A powerful Python tool combining Gemini 1.5 Flash (for AI-powered prompt enhancement) and Gemini 2.0 Flash (for fast, high-quality image generation). Enter a prompt, let AI enhance it, and generate stunning images instantly — outputted directly as Base64 and saved locally.

• 📝 Prompt Enhancement: Gemini 1.5 Flash enriches your text prompts for rich image details
• 🖼️ AI Image Generation: Gemini 2.0 Flash creates high-quality images
• 🧵 Base64 Encoding: Automatically encodes generated images
• 🗂️ Local Storage: Saves output in the static/ folder
• ⚡ Fast & Developer-Friendly: Ideal for AI creators, developers, and hobbyists

Prompted Output	Folder Path	Terminal Run

git clone https://github.com/ajmal-uk/image-generation-using-python-google-gemini-image-studio.git
cd image-generation-using-python-google-gemini-image-studio

pip install -r requirements.txt

Create a .env file in the root directory:

GEMINI_TEXT_API_KEY=your_text_api_key_here
GEMINI_IMAGE_API_KEY=your_image_api_key_here

python main.py

Enter your prompt and the AI-enhanced image will be saved in /static and encoded in Base64.

• Python 3 – Core programming language
• Google Generative AI – google-generativeai SDK for text & image generation
• dotenv – API key management
• Base64 – Encoding images for API/web use

1. Prompt Enhancement – Gemini 1.5 Flash enriches the user input text.
2. Image Generation – Enhanced prompt is passed to Gemini 2.0 Flash for creating images.
3. Base64 Encoding & Storage – Images are saved locally and encoded for flexible usage.

google-generativeai
python-dotenv

Ajmal UK – Passionate about AI, Python, and creative development.

🌐 Website • 📧 Email • 🐦 Twitter • 🐙 GitHub