# Create viral ads with AI: NanoBanana: n8n workflow template

> Started by an incoming Telegram message, and works across Google Drive, Google Sheets and Telegram. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/create-viral-ads-with-ai-nanobanana (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Content](https://millionrounds.com/workflows?category=Content#library)

# Create viral ads with AI: NanoBanana

Started by an incoming Telegram message, and works across Google Drive, Google Sheets and Telegram. It hands the judgement calls to OpenAI. 35 steps, 4 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-viral-ads-with-ai-nanobanana)

**35 steps** Large: read it before trusting it with anything live

**0** Branches: places the flow splits

**4** Loops or waits

**3** Services it connects to

## The flow

Starts it 1 Model 6 Logic 8 Service 20

The steps in the order they run, from what starts it.

- 1 **Trigger: Receive Idea via Telegram** Telegram trigger *Starts it*
- 2 **Structured Output Parser** Output Parser Structured *Model*
- 3 **Think** Tool Think *Model*
- 4 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 5 **Telegram: Get Image File** Telegram *Service*
- 6 **Generate Image Prompt** Agent *Model*
- 7 **Google Drive: Upload Image** Google Drive *Service*
- 8 **NanoBanana: Create Image** Http Request *Service*
- 9 **Parse Idea Into Prompts** Code *Logic*
- 10 **Wait for Image Edit** Wait *Logic*
- 11 **Download Edited Image** Http Request *Service*
- 12 **Rewrite Caption (TikTok/Instagram)** Open Ai *Model*
- 13 **Seedance: Generate Video from Image** Http Request *Service*
- 14 **Upload Post** Upload Post *Service*
- 15 **Wait for Rendering** Wait *Logic*
- 16 **Download Video from Seedance** Http Request *Service*
- 17 **Set: Video URL** Set *Logic*
- 18 **Wait: Music Rendering1** Http Request *Service*
- 19 **Wait: Music Rendering** Wait *Logic*
- 20 **Download Music File** Http Request *Service*
- 21 **Set: Audio URL** Set *Logic*
- 22 **Merge Audio + Video** Http Request *Service*
- 23 **Wait: Merge Process** Wait *Logic*
- 24 **Check Merge Status** Http Request *Service*
- 25 **Download Final Video** Http Request *Service*
- 26 **Upload Final Video to Google Drive** Google Drive *Service*
- 27 **Read Brand Settings** Google Sheets *Service*
- 28 **Extract Brand Info** Code *Logic*
- 29 **Message a model** Open Ai *Model*
- 30 **Save Ad Data to Google Sheets** Google Sheets *Service*
- 31 **Send Video URL via Telegram** Telegram *Service*
- 32 **Send a video** Telegram *Service*
- 33 **Post Video on Social Media (FB, TikTok, YT)** Upload Post *Service*
- 34 **Save Publishing Status to Google Sheets** Google Sheets *Service*
- 35 **Telegram: Send notification** Telegram *Service*

## How it's built

- **Starts on:** An incoming Telegram message
- **Steps:** 35, 4 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, Google Sheets, Telegram
- **Model:** OpenAI

## Questions

What does it need to run?

An n8n account, plus your own Google Drive, Google Sheets 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?

Take your time. At 35 steps it is large: read it before trusting it with anything live.

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.

**Before you run it**

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 35 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-viral-ads-with-ai-nanobanana)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Google Sheets](https://millionrounds.com/workflows?service=Google+Sheets#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also content, with the same services where possible, closest in size first.

- [**AI content generation for Auto Service, automate your social** 35 steps · calls a model · Google Sheets, LinkedIn](https://millionrounds.com/workflow/ai-content-generation-for-auto-service-automate-your-social)
- [**AI content generation for auto service automate your social media** 35 steps · calls a model · Google Sheets, LinkedIn](https://millionrounds.com/workflow/ai-content-generation-for-auto-service-automate-your-social-)
- [**Automate RSS content to blog posts with WordPress and LinkedIn** 36 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/automate-rss-content-to-blog-posts-with-wordpress-and-linked)
- [**Automate news publishing to LinkedIn with Gemini and RSS** 34 steps · calls a model · Google Sheets, LinkedIn](https://millionrounds.com/workflow/automate-news-publishing-to-linkedin-with-gemini-and-rss)
- [**Automate video creation from voice input with HeyGen** 36 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/automate-video-creation-from-voice-input-with-heygen)
- [**Automated PDF & Image Text Extractor & Instant Social Media** 36 steps · calls a model · Discord, Gmail](https://millionrounds.com/workflow/automated-pdf-and-image-text-extractor-and-instant-social-me)