Instagram reels creation with GPT-4o-mini and Sisif.ai
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: Function (legacy). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 10 nodes and runs on a schedule (every 6 hours). Along the way it connects OpenAI Chat Model. It also calls sisif.ai over HTTP.
How it runs
Trigger: On a schedule (every 6 hours).
- Set Reels Config (Edit Fields (Set)): sets or maps fields
- Idea creator (Basic LLM Chain): sends a prompt to an LLM, with model: OpenAI Chat Model; output parser: Structured Output Parser
- Create Sisif Video (HTTP Request): calls sisif.ai (POST)
- Wait: waits 10 seconds
- Check Video Status (HTTP Request): calls an HTTP API
- Video Ready? (If): checks a condition and branches into true / false
- Prepare Final Data (Function): runs custom JavaScript (legacy Function node)
Services it uses
HTTP calls to: sisif.ai
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- Function (legacy) in Prepare Final Data: replace with Code node, mode 'Run Once for All Items'.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| Function (legacy) Prepare Final Data | Code node, mode 'Run Once for All Items' |
Nodes used (9)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - If
n8n-nodes-base.if - Function
n8n-nodes-base.function - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Edit Fields (Set)
n8n-nodes-base.set - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
From the author
Description This workflow automates a video content pipeline that generates creative, Instagram Reel videos using AI. It combines OpenAI's GPT-4o-mini for idea generation with Sisif.ai's text-to-video AI technology to produce engaging short-form content…