Merge Multiple Images w/ Gemini API

This workflow is for anyone who needs to combine multiple images into a new, single image using AI. This includes people creating marketing materials, storyboards, or trying out new fashion combinations. This workflow fetches three images, converts them for AI use, and then sends them to Google's Gemini AI. Gemini merges the images based on your instructions and creates a new image. Finally, the workflow saves this new image to Google Drive. You need to replace the manual trigger with your desired trigger (like a webhook). You also need a Gemini account for AI processing and a Google Drive account for saving images. You need a Gemini account for the AI and a Google Drive account for saving files. You can change the trigger to automate the process further. You can also adjust the prompt sent to Gemini to change how the images are merged. You can also upload to any destination of your choosing after the image has been converted to a file for upload. Key Technologies: n8n,Google Gemini API,Google Drive Automation Value: This workflow automates the process of merging images using AI, saving time and effort compared to manual image editing. It uses existing images to create new content, which helps with consistent branding and content creation. You can easily adapt it for marketing, storytelling, or design tasks. Best Practices: Input images are converted to base64 strings before sending to Gemini, which is a required format for the API. The Gemini prompt clearly instructs the AI on how to compose the new image, ensuring the desired outcome. After Gemini processes the image, the output is converted back to binary for easier storage/upload to services like Google Drive. The workflow includes sticky notes to explain each section, making it easy to understand and maintain.