# Grok Imagine Video Chatbot : Generate & Modify Videos: n8n workflow

> Started by someone opening a chat with it, and works across FTP. It puts OpenRouter behind a retrieval step, so answers are drawn from documents you supply...

Source: https://millionrounds.com/workflow/grok-imagine-video-chatbot-generate-and-modify-videos (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)

# Grok Imagine Video Chatbot: Generate & Modify Videos

Started by someone opening a chat with it, and works across FTP. It puts OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 27 steps, 5 branches, 3 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenRouter Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgrok-imagine-video-chatbot-generate-and-modify-videos)

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

**5** Branches: places the flow splits

**3** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 6 Logic 9 Service 10

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

- 1 **Run text to video** Tool Workflow *Model*
- 2 **Run Text-to-Video1** Execute Workflow trigger *Starts it*
- 3 **When chat message received** Chat trigger *Starts it*
- 4 **Simple Memory** Memory Buffer Window *Model*
- 5 **Run image to video** Tool Workflow *Model*
- 6 **Run video to video** Tool Workflow *Model*
- 7 **Grok 4.1 Fast** Lm Chat Open Router *Model*
- 8 **Grok Imagine Video Agent** Agent *Model*
- 9 **Switch1** Switch *Logic*
- 10 **Binary?** If *Logic*
- 11 **Text to Video** Http Request *Service*
- 12 **Edit Video** Http Request *Service*
- 13 **Image to Video** Http Request *Service*
- 14 **Upload image** Ftp *Service*
- 15 **Wait 10 sec.** Wait *Logic*
- 16 **Wait 10 sec.1** Wait *Logic*
- 17 **Wait 10 sec.2** Wait *Logic*
- 18 **Set Image Url** Set *Logic*
- 19 **Get status** Http Request *Service*
- 20 **Get status1** Http Request *Service*
- 21 **Get status2** Http Request *Service*
- 22 **Completed?** If *Logic*
- 23 **Completed?1** If *Logic*
- 24 **Completed?2** If *Logic*
- 25 **Get final text to video url** Http Request *Service*
- 26 **Get final edit video url** Http Request *Service*
- 27 **Get final image to video url** Http Request *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 27, with 5 branches, 3 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** FTP
- **Model:** OpenRouter
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own FTP account, and a key for OpenRouter. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenRouter. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 27 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 27 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%2Fgrok-imagine-video-chatbot-generate-and-modify-videos)
- **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.

[FTP](https://millionrounds.com/workflows?service=FTP#library)

## Workflows like it

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

- [**AI YouTube Shorts Creator: Prompt-Based Clipping, Dubbing** 26 steps · calls a model · FTP, Google Drive](https://millionrounds.com/workflow/ai-youtube-shorts-creator-prompt-based-clipping-dubbing)
- [**Video speech enhancement with OpenAI Whisper** 26 steps · calls a model · FTP, Google Drive](https://millionrounds.com/workflow/video-speech-enhancement-with-openai-whisper)
- [**Automate video voiceover & subtitles with OpenAI TTS** 38 steps · calls a model · FTP, Google Drive](https://millionrounds.com/workflow/automate-video-voiceover-and-subtitles-with-openai-tts)
- [**Telegram video merger bot with FTP and Postgres** 42 steps · FTP, Postgres](https://millionrounds.com/workflow/telegram-video-merger-bot-with-ftp-and-postgres)
- [**Generate highly expressive audio with ElevenLabs** 10 steps · calls a model · FTP, Google Drive](https://millionrounds.com/workflow/generate-highly-expressive-audio-with-elevenlabs)