The flow
Starts it 1Model 3Logic 5Service 4
The steps in the order they run, from what starts it.
- 1Telegram TriggerTelegram triggerStarts it
- 2HTTP- Leonardo AIHttp RequestService
- 3Structured Output ParserOutput Parser StructuredModel
- 4DeepSeek from OpenRouterLm Chat Open RouterModel
- 5Image-countSetLogic
- 6Prompt generator (USER_Inspired)Chain LlmModel
- 7Split Out PromptsSplit OutLogic
- 8Loop Over PromptsSplit In BatchesLogic
- 9Send pics via TelegramTelegramService
- 10HTTP- GeminiHttp RequestService
- 11Set base64SetLogic
- 12Convert to FileConvert To FileService
- 13Wait 10sWaitLogic
How it's built
- Starts on
- An incoming Telegram message
- Steps
- 13, 2 loops or waits
- Size
- Medium: a working afternoon
- Connects to
- Telegram
- Model
- OpenRouter
Questions
What does it need to run?
An n8n account, plus your own Telegram account, and a key for OpenRouter. 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 OpenRouter. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 13 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 13 steps before you point it at anything that matters.