Create AI image and video posts from Telegram with GPT-4o, AtlasCloud and Blotato
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 30 nodes and runs on Telegram events (message). Along the way it connects Telegram, OpenAI Chat Model and Blotato (community). It also calls api.atlascloud.ai over HTTP.
How it runs
Trigger: On Telegram events (message).
- Configuration (Edit Fields (Set)): sets 11 fields: post_description, telegram_chat_id, image_model…
- Generate platform posts (AI Agent): runs an AI agent, with model: GPT-4o mini; output parser: Platform posts schema
- Create image with GPT Image (HTTP Request): calls api.atlascloud.ai (POST)
- Create video with Seedance 2. (HTTP Request): calls api.atlascloud.ai (POST)
- Wait: waits 10 seconds
- Wait: waits 30 seconds
- Get image status (HTTP Request): calls an HTTP API
- Get video status (HTTP Request): calls an HTTP API
- Image ready? (If): checks a condition and branches into true / false
- Video ready? (If): checks a condition and branches into true / false
…plus 17 more steps. See the full node list below.
Services it uses
HTTP calls to: api.atlascloud.ai
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Generate platform posts (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Generate platform posts (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (11)
- Telegram Trigger
n8n-nodes-base.telegramTrigger - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - If
n8n-nodes-base.if - Telegram
n8n-nodes-base.telegram - Blotato
@blotato/n8n-nodes-blotato.blotato - Merge
n8n-nodes-base.merge
From the author
Quick overview This workflow receives a post idea via Telegram, uses OpenAI (GPT-4o mini) to generate platform-specific copy plus image/video prompts, creates media through AtlasCloud (GPT Image 2 and Seedance 2.0), requests approvals in Telegram, and…