How to Use Vidu Q1 Reference to Video in Cursor
Combine characters, props, or locations from up to seven reference images in a five-second, 1080p scene. Choose this mode for subject consistency when your references do not need to become the opening frame.
Prompts to try with Vidu Q1 Reference to Video in Cursor
Copy an example into Cursor, or ask in your own words.
Use Vidu Q1 Reference to Video with the project's mascot, prop, and background images. Create a five-second shot of the mascot standing beside the prop in that location, with a slight head turn.
Estimate, then generate a 5-second 9:16 clip with Vidu Q1 Reference to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
Make a 10-second product teaser with Vidu Q1 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 Q1 Reference to Video and list what each cost.
Make a 6-second 16:9 drone shot over a misty pine forest at sunrise with Vidu Q1 Reference to Video.
How to set up Vidu Q1 Reference to Video in Cursor
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to Cursor on the console's Agents & MCP page, or add this to .cursor/mcp.json (one project) or ~/.cursor/mcp.json (every project):
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.
Use the Spiral skill
- Send Cursor this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Vidu Q1 Reference to Video
One request; the result comes back by polling or a webhook.
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/q1/reference-to-video", "input": { "prompt": "A young woman and a monkey inside a colorful house", "reference_image_urls": [ "<reference_image_urls>" ] } }'
Then paste one of the prompts above: Cursor finds Vidu Q1 Reference to Video on Spiral, shows the price and runs it.
Vidu Q1 Reference to Video providers and prices
Spiral runs Vidu Q1 Reference to Video through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Vidu Q1 Reference to Video works from your prompt and reference image URLs. Ask Cursor for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | Random seed for generation | |
| Aspect ratio | 16:9, 9:16, or 1:1 | 16:9 | The aspect ratio of the output video |
| Movement amplitude | auto, small, medium, or large | auto | The movement amplitude of objects in the frame |
| Bgm | on or off | off | Whether to add background music to the generated video |
Every API field of Vidu · Reference to Video is on its tool page: open its card above.
What can you do with Vidu Q1 Reference to Video in Cursor?
Turn project artwork into short motion assets and test scenes against an existing storyboard. A coding agent can use the repository's images and creative brief to prepare individual five-second shots.
Animate a finished illustration
Use image-to-video for a five-second character reaction: a glance, a smile, or a small change in posture.
Keep a mascot across several shots
Reuse a mascot reference in separate scenes, then review its face, clothing, and proportions before editing the clips together.
Connect two storyboard panels
Supply opening and closing artwork to start-end generation and describe the movement that should connect them.
Explore a scene before making assets
Use text-to-video to test a setting, lighting idea, and camera direction as a short visual concept.
Create short anime reactions
Build individual shots around facial expressions or upper-body movement, leaving demanding hand choreography for manual work.
Combine existing visual assets
Use reference-to-video to place a character, a prop, and a location from separate images into one short scene.
More on Vidu Q1 Reference to Video and Cursor
Overview
Vidu Q1 Reference to Video in other agents
Questions about Vidu Q1 Reference to Video in Cursor
Can Cursor use Vidu Q1 Reference to Video?
Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run Vidu Q1 Reference to Video like any built-in tool.
How much does Vidu Q1 Reference to Video cost in Cursor?
$0.52 per run. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Cursor plan is separate.
Do I need a fal account to use Vidu Q1 Reference to Video in Cursor?
No. Spiral runs Vidu Q1 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 Q1 Reference to Video in Cursor?
About two minutes: add the hosted server, then sign in.
Does Cursor wait while Vidu Q1 Reference to Video runs?
Vidu Q1 Reference to Video runs in the background. Cursor starts the run, checks on it and gives you the video when it's ready.
How long are Vidu Q1 videos, and what resolution do they use?
The Q1 modes covered here make five-second clips at 1080p. Plan longer sequences as separate shots that you edit together.
Which Q1 mode should I choose?
Use image-to-video when you have a finished opening image, start-end when you have both endpoint images, and reference-to-video when you want to combine recognizable subjects. Text-to-video is useful when you want to start from a written scene description.
Can Q1 keep a character recognizable across scenes?
Reference-to-video is designed to preserve subject appearance from supplied images. Reuse the same references across shots, and review each result before treating the sequence as finished.
What kinds of movement suit Q1?
Vidu's published Q1 creator guide recommends facial expressions and upper-body motion. It reports failures with fine hand gestures, full-body action, and complex camera moves, so start with a restrained shot.
How should I write a Q1 prompt?
Describe the subject, its action, the setting, and the camera behavior. For these routes, keep the prompt under 1,500 characters and build the shot around one clear action.
Start using Vidu Q1 Reference to Video in Cursor
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Cursor:
set up https://spiral.ai/SKILL.md


