Generate scalable e-commerce product images with GPT-4 and NanoBanana Pro

Go to Workflow
0 views
Built by Dr. Firas Dr. Firas
Created on June 05, 2026

Description

🚀 AI Image Generation Workflow – Scalable E-commerce Product Images

This workflow automates the creation of high-quality, AI-generated product images using NanoBanana Pro.
It analyzes multiple reference images, generates a professional photoshoot-style prompt, creates a new image, and stores the final result with a public URL for reuse.




📄 Documentation: Notion Guide

👤 Who is this for?

This workflow is designed for:

E-commerce store owners
Digital marketers and growth teams
Creative agencies
Automation builders using n8n
Anyone who wants to generate scalable, consistent product images from existing photos

No advanced coding skills are required.

❓ What problem does this workflow solve? / Use case

Creating professional product images at scale is expensive, slow, and inconsistent.

This workflow solves:
Manual photoshoot costs
Inconsistent visual branding
Time wasted on prompt writing
Difficulty generating AI-ready public image URLs
Repetitive image upload and storage steps

Typical use case:
Transform 3 reference photos (model + product) into a studio-quality fashion image automatically.

⚙️ What this workflow does

Collects exactly 3 images via a form upload
Validates inputs to ensure all required images are present
Splits images into individual processing paths
Uploads original images to Google Drive (permanent storage)
Generates public, crawlable image URLs
Analyzes each image using AI vision (GPT-4O)
Aggregates image descriptions into a structured context
Generates a professional photoshoot prompt using an AI agent
Creates a new image via NanoBanana Pro
Polls the API until the image generation is completed
Downloads the final image as a binary file
Uploads the final image to Google Drive
Logs results (images + descriptions) into Google Sheets

🛠️ Setup

Required credentials
Google Drive (OAuth)
Google Sheets (OAuth)
OpenAI API key
AtlasCloud API key

Required configuration
Replace all <PLACEHOLDER_VALUE> fields:
Google Drive folder IDs
Google Sheets document ID and sheet name
AtlasCloud API key
Ensure Google Drive folders have write permissions
Confirm tmpfiles.org is reachable from your environment

Important notes
The workflow expects exactly 3 images
The final image is downloaded as binary before upload
Public URLs are normalized to https://tmpfiles.org/dl/... for maximum AI compatibility

🎥 Watch This Tutorial

👋 Need help or want to customize this?
📩 Contact: LinkedIn
📺 YouTube: @DRFIRASS
🚀 Workshops: Mes Ateliers n8n

Need help customizing?
Contact me for consulting and support : Linkedin / Youtube / 🚀 Mes Ateliers n8n

Nodes Used (8)

AI Agent
@n8n/n8n-nodes-langchain.agent
Code
n8n-nodes-base.code
Google Drive
n8n-nodes-base.googleDrive
Google Sheets
n8n-nodes-base.googleSheets
HTTP Request
n8n-nodes-base.httpRequest
OpenAI
@n8n/n8n-nodes-langchain.openAi
OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured