The flow
Starts it 1Model 1Logic 4Service 6
The steps in the order they run, from what starts it.
- 1📱 Telegram TriggerTelegram triggerStarts it
- 2📋 Extract Message DataCodeLogic
- 3🔀 Route by Content Type - Image or TextSwitchLogic
- 4📸 Get Image file from TelegramTelegramService
- 5Get Text from TelegramTelegramService
- 6Analyze image using GPT-4O-MiniOpen AiModel
- 7HTTP Nvidia VilaHttp RequestService
- 8NVIDIA API NVIDIA Stable Diffusion 3Http RequestService
- 9🔀 Merge AI ResultsMergeLogic
- 10Convert to Binary FileCodeLogic
- 11Send a message of image-to-text resultsGmailService
- 12Send a message of text-to-image resultsGmailService
How it's built
- Starts on
- An incoming Telegram message
- Steps
- 12, with 1 branch
- Size
- Medium: a working afternoon
- Connects to
- Gmail, Telegram
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Gmail and Telegram accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on an incoming Telegram message.
Does it use AI?
Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 12 steps is enough that you should read each one before running it.
How do I import it?
Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.
Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 12 steps before you point it at anything that matters.