How to Use Vidu Reference to Image in ChatGPT
Vidu Reference to Image turns reference photos and a written brief into still images with consistent subjects. Use it to compose product scenes, place characters together, or edit objects in an existing picture.
Prompts to try with Vidu Reference to Image in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Vidu Reference to Image with these product and kitchen pictures. Create a wide image of the product on the counter near the window, with soft daylight and the product's shape and color preserved.
Use Vidu Reference to Image to put the two characters in these reference pictures at the same café table. Make a square image, place one character on each side, and preserve their faces and outfits.
Use Vidu Reference to Image to change the coat in this portrait from red to dark green. Preserve the person's face, pose, and background.
Use Vidu Reference to Image with this living room picture and sofa reference. Replace the existing sofa with the referenced sofa in the same position, preserving the windows and other furniture.
Use Vidu Reference to Image with these portrait and backpack pictures. Create a vertical image of the person wearing the backpack on a woodland path, with natural daylight and the backpack's visible details preserved.
How to set up Vidu Reference to Image in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- 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
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- 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
- Send ChatGPT 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 Reference to Image
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-image", "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 Image on Spiral, shows the price and runs it.
Vidu Reference to Image providers and prices
Spiral runs Vidu Reference to Image through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Vidu Reference to Image works from your prompt and reference image URLs. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Aspect ratio | 16:9, 9:16, or 1:1 | 16:9 | The aspect ratio of the output video |
| Seed | a whole number | Random seed for generation |
Every API field of Vidu is on its tool page: open its card above.
What can you do with Vidu Reference to Image in ChatGPT?
Turn reference pictures into product scenes, character compositions, and photo edits through a conversation. Describe what the finished image should show and which details should carry over from the references.
Product lifestyle scenes
Combine a product reference with a setting reference to draft a lifestyle image. Describe the product's placement, lighting, and details to preserve.
Character scenes for storyboards
Use character references to draft individual storyboard images. Specify each character's position, expression, and relationship to the scene.
Campaign composition tests
Reuse the same product and person references across different compositions. Compare a close product view, a person holding it, and a wider environmental scene.
Interior design concepts
Start with a room photo and a furniture reference to explore a replacement piece. Describe its position and the room details that should remain.
Wardrobe color studies
Use an existing portrait to explore changes to an outfit's color. State which garment should change and which facial and background details to preserve.
Prop replacements
Replace an object in a source photo using a separate prop reference. Describe the intended scale, placement, and interaction with the person holding it.
Creator thumbnail drafts
Combine a portrait and an object reference into a thumbnail concept. Specify the expression, subject placement, and empty space for a headline added later.
More on Vidu Reference to Image and ChatGPT
Overview
Vidu Reference to Image in other agents
Questions about Vidu Reference to Image in ChatGPT
Can ChatGPT use Vidu Reference to Image?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Vidu Reference to Image like any built-in tool.
How much does Vidu Reference to Image cost in ChatGPT?
$0.065 per image. 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 Image in ChatGPT?
No. Spiral runs Vidu Reference to Image 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 Image 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 Image runs?
Vidu Reference to Image runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is Vidu Reference to Image useful for?
Use it when an existing person, character, or product needs to appear in a newly composed still image. Reference images guide appearance, while your prompt describes the result.
Can Vidu Reference to Image combine several pictures?
Yes. The original reference-to-image model supports one to seven reference images, allowing you to bring separately photographed subjects into one composition.
How should I write a Vidu Reference to Image prompt?
Describe the scene, style, composition, and details to preserve. Keep the generation prompt within 1,500 characters, and make each reference's intended role clear.
Can Vidu Reference to Image change an existing photo?
Yes. Its editing capabilities include adding objects, replacing objects, changing part of an object's appearance, and combining multiple images.
Does Vidu Reference to Image animate the references?
It produces a still image. Use it for the composition or edited picture you want to create.
Start using Vidu Reference to Image in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


