Re-render product images and auto-tag VNTANA 3D assets with Gemini

by Derek Cicero ✓ · 11 views · created 2026-07-21 · Content Creation, Multimodal AI

What this workflow does

This workflow has 11 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Vntana (community). It also calls generativelanguage.googleapis.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Download renders (Vntana): work with render
2. Skip Images Already Processed (Code): runs custom JavaScript code
3. Prep Image for Gemini (Code): runs custom JavaScript code
4. Limit: keeps the first few items
5. Gemini Studio Re-render (HTTP Request): calls generativelanguage.googleapis.com (POST)
6. Gemini Tagging (HTTP Request): calls generativelanguage.googleapis.com (POST)
7. Extract Gemini Image (Code): runs custom JavaScript code
8. Resolve Tags & Update Asset (Code): runs custom JavaScript code
9. Upload a render (Vntana): upload (render)

Services it uses

Vntana (community)

HTTP calls to: generativelanguage.googleapis.com

Before you upgrade to n8n 3.0

Nodes used (6)

• Manual Triggern8n-nodes-base.manualTrigger
• Webhookn8n-nodes-base.webhook
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• Limitn8n-nodes-base.limit
• Vntanan8n-nodes-vntana.vntana

From the author

Quick Overview This workflow receives a VNTANA product publish webhook, downloads the product’s renders, uses Google Gemini to create a studio-style re-render and generate catalog tags, then uploads the new render back to VNTANA and updates the product’s tags…

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