Generate & Edit Images with OpenAI GPT-Image-1

This n8n workflow leverages OpenAI's GPT-Image-1 model to generate images from text prompts and edit existing ones via API endpoints. It starts with a manual trigger, generates a base64 image, converts it to binary, applies edits with a new prompt, and outputs the final binary file for download or further use. No programming is required, making it accessible for n8n users with OpenAI credentials.

Key benefits include rapid visual content creation, prompt chaining for iterative designs, and compatibility with marketing or creative tools. It saves hours of manual design work by automating high-quality image manipulation.

Ideal use cases: artists generating concept art variations, e-commerce for product mockups, marketing teams creating social media visuals, and bonus integrations like Telegram/Slack for chat-based image generation or webhooks for form-fed prompts.