# Turn ideas into movies with DeepSeek and RunwayML: n8n workflow

> Started by another system calling it, and works across Dropbox, Notion and Slack. It hands the judgement calls to DeepSeek.

Source: https://millionrounds.com/workflow/turn-ideas-into-movies-with-deepseek-and-runwayml (Millionrounds; every figure on the page links to its filing or article)

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

# Turn ideas into movies with DeepSeek and RunwayML

Started by another system calling it, and works across Dropbox, Notion and Slack. It hands the judgement calls to DeepSeek. 38 steps, 5 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: DeepSeek

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fturn-ideas-into-movies-with-deepseek-and-runwayml)

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

**0** Branches: places the flow splits

**5** Loops or waits

**3** Services it connects to

## The flow

Starts it 1 Model 11 Logic 14 Service 12

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

- 1 **Narrative LLM Core** Lm Chat Deep Seek *Model*
- 2 **Visual LLM Core** Lm Chat Deep Seek *Model*
- 3 **Score LLM Core** Lm Chat Deep Seek *Model*
- 4 **Voice LLM Core** Lm Chat Deep Seek *Model*
- 5 **Visual Parser** Output Parser Structured *Model*
- 6 **Score Parser** Output Parser Structured *Model*
- 7 **Voice Parser** Output Parser Structured *Model*
- 8 **Creative Brief Intake** Webhook *Starts it*
- 9 **Narrative Director** Chain Llm *Model*
- 10 **Visual Art Director** Chain Llm *Model*
- 11 **Score Composer** Chain Llm *Model*
- 12 **Narration Artist** Chain Llm *Model*
- 13 **Creative Archive** Notion *Service*
- 14 **Scene Breakdown** Split Out *Logic*
- 15 **Orchestration Engine** Http Request *Service*
- 16 **Dialogue Segmenter** Split Out *Logic*
- 17 **Production Sync Hub** Merge *Logic*
- 18 **Concept Art Studio** Http Request *Service*
- 19 **Track Data Manager** Set *Logic*
- 20 **Line Delivery Manager** Split In Batches *Logic*
- 21 **Post-Production Orchestrator** Code *Logic*
- 22 **Render Queue** Wait *Logic*
- 23 **Voiceover Collector** Merge *Logic*
- 24 **Voice Synthesis Studio** Http Request *Service*
- 25 **Final Cut Renderer** Http Request *Service*
- 26 **Asset Fetcher** Http Request *Service*
- 27 **Voice Upload Loop** Split In Batches *Logic*
- 28 **Rendering Buffer** Wait *Logic*
- 29 **Storyboard Assembler** Http Request *Service*
- 30 **Dropbox Uploader** Dropbox *Service*
- 31 **File Renamer** No Op *Logic*
- 32 **Final Delivery Fetcher** Http Request *Service*
- 33 **Encoding Queue** Wait *Logic*
- 34 **Dropbox Link Generator** Http Request *Service*
- 35 **Release Announcement** Slack *Service*
- 36 **Media Retriever** Http Request *Service*
- 37 **Voiceover Mapper** Set *Logic*
- 38 **Metadata Curator** Set *Logic*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 38, 5 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Dropbox, Notion, Slack
- **Model:** DeepSeek

## Questions

What does it need to run?

An n8n account, plus your own Dropbox, Notion and Slack accounts, and a key for DeepSeek. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls DeepSeek. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 38 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 38 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%2Fturn-ideas-into-movies-with-deepseek-and-runwayml)
- **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.

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

## Workflows like it

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

- [**Rerank PM priorities every 2 hours with OpenAI and Notion** 40 steps · calls a model · Notion, Slack](https://millionrounds.com/workflow/rerank-pm-priorities-every-2-hours-with-openai-and-notion)
- [**Generate consensus-based answers with Claude and OpenAI** 41 steps · calls a model · Gmail, Slack](https://millionrounds.com/workflow/generate-consensus-based-answers-with-claude-and-openai)
- [**Pyragogy AI Village - Orchestration Master with OpenAI** 35 steps · calls a model · Email, GitHub](https://millionrounds.com/workflow/pyragogy-ai-village-orchestrazione-master-with-openai)
- [**Pyragogy AI-driven handbook generator with OpenAI and GitHub** 35 steps · calls a model · Email, GitHub](https://millionrounds.com/workflow/pyragogy-ai-driven-handbook-generator-with-openai-and-github)
- [**Assist hospital doctors with Telegram and OpenAI** 34 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/assist-hospital-doctors-with-telegram-and-openai)
- [**Guard releases and investigate regressions with Browserbase** 34 steps · calls a model · Email, GitHub](https://millionrounds.com/workflow/guard-releases-and-investigate-regressions-with-browserbase)