[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [H3 Max 3D to Video](https://spiral.ai/integrations/muse-code/h3-max-3d-to-video)

# How to Use H3 Max 3D to Video in Muse Code

H3 Max 3D to Video turns rough 3D animation into photoreal footage for product films, architectural previews, and cinematics. Its camera and action follow a rendered source clip, with optional images guiding appearance.

|  |  |
| --- | --- |
| Model | H3 Max 3D to Video |
| Available through | fal |
| Category | Video |
| Price | Up to $16.767504 per run at the default inputs for 60 seconds of input. `resolution`: 480P $14.427504, 768P (default) $16.767504, 1080P $23.007504. $26.00 per 1M input tokens. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with H3 Max 3D to Video in Muse Code

- Use H3 Max 3D to Video on the project's 8-second product turntable at 1080p. Guide the brushed steel finish with the product references.
- Process the project's 10-second villa blockout with H3 Max 3D to Video. Explain that the blue slab is a pool and export at 768p.
- Use H3 Max 3D to Video on the 12-second level flythrough. Apply the environment references and return a 1080p trailer concept.
- Convert the project's 6-second vehicle previs with H3 Max 3D to Video at 768p. Describe the vehicle as a red delivery van.
- Use H3 Max 3D to Video on the 15-second, three-shot machine animation at 1080p. Flag visible departures from the source mechanics.

