(req, res) { const { prompt } = req.body; if (!prompt) { return res.status(400).json({ error: "Prompt is required" }); } try { const imagePath = await generateImage(prompt); res.status(200).json({ message: "Image generated successfully", imagePath }); } catch (error) { res.status(500).json({ error: error.message }); } } module.exports = { generateImageController };
Enter fullscreen mode Exit fullscreen mode

3. Integrating the Gemini API

The geminiService.js file calls Google's AI API:

const { GoogleGenerativeAI } = require("@google/generative-ai"); const fs = require("fs"); const path = require("path"); const { geminiApiKey } = require("../config/env"); const genAI = new GoogleGenerativeAI(geminiApiKey); async function generateImage(prompt) { const model = genAI.getGenerativeModel({ model: "gemini-2.0-flash-exp-image-generation", generationConfig: { responseModalities: ['Text', 'Image'] } }); try { const response = await model.generateContent(prompt); for (const part of response.response.candidates[0].content.parts) { if (part.inlineData) { const imageData = part.inlineData.data; const buffer = Buffer.from(imageData, 'base64'); const filePath = path.join(__dirname, '../temp/generated_image.png'); fs.writeFileSync(filePath, buffer); return filePath; } } } catch (error) { console.error("Error generating image:", error); throw new Error("Failed to generate image"); } } module.exports = { generateImage };
Enter fullscreen mode Exit fullscreen mode

Conclusion

By integrating Google’s Gemini API with Node.js, we’ve built an AI-powered image generation API that can transform text into creative visuals. This project can be expanded to support image style selection, real-time previews, and cloud storage integration.

If you found this useful, ⭐ star the repo and feel free to contribute! 🚀

👉 GitHub Repository

Top comments (0)