AI Image Stitching: Compose Separate Images with Gemini in n8n

This workflow automates the composition or 'stitching' of separate images using Gemini AI's image generation model in n8n. It fetches source images from cloud storage via HTTP, converts them to base64, aggregates them, and feeds them into Gemini along with a custom prompt to generate a new image that retains the original assets' styles and details with minimal hallucinations.

Key benefits include high-fidelity results at low cost ($0.039 per generation), seamless integration with Google Drive for output storage, and versatility for creative tasks. It's ideal for sales teams generating marketing materials, consistent product visuals in quotes, or fashion mockups without manual editing tools.

Use cases span storyboarding with recurring characters, assembling product shots for quotes, virtual try-ons, or any scenario needing composite images. Customize by adding more images, swapping triggers (e.g., webhooks), or adjusting prompts. Requires Gemini API and Google Drive credentials; geo-restrictions may apply.

The workflow demonstrates efficient AI image editing, saving hours of Photoshop work while ensuring professional outputs for sales and creative pipelines.