How to Use Vidu Q2 Reference to Image in ChatGPT
Use Vidu Q2 Reference to Image to create new scenes around an existing character or product. It combines visual references with written direction to change the setting, style, or composition while keeping the subject recognizable.
Prompts to try with Vidu Q2 Reference to Image in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Vidu Q2 Reference to Image with the attached mug photo to create a square image on a wooden breakfast table. Keep the mug's shape, handle, and glaze color, with soft window light.
Use Vidu Q2 Reference to Image with the attached character image to create a wide bookstore scene. Preserve the face, hairstyle, and coat, and show the character browsing a shelf.
Use Vidu Q2 Reference to Image with these two images. Use the first for the product's appearance and the second for composition; create a studio image with a pale gray background.
Use Vidu Q2 Reference to Image to reinterpret the attached illustration in watercolor. Keep the subject placement and recognizable clothing, with a restrained green and brown palette.
Use Vidu Q2 Reference to Image with the attached mascot to draft a tall poster image. Keep the mascot recognizable, place it near the bottom, and leave the upper area clear for text I will add later.
How to set up Vidu Q2 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 Q2 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/q2/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 Q2 Reference to Image on Spiral, shows the price and runs it.
Vidu Q2 Reference to Image providers and prices
Spiral runs Vidu Q2 Reference to Image through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Vidu Q2 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 Q2 Reference to Image in ChatGPT?
Turn shared visual references into product scenes, character images, and illustration studies. Describe the changes in ordinary language and ask Vidu Q2 Reference to Image to preserve the details that matter.
Product background concepts
Use an existing product image to explore a kitchen counter, studio table, or outdoor setting. Specify the product shape and details that should stay recognizable.
Character scene drafts
Place a reference character in different story settings while asking to retain the face, hairstyle, outfit, and silhouette.
Campaign image studies
Start with an approved visual and explore seasonal settings, lighting, and mood for a campaign review.
Illustration style exploration
Use existing artwork to test a different rendering style while preserving selected subject and composition details.
Thumbnail concepts
Turn a character or product reference into a thumbnail draft with deliberate subject placement and space for a title added during editing.
Video reference preparation
Create a still character reference with explicit clothing, facial details, lighting, and framing for review before video production.
Brand composition reviews
Combine subject and composition references into a concrete image draft that stakeholders can review for visual direction.
More on Vidu Q2 Reference to Image and ChatGPT
Overview
Vidu Q2 Reference to Image in other agents
Questions about Vidu Q2 Reference to Image in ChatGPT
Can ChatGPT use Vidu Q2 Reference to Image?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Vidu Q2 Reference to Image like any built-in tool.
How much does Vidu Q2 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 Q2 Reference to Image in ChatGPT?
No. Spiral runs Vidu Q2 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 Q2 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 Q2 Reference to Image runs?
Vidu Q2 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 Q2 Reference to Image best for?
Use it when a recognizable character, product, or visual direction already exists. It suits new scene drafts, changes in style, and composition studies guided by those references.
Can Vidu Q2 Reference to Image keep the same character or product?
Consistent subject appearance is a documented purpose. State which features must stay, then compare the result with the reference before approving it.
How many reference images can Vidu Q2 use?
Vidu documents up to seven references for Q2 image generation. Give each image a clear role, such as character identity, product details, or composition.
How should I prompt Vidu Q2 Reference to Image?
Describe the scene, style, composition, and details that must remain recognizable. Separate the requested changes from the details you want preserved.
How long can a Vidu Q2 Reference to Image prompt be?
Keep the prompt within 1,500 characters for this endpoint. Prioritize the subject, the requested change, and the details that must stay.
Start using Vidu Q2 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


