Spiral gives your agent every tool with one account. Browse the tools →

ChatGPT · Video

How to Use Vidu Reference to Video in ChatGPT

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.

Prompts to try with Vidu Reference to Video in ChatGPT

Copy an example into ChatGPT, or ask in your own words.

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.

Vidu Reference to VideoChatGPT
Try asking
  • 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 ChatGPT

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

Use the ChatGPT connector

  1. Add a custom MCP server

    In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

    https://api.spiral.ai/mcp
  2. Click Connect

    ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

  3. Sign in to Spiral and approve

    Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

Use the Spiral skill

  1. Send ChatGPT 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.

    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.

    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: ChatGPT finds Vidu Reference to Video on Spiral, shows the price and runs it.

Vidu Reference to Video providers and prices

Spiral runs Vidu Reference to Video through fal. Open a card for today's price, with every fee included.

falVideo
Vidu Reference to Video · Reference-to-Video
fal-ai/vidu/reference-to-video

Settings you can ask for

Vidu Reference to Video works from your prompt and reference image URLs. Ask ChatGPT for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number

Random seed for generation

Aspect ratio16:9, 9:16, or 1:116:9

The aspect ratio of the output video

Movement amplitudeauto, small, medium, or largeauto

The movement amplitude of objects in the frame

Every API field of Vidu Reference to Video · Reference-to-Video is on its tool page: open its card above.

What can you do with Vidu Reference to Video in ChatGPT?

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.

Questions about Vidu Reference to Video in ChatGPT

Can ChatGPT use Vidu Reference to Video?

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

How much does Vidu Reference to Video cost in ChatGPT?

$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 ChatGPT plan is separate.

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

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 ChatGPT?

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

Does ChatGPT wait while Vidu Reference to Video runs?

Vidu Reference to Video runs in the background. ChatGPT 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.

Get started

Start using Vidu Reference to Video in ChatGPT

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into ChatGPT:

Set up ChatGPT

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options