Generate UGC-style AI videos with Google Sheets, NanoBanana Pro and Veo 3.1
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 24 nodes and runs on a schedule (every hour) (plus 1 other trigger). Along the way it connects Google Sheets, OpenAI, OpenAI Chat Model and Groq Chat Model. It also calls api.atlascloud.ai and tmpfiles.org over HTTP.
How it runs
Trigger: On a schedule (every hour) (plus 1 other trigger).
- Get Ready Task (Google Sheets): uses Google Sheets
- Get Edited Task (Google Sheets): uses Google Sheets
- Image Prompt Agent (AI Agent): runs an AI agent, with model: GPT-5-Mini, GPT-OSS-120b
- Video Prompt Agent (AI Agent): runs an AI agent, with model: GPT-5-Mini, GPT-OSS-120b
- Get Image Array (Code): runs custom JavaScript code
- Veo 3. (HTTP Request): calls api.atlascloud.ai (POST)
- Split Out: splits a list into separate items
- Wait: waits 10 seconds
- Download Images (HTTP Request): calls an HTTP API
- Get a Video (HTTP Request): calls an HTTP API
…plus 10 more steps. See the full node list below.
Services it uses
HTTP calls to: api.atlascloud.ai, tmpfiles.org
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (12)
- Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - AI Agent
@n8n/n8n-nodes-langchain.agent - If
n8n-nodes-base.if - Google Sheets
n8n-nodes-base.googleSheets - Schedule Trigger
n8n-nodes-base.scheduleTrigger - OpenAI
@n8n/n8n-nodes-langchain.openAi - Wait
n8n-nodes-base.wait - Switch
n8n-nodes-base.switch - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq
From the author
🎬 AI-Powered UGC Video Generator Automatically create consistent, professional UGC (User-Generated Content) videos at scale using cutting-edge AI models. This workflow combines three reference images into hyper-realistic selfie-style photos, then transforms…