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

Codex · Image

How to Use Qwen Image Edit Inpaint in Codex

Use Qwen Image Edit Inpaint for a repair or replacement within a masked area. Unlike Qwen Image Edit Image to Image, it uses a supplied mask to target the edit.

Prompts to try with Qwen Image Edit Inpaint in Codex

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

Use Qwen Image Edit Inpaint with the project photo and its supplied mask. Remove the cable inside the marked area and continue the tabletop texture through the repair. Save the result beside the original for inspection.

Qwen Image Edit InpaintCodex
Try asking
  • Remove the background from the photo I attach with Qwen Image Edit Inpaint and give me a transparent PNG. Save the result in ./assets.

  • Use Qwen Image Edit Inpaint to clean up these product shots so they sit on pure white.

  • Edit this image with Qwen Image Edit Inpaint: keep the subject, swap the background for a sunlit studio.

  • Use Qwen Image Edit Inpaint to turn this daytime photo into a dusk scene with warm window light.

How to set up Qwen Image Edit Inpaint 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 Qwen Image Edit Inpaint

    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/qwen-image-edit/inpaint",
        "input": {
          "prompt": "Change the ball to a black and white football",
          "image_url": "https://storage.googleapis.com/falserverless/example_inputs/image_kontext_inpaint.jpeg",
          "mask_url": "https://storage.googleapis.com/falserverless/example_inputs/mask_kontext_inpaint.png"
        }
      }'

Then paste one of the prompts above: Codex finds Qwen Image Edit Inpaint on Spiral, shows the price and runs it.

Qwen Image Edit Inpaint providers and prices

Spiral runs Qwen Image Edit Inpaint through fal. Open a card for today's price, with every fee included.

falImage
Qwen Image Edit
fal-ai/qwen-image-edit/inpaint

Settings you can ask for

Qwen Image Edit Inpaint works from your prompt, image URL, and mask URL. Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Number of inference steps2 to 5030

The number of inference steps to perform.

Seeda whole number

The same seed and the same prompt given to the same version of the model

will output the same image every time.

Guidance scale0 to 204

The CFG (Classifier Free Guidance) scale is a measure of how close you want

the model to stick to your prompt when looking for a related image to show you.

Number of images1 to 41

The number of images to generate.

Output formatjpeg or pngpng

The format of the generated image.

Negative promptwhat to leave out, in words

The negative prompt for the generation

Accelerationnone, regular, or highregular

Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.

Strength0.01 to 10.93

Strength of noising process for inpainting

Every API field of Qwen Image Edit is on its tool page: open its card above.

What can you do with Qwen Image Edit Inpaint in Codex?

Turn existing project images into revised artwork for pages, documentation, and demos. A coding agent can prepare a specific edit, save the result beside the original, and show both for review.

Correct poster headlines

Replace a misspelled English headline or Chinese phrase in an existing poster. Specify the exact replacement and inspect every character before using the result.

Preview product colors

Recolor a product in an existing photograph to compare design choices. Ask to retain its shape, label, camera angle, and surrounding scene.

Remove small distractions

Remove a stray object or unwanted detail from a photograph. Use a mask with Qwen Image Edit Inpaint to identify the repair area.

Revise portrait clothing

Change a jacket’s color or replace an outfit in a supplied portrait. State that the person’s face, pose, and background should remain consistent.

Replace a photo background

Move an existing subject into a different setting by editing the background. For Qwen Image Edit Inpaint, mask the background around the subject.

Questions about Qwen Image Edit Inpaint in Codex

Can Codex use Qwen Image Edit Inpaint?

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

How much does Qwen Image Edit Inpaint cost in Codex?

Up to $0.039 per run at the default inputs. $0.039 per unit of `num_images`. 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 Qwen Image Edit Inpaint in Codex?

No. Spiral runs Qwen Image Edit Inpaint on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Qwen Image Edit Inpaint in Codex?

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

Does Codex wait while Qwen Image Edit Inpaint runs?

Qwen Image Edit Inpaint runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

What is Qwen Image Edit useful for?

Use it to revise an existing image: correct a poster headline, recolor an object, remove a distraction, change clothing, or replace a background. Give the edit a clear target and describe the result you want.

Can Qwen Image Edit change text inside a picture?

Yes. Qwen documents Chinese and English text editing, including replacing words while retaining their font, size, and style. Specify the exact old text and replacement text, then check the result letter by letter.

Will everything outside my requested edit stay identical?

Treat preservation as a goal to check. Qwen distinguishes local appearance edits from broader semantic edits, such as restyling, which can change pixels throughout the image while retaining the subject.

How should I phrase an editing prompt?

Name the target, describe one concrete change, and state what should stay: “Change the jacket to dark green; preserve the face, pose, lighting, and background.” For text, include the exact replacement wording.

Why might a Chinese character still look wrong?

Qwen’s own example shows an obscure character failing to correct in one pass. Mark the incorrect part and repair that smaller detail in a follow-up edit.

Get started

Start using Qwen Image Edit Inpaint 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