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

Codex · ImageReleased 2026-04-01

How to Use Wan 2.7 Image to Image in Codex

Wan 2.7 Image to Image changes an existing picture with written instructions, from a new background to a pencil drawing. Unlike Wan 2.7 Text to Image, it starts with a reference image.

Prompts to try with Wan 2.7 Image to Image in Codex

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

Use Wan 2.7 Image to Image to revise the product photo in this project's assets: replace the background with a matte gray tabletop, preserve the object's shape and label, and return one 1024 × 1024 image.

Wan 2.7 Image to ImageCodex
Try asking
  • Use Wan 2.7 Image to Image to update the date on the event poster in this project's assets to October 12. Preserve the illustration and all other wording; return one 2048 × 2048 image.

  • Remove the background from the photo I attach with Wan 2.7 Image to Image and give me a transparent PNG. Save the result in ./assets.

  • Use Wan 2.7 Image to Image to clean up these product shots so they sit on pure white.

  • Edit this image with Wan 2.7 Image to Image: keep the subject, swap the background for a sunlit studio.

How to set up Wan 2.7 Image to Image in Codex

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

Use Spiral's MCP server

  1. Add the hosted server
    codex mcp add spiral --url https://api.spiral.ai/mcp
  2. Sign in

    Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.

    codex mcp login spiral

Use the Spiral skill

  1. Send Codex 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 Wan 2.7 Image 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/wan/v2.7/edit",
        "input": {
          "prompt": "Turn image 1 into a watercolor painting.",
          "image_urls": [
            "<image_urls>"
          ]
        }
      }'

Then paste one of the prompts above: Codex finds Wan 2.7 Image to Image on Spiral, shows the price and runs it.

Wan 2.7 Image to Image providers and prices

Spiral runs Wan 2.7 Image to Image through fal. Open a card for today's price, with every fee included.

falImage
Wan 2.7 · Image to Image
fal-ai/wan/v2.7/edit

Settings you can ask for

Wan 2.7 Image to Image works from your prompt and image URLs. Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Negative promptwhat to leave out, in words

Content to avoid in the generated image. Max 500 characters.

Number of images1 to 41

Number of images to generate (1-4).

Enable prompt expansionon or offon

Enable DashScope prompt expansion. Supported only for image edit mode.

Seeda whole number

Random seed for reproducibility (0-2147483647).

Output formatjpeg, png, or webpjpeg

The format of the generated images.

Every API field of Wan 2.7 · Image to Image is on its tool page: open its card above.

What can you do with Wan 2.7 Image to Image in Codex?

Turn a project's visual requirements into images that fit its screens and content. Use Wan 2.7 Image for text-bearing graphics and detailed compositions, then inspect the results in the actual layout.

Product background revisions

Revise a supplied product photo with a different setting, lighting treatment, or surrounding props while asking to preserve the product's appearance.

Portrait style studies

Turn a supplied portrait into a pencil drawing or watercolor study, with explicit instructions about which facial features to preserve.

Poster text revisions

Update a headline or date in a supplied graphic while asking to keep its layout, illustration, and remaining wording.

Reference-based compositions

Combine elements from supplied images into a composition, identifying which image supplies each subject, background, or visual treatment.

Questions about Wan 2.7 Image to Image in Codex

Can Codex use Wan 2.7 Image to Image?

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Wan 2.7 Image to Image like any built-in tool.

How much does Wan 2.7 Image to Image cost in Codex?

$0.039 per image. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

Do I need a fal account to use Wan 2.7 Image to Image in Codex?

No. Spiral runs Wan 2.7 Image 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 Wan 2.7 Image to Image in Codex?

About two minutes: add the hosted server, then sign in.

Does Codex wait while Wan 2.7 Image to Image runs?

Wan 2.7 Image to Image runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

What is Wan 2.7 Image useful for?

Wan 2.7 Image is useful for posters, illustrated content, and visual work that combines readable text with a specified composition. Alibaba highlights text rendering, subject consistency, and complex instruction following.

Can Wan 2.7 Image put text inside a picture?

Yes. Text rendering is one of its documented strengths, making it useful for poster headlines, labels, and illustrated explainers. Give the exact wording and check the result before publishing.

Does Wan 2.7 Image support multilingual text?

Alibaba reports text rendering in 12 languages. For a localized graphic, supply the approved wording rather than asking the image model to translate it.

How should I describe the picture I want?

Specify the subject, setting, style, lighting, and composition. For example, describe a ceramic mug photographed from above on a wooden table in morning window light, rather than asking for a nice product picture.

Can Wan 2.7 Image make a 2048 × 2048 image?

Yes. A square image at 2048 × 2048 fits the documented 2K output limit shared across these models.

Get started

Start using Wan 2.7 Image to Image in Codex

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

Paste this into Codex:

Set up Codex

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