Telegram bot: analyze images with GPT-4o-Mini/NVIDIA Vila & generate images with Stable Diffusion 3
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 12 nodes and runs on Telegram events (message). Along the way it connects Telegram, Gmail and OpenAI. It also calls ai.api.nvidia.com over HTTP.
How it runs
Trigger: On Telegram events (message).
- 📋 Extract Message Data (Code): runs custom JavaScript code
- 🔀 Route by Content Type - Image or Text (Switch): routes items into 2 branches
- 📸 Get Image file from Telegram (Telegram): work with file
- Get Text from Telegram (Telegram): uses Telegram
- Analyze image using GPT-4O-Mini (OpenAI): analyze (image)
- HTTP Nvidia Vila (HTTP Request): calls ai.api.nvidia.com (POST)
- NVIDIA API NVIDIA Stable Diffusion (HTTP Request): calls ai.api.nvidia.com (POST)
- Merge: merges the data from its input branches
- Convert to Binary File (Code): runs custom JavaScript code
- Send a message of image-to-text results (Gmail): uses Gmail
…plus 1 more step. See the full node list below.
Services it uses
HTTP calls to: ai.api.nvidia.com
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 (8)
- Telegram Trigger
n8n-nodes-base.telegramTrigger - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Merge
n8n-nodes-base.merge - Gmail
n8n-nodes-base.gmail - OpenAI
@n8n/n8n-nodes-langchain.openAi - Switch
n8n-nodes-base.switch - Telegram
n8n-nodes-base.telegram
From the author
Introduction Transform your Telegram bot into an AI vision system using GPT-4o-Mini and NVIDIA Stable Diffusion 3. Perfect for content moderators, researchers, and developers. Workflow Explanatory 1. At start: Processes Telegram messages: images→analysis,…