Automated Image Editing with LLM-Generated Coordinates

Http Request

Complex Trigger

This n8n workflow automates image editing tasks by dynamically extracting parameters from an AI model's output. It initiates with a manual trigger, primarily for testing or direct execution. The core functionality involves the 'Get Variables' node, which is designed to parse a specific JSON structure typically found in responses from Large Language Models (LLMs), such as Google Gemini. From this LLM output, it extracts image manipulation coordinates (e.g., for cropping, resizing, or overlaying elements) into a dedicated variable. The subsequent 'HTTP Request' node, listed as a service, indicates that these extracted coordinates are then used to interact with an external image processing API. This enables automated, context-aware image modifications based on AI-generated instructions, streamlining visual content creation or management processes.