AI Fashion Image Generator with Nano Banana + n8n workflow

Discover the basics of n8n, a no-code, open source workflow tool, and learn how drag-and-drop connects APIs, databases, SaaS apps, and AI models like OpenAI and ChatGPT.

Learn to automate with n8n using drag-and-drop nodes to connect 300+ services, automate repetitive tasks, and integrate AI tools like OpenAI for chatbots and content generation.

Discover three installation options for n8n: cloud hosted by the n8n team, self-hosted on your own server with unlimited workflows, and enterprise edition for larger teams.

Launch an AWS EC2 instance running Ubuntu 24.04 LTS (t2.micro) using the free tier, create a key pair, access via SSH with Mobaxterm, and prepare for installing n8n.

Install and configure Docker and Docker Compose on Ubuntu, including setting up the apt repository, verifying installations, and enabling non-sudo access by adding the user to the Docker group.

Set up n8n with docker compose version 3.8 using image n8n:latest, map port 5678, and configure an .env file for admin credentials and http, plus a host volume for data.

Launch the n8n server with docker compose up -d, pull the latest image, and verify it runs with docker ps and logs.

Connect to the n8n server on an EC2 docker setup via browser, access the dashboard and start a free trial, then prepare to copy the key in the next lecture.

Copy the activation key from the email, paste it in the activation key field in settings, and click activate. Activate the license for the community edition and start creating automations.

Explore the n8n dashboard to access your home base for managing workflows. Securely store credentials, view execution history, and use templates and variables to streamline automations.

Explore node types in n8n workflows, including trigger, processing, logic branches, action, and end, and learn they combine to automate tasks such as sending emails, updating databases, and notifying teams.

Design and implement an ai powered fashion image generator using nano banana and n8n workflow to transform uploaded outfits into high quality model photos via image analysis and prompt generation.

Trigger an n8n workflow on form submission at chatbot.com to transform an outfit image into quality model photos with natural poses, using a required file and a simple prompt.

Upload an output image via an http post to ImgBB, then obtain a publicly accessible URL for the next steps in the n8n workflow.

Upload the outfit image via an http request node to img Bebe using form data, then use the public url and ensure the n8n binary file name matches 'image'.

Analyze the uploaded image with the OpenAI node to extract colors, text style, and patterns; merge these with the user prompt to create a final prompt with fashion details.

Create an OpenAI account, add a $5 billing credit, generate API keys for text models and image generation, and name the secret key nano banana testing in n8n.

Set the analyze image operation in the image node, selecting the GPT four zero mini model and an image URL to extract caption, tags, colors, and style.

The ai agent analyzes the outfit image to extract color and fabric details, then uses the thing tool and prompt generator to combine user requests with analysis into a prompt.

Configure an AI agent prompt to generate a single, accurate image prompt by combining the user request with image analysis, include aspect ratio, and verify with think tool before finalizing.

Integrate a chat model and the Think tool into an ai agent to combine user instruction with image analysis. Execute workflow to generate the final image prompt.

Queue the image by sending the final prompt to the nano banana api via an http post request to felt ai, using an api key in the n8n workflow.

Create an api key on fal.ai, copy it, and authenticate with an authorization header. Send a json body with the prompt and image url, ensuring json safety by escaping characters.

Run the nano banana and n8n workflow to generate a high-quality image from the prompt on felt AI, verify the result on fal.ai, and add email delivery in the workflow.

Implement an http request to fetch images from Felt AI within an n8n workflow, using an api key for authorization, and insert a wait node to handle image generation delays.

Add a wait node between image generation and retrieval, configure a 30-second pause, then set up an http request with authorization to fetch the image url and retrieve the image.

Implement an if node in the ai fashion image generator workflow to check the image URL, looping on wait until the image is ready, then retrieve it via email.

Fetch the final generated model image with an HTTP GET request using the provided URL, then view or download it. Add a Gmail node to receive the image by email.

Configure a Gmail node to send the image, creating OAuth client ID and client secret in Google Cloud Console and signing in to establish the connection.

Configure Gmail node parameters to send an image by specifying the recipient, subject 'your image is ready,' and an HTML body with an attachment.

Execute the built ai fashion image generator workflow to generate a full-body suit image of an Indian actress, submit the prompt and file, and receive the image by email.

Execute the final ai fashion image generator workflow to create high-quality images by naming indian actors like Katrina Kaif or Shah Rukh Khan and outfits, then check email results.

Celebrate reaching the last lecture of this course module; post doubts in the question-answer forum or ping the instructor for quick responses and good luck on your exam and career.