Generate UGC e-commerce video ads with GPT-4o Vision, Gemini 2.5 Pro and Sora 2

by Kuzey Aras Sakınç ✓ · 24 views · created 2026-10-03 · Content Creation, Multimodal AI

What this workflow does

This AI workflow has 20 nodes and runs when someone submits an n8n form (“eCommerce Product Video Generator”). Along the way it connects OpenAI and Google Gemini Chat Model. It also calls generativelanguage.googleapis.com and gateway-api.prototipal.com over HTTP.

How it runs

Trigger: When someone submits an n8n form (“eCommerce Product Video Generator”).

1. extract_webhook_data (Edit Fields (Set)): sets 2 fields: productName, productImageUrl
2. download_product_image (HTTP Request): calls an HTTP API
3. convert_product_to_base (Extract from File): extracts data from a file (binary to propery)
4. convert_product_to_image (Convert to File): converts data to a file (to binary)
5. analyze_product (OpenAI): analyze (image)
6. set_model_details (Edit Fields (Set)): sets 1 field: prompt
7. set_build_video_prompts (Edit Fields (Set)): sets 1 field: prompt
8. generate_ad_prompts (HTTP Request): calls generativelanguage.googleapis.com (POST)
9. extract_prompts (Basic LLM Chain): sends a prompt to an LLM, with model: gemini-2.5-pro; output parser: prompts-parser
10. split_prompts (Split Out): splits a list into separate items

…plus 7 more steps. See the full node list below.

Services it uses

OpenAIGoogle Gemini Chat Model

HTTP calls to: generativelanguage.googleapis.com, gateway-api.prototipal.com

Before you upgrade to n8n 3.0

Nodes used (13)

• OpenAI@n8n/n8n-nodes-langchain.openAi
• Edit Fields (Set)n8n-nodes-base.set
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Split Outn8n-nodes-base.splitOut
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• HTTP Requestn8n-nodes-base.httpRequest
• Extract from Filen8n-nodes-base.extractFromFile
• Convert to Filen8n-nodes-base.convertToFile
• n8n Form Triggern8n-nodes-base.formTrigger
• Ifn8n-nodes-base.if
• Waitn8n-nodes-base.wait

From the author

Quick overview This workflow collects a product image URL and product name from an n8n form, uses OpenAI Vision to build an ideal UGC creator persona, uses Google Gemini to generate three 12‑second UGC scripts, and then generates portrait videos for each…

View the original on n8n.io → Check your own copy