Extract License Plate from Car Image via n8n Form

This workflow demonstrates a simple yet powerful way to perform image-to-text analysis in n8n. It starts with a form trigger that allows users to upload an image of a car. The uploaded file is then processed by an LLM via OpenRouter.ai, using a customizable prompt to extract the license plate number. This setup showcases seamless integration of file uploads with AI vision models for quick prototyping.

Benefits include rapid development without custom coding, cost-effective use of various LLMs through OpenRouter, and high flexibility. Users save significant time compared to building from scratch, enabling instant testing and iteration. It's ideal for proof-of-concepts in automotive, security, or parking applications where license plate recognition is needed.

To adapt, modify the prompt in the Settings node for tasks like image summarization, location identification, or general text extraction. Experiment with models such as google/gemini-2.0-flash-001, meta-llama/llama-3.2-90b-vision-instruct, or openai/gpt-4o for optimal results. For production, consider specialized APIs like Google Cloud Vision.

Setup is straightforward: import the workflow, create an OpenRouter credential with your API key, and test by submitting a car image. This workflow highlights n8n's strength in AI-driven automations, making advanced computer vision accessible to non-experts.