## How to set up H3 Max 3D to Video in Muse Code

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse Code this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run H3 Max 3D to Video**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "minimax/h3-max/3d-to-video",
    "input": {
      "video_url": "<video_url>"
    }
  }'
```

Then paste one of the prompts above: Muse Code finds H3 Max 3D to Video on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## H3 Max 3D to Video tools and prices

- [H3 Max 3D to Video](https://spiral.ai/tools/fal/minimax/h3-max/3d-to-video) (fal): Up to $16.767504 per run at the default inputs for 60 seconds of input. `resolution`: 480P $14.427504, 768P (default) $16.767504, 1080P $23.007504. $26.00 per 1M input tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| prompt |  | — | Optional clarification of what your proxies represent or how they move, for example: 'The moving block represents a running person.' Camera, trajectories, timing and object count remain defined by the video. |
| reference_image_urls |  | — | Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video. |
| max_generated_reference_images | 1 to 8 | 2 | Maximum NEW images to generate when no reference images are supplied. Ignored when reference images are supplied. Uses fewer when enough views are covered. Uncovered shots stay in the video. |
| resolution | 480P, 768P, 1080P | 768P | Output quality. Duration is taken automatically from the video. |

## What can you do with H3 Max 3D to Video in Muse Code?

Turn project previs renders into photoreal footage for review. Use the project's animation to establish motion and its reference images to guide appearance.

### Product reveal

Turn a rendered product turntable into a photoreal reveal, using product images to guide its finish.

### Architectural preview

Convert a building blockout's camera pass into a presentation showing the intended materials and setting.

### Game trailer pitch

Use a rendered camera run through a gray-box level to explore a trailer's visual direction.

### Film previs review

Give a rough animated sequence a photoreal treatment for reviewing blocking and shot choices.

### Automotive concept film

Start with a rendered vehicle animation and explore the surrounding environment, reflections, and light.

### Machine presentation

Turn a rendered machine animation into a visual concept, reviewing the result for mechanical accuracy.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## H3 Max 3D to Video in other agents

- [Amp](https://spiral.ai/integrations/amp/h3-max-3d-to-video)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/h3-max-3d-to-video)
- [Claude](https://spiral.ai/integrations/claude-desktop/h3-max-3d-to-video)
- [Claude Code](https://spiral.ai/integrations/claude-code/h3-max-3d-to-video)
- [Cline](https://spiral.ai/integrations/cline/h3-max-3d-to-video)
- [Codex](https://spiral.ai/integrations/codex/h3-max-3d-to-video)
- [Cursor](https://spiral.ai/integrations/cursor/h3-max-3d-to-video)
- [Devin](https://spiral.ai/integrations/devin/h3-max-3d-to-video)
- [dots](https://spiral.ai/integrations/dots/h3-max-3d-to-video)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/h3-max-3d-to-video)
- [Gemini](https://spiral.ai/integrations/gemini/h3-max-3d-to-video)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/h3-max-3d-to-video)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/h3-max-3d-to-video)
- [goose](https://spiral.ai/integrations/goose/h3-max-3d-to-video)
- [Grok](https://spiral.ai/integrations/grok/h3-max-3d-to-video)
- [Grok Build](https://spiral.ai/integrations/grok-build/h3-max-3d-to-video)
- [Hermes](https://spiral.ai/integrations/hermes/h3-max-3d-to-video)
- [Instinct](https://spiral.ai/integrations/instinct/h3-max-3d-to-video)
- [Manus](https://spiral.ai/integrations/manus/h3-max-3d-to-video)
- [Muse](https://spiral.ai/integrations/muse/h3-max-3d-to-video)
- [n8n](https://spiral.ai/integrations/n8n/h3-max-3d-to-video)
- [Notion](https://spiral.ai/integrations/notion/h3-max-3d-to-video)
- [OpenClaw](https://spiral.ai/integrations/openclaw/h3-max-3d-to-video)
- [opencode](https://spiral.ai/integrations/opencode/h3-max-3d-to-video)
- [Perplexity](https://spiral.ai/integrations/perplexity/h3-max-3d-to-video)
- [Raycast](https://spiral.ai/integrations/raycast/h3-max-3d-to-video)
- [VS Code](https://spiral.ai/integrations/vscode/h3-max-3d-to-video)
- [Windsurf](https://spiral.ai/integrations/windsurf/h3-max-3d-to-video)
- [Zapier](https://spiral.ai/integrations/zapier/h3-max-3d-to-video)

## More Muse Code guides

- [Grok Imagine Video 1.5 Text to Video](https://spiral.ai/integrations/muse-code/grok-imagine-video-1-5-text-to-video)
- [H3 Max Camera Controls](https://spiral.ai/integrations/muse-code/h3-max-camera-controls)
- [Grok Imagine Video 1.5 Reference to Video](https://spiral.ai/integrations/muse-code/grok-imagine-video-1-5-reference-to-video)
- [H3 Max Extend Video](https://spiral.ai/integrations/muse-code/h3-max-extend-video)
- [Grok Imagine Video 1.5 Image to Video](https://spiral.ai/integrations/muse-code/grok-imagine-video-1-5-image-to-video)
- [H3 Max Image to Video](https://spiral.ai/integrations/muse-code/h3-max-image-to-video)

## Questions about H3 Max 3D to Video in Muse Code

**Can Muse Code use H3 Max 3D to Video?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run H3 Max 3D to Video like any built-in tool.

**How much does H3 Max 3D to Video cost in Muse Code?**

Up to $16.767504 per run at the default inputs for 60 seconds of input. `resolution`: 480P $14.427504, 768P (default) $16.767504, 1080P $23.007504. $26.00 per 1M input tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

**Do I need a fal account to use H3 Max 3D to Video in Muse Code?**

No. Spiral runs H3 Max 3D to Video on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up H3 Max 3D to Video in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while H3 Max 3D to Video runs?**

H3 Max 3D to Video runs in the background. Muse Code starts the run, checks on it and gives you the video when it's ready.

**What is H3 Max 3D to Video good for?**

Turning rough 3D animation into photoreal footage when you have already planned the camera and action. Useful applications include product films, architectural previews, and game trailers.

**How long can the finished video be?**

The source can run up to 15 seconds and contain up to 32 shots. The finished video matches its duration.

**Does it reproduce the 3D scene exactly?**

Exact geometry, camera paths, and motion are not guaranteed. Review any shot where precise alignment matters.

**What should the scene description explain?**

Explain what unclear shapes represent, such as a moving block standing for a person. Put the desired camera movement and timing into the source animation.

**Are reference images required?**

No. The model generates appearance references when you supply none; use your own images when a particular subject, environment, or finish matters.

