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

Codex · Image

How to Use NAFNet Deblur in Codex

NAFNet Deblur restores blurry photos while keeping their original dimensions. Unlike NAFNet-denoise, it targets motion blur and focus issues rather than sensor noise and grain.

Prompts to try with NAFNet Deblur in Codex

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

Use NAFNet Deblur on the blurry product photos in this project's assets folder. Save separate restored copies and build a local comparison page with matching crops.

NAFNet DeblurCodex
Try asking
  • Use NAFNