Narrative chaining: AI-generated video scene extensions with Veo3

by Deniz ✓ · 1,000 views · created 2025-10-01 · Content Creation, Multimodal AI

What this workflow does

This AI workflow has 28 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model and Google Sheets. It also calls queue.fal.run and api.kie.ai over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Get input (Google Sheets): uses Google Sheets
2. Clear scenes (Google Sheets): clear
3. Initial Values (Edit Fields (Set)): sets 3 fields: step, complete, videoURL
4. Looper (Edit Fields (Set)): sets 3 fields: step, complete, mediaURL
5. Analyze Video (HTTP Request): calls queue.fal.run (POST)
6. Wait: waits 60 seconds
7. Get Analysis (HTTP Request): calls an HTTP API
8. Extend AI Agent (AI Agent): runs an AI agent, with model: GPT; 1 tool (Think); output parser: Structured Output
9. Request last (HTTP Request): calls queue.fal.run (POST)
10. Wait: waits 30 seconds

…plus 14 more steps. See the full node list below.

Services it uses

OpenAI Chat ModelGoogle Sheets

HTTP calls to: queue.fal.run, api.kie.ai

Before you upgrade to n8n 3.0

Nodes used (11)

• Think Tool@n8n/n8n-nodes-langchain.toolThink
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• HTTP Requestn8n-nodes-base.httpRequest
• Edit Fields (Set)n8n-nodes-base.set
• Ifn8n-nodes-base.if
• Aggregaten8n-nodes-base.aggregate
• Google Sheetsn8n-nodes-base.googleSheets
• Waitn8n-nodes-base.wait
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Manual Triggern8n-nodes-base.manualTrigger
• AI Agent@n8n/n8n-nodes-langchain.agent

From the author

Structured Setup Guide: Narrative Chaining with N8N + AI 1. Input Setup Use a Google Sheet as the control panel. Fields required: Video URL (starting clip, ends with .mp4) Number of clips to extend (e.g., 2 extra scenes) Aspect ratio (horizontal, vertical,…

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