[Integrations](https://spiral.ai/integrations) › [Gemini](https://spiral.ai/integrations/gemini) › [Vidu Reference to Video](https://spiral.ai/integrations/gemini/vidu-reference-to-video)

# How to Use Vidu Reference to Video in Gemini

Vidu Reference to Video uses reference images to keep subjects recognizable while generating a scene. Unlike Vidu Image to Video, it uses images to guide subject appearance rather than define the opening frame.

|  |  |
| --- | --- |
| Model | Vidu Reference to Video |
| Available through | fal |
| Category | Video |
| Price | $0.52 per run at the default inputs. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Vidu Reference to Video in Gemini

- Use Vidu Reference to Video with these character and café images. Show the character sitting at a table and looking toward the window; use a wide composition and keep the clothing consistent.
- Use Vidu Reference to Video with these toy robot references. Create a square shot of the robot raising one arm, using small movement and keeping its shape and colors consistent.
- Estimate, then generate a 5-second 9:16 clip with Vidu Reference to Video: a paper boat drifting down a rainy street.
- Make a 10-second product teaser with Vidu Reference to Video for a smartwatch, slow orbit shot, studio lighting.
- Generate three 5-second b-roll clips of a busy coffee shop with Vidu Reference to Video and list what each cost.

## How to set up Vidu Reference to Video in Gemini

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

### Use the Gemini connector

1. **Open Connected Apps**: On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.

2. **Add Spiral as a custom app**: Under Custom apps, click Add a custom app and paste this MCP server URL:

```text
https://api.spiral.ai/mcp
```

3. **Sign in to Spiral and approve**: Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Gemini 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 Vidu Reference 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": "fal-ai/vidu/reference-to-video",
    "input": {
      "prompt": "The little devil is looking at the apple on the beach and walking around it.",
      "reference_image_urls": [
        "<reference_image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini finds Vidu Reference to Video on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini

## Vidu Reference to Video tools and prices

- [Vidu Reference to Video · Reference-to-Video](https://spiral.ai/tools/fal/fal-ai/vidu/reference-to-video) (fal): $0.52 per run at the default inputs.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | Random seed for generation |
| aspect_ratio | 16:9, 9:16, 1:1 | 16:9 | The aspect ratio of the output video |
| movement_amplitude | auto, small, medium, large | auto | The movement amplitude of objects in the frame |

## What can you do with Vidu Reference to Video in Gemini?

Turn supplied visual ideas into short clips you can compare and refine in conversation. A chat app can help describe the action, camera direction, and details to preserve before generating each draft.

### Product ad concepts

Use product images to test a short reveal, a gentle camera move, or movement around a stationary object. Review whether the product remains recognizable before developing the ad.

### Character gesture studies

Turn character artwork into a focused gesture study, such as a head turn or a small pose change. Use the result to judge movement and visual consistency.

### Atmospheric scene shots

Add motion to clouds, water, light, or fabric in an established scene. Keep the action narrow so the atmosphere supports the composition.

### Camera movement previews

Use scene images to explore a slow push-in, pan, or reveal before planning a larger animation. Compare how each camera direction draws attention to the subject.

### Concept art in motion

Use illustrated environments or rendered scenes to test depth, subject movement, and mood. Share the motion draft when a still image leaves the intended action unclear.

### Social post openers

Develop a brief moving opener from campaign imagery. Test whether the movement gives the visual a clear focal point and enough rhythm for the intended post.

### Recurring character shots

Reuse character references while generating separate scenes. Compare appearance across the resulting shots before assembling a sequence.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Gemini guides](https://spiral.ai/integrations/gemini)

## Vidu Reference to Video in other agents

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

## More Gemini guides

- [Vidu Q4 Reference to Video](https://spiral.ai/integrations/gemini/vidu-q4-reference-to-video)
- [Vidu Start-End to Video](https://spiral.ai/integrations/gemini/vidu-start-end-to-video)
- [Vidu Q4 Image to Video](https://spiral.ai/integrations/gemini/vidu-q4-image-to-video)
- [Vidu Template to Video](https://spiral.ai/integrations/gemini/vidu-template-to-video)
- [Vidu Q3 Turbo Text to Video](https://spiral.ai/integrations/gemini/vidu-q3-turbo-text-to-video)
- [Vizard AI Clip v1](https://spiral.ai/integrations/gemini/vizard-ai-clip-v1)

## Questions about Vidu Reference to Video in Gemini

**Can Gemini use Vidu Reference to Video?**

Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Vidu Reference to Video like any built-in tool.

**How much does Vidu Reference to Video cost in Gemini?**

$0.52 per run at the default inputs. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.

**Do I need a fal account to use Vidu Reference to Video in Gemini?**

No. Spiral runs Vidu Reference 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 Vidu Reference to Video in Gemini?**

About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.

**Does Gemini wait while Vidu Reference to Video runs?**

Vidu Reference to Video runs in the background. Gemini starts the run, checks on it and gives you the video when it's ready.

**What is Vidu useful for?**

Use Vidu to turn visual concepts into short motion drafts: product reveals, character actions, camera moves, and atmospheric scenes. These are practical ways to test a shot before committing to a longer edit.

**How should I write a Vidu prompt?**

Describe one main action, the camera movement, and the details that should stay stable. For example: a ceramic cup stays still while steam rises and the camera slowly moves closer.

**What source images work best with Vidu?**

Choose clear subjects and readable compositions. Blurry, crowded, or heavily cropped images can produce less stable motion.

**Can Vidu animate illustrations and concept art?**

Yes. Illustrations, character artwork, posters, and concept art can serve as source visuals for motion drafts. Start with artwork that already establishes the look you want to preserve.

**How can I make Vidu results less erratic?**

Start with one motion type and a simple prompt, then review the result before adding complexity. Check that faces, object edges, and poses remain recognizable throughout the shot.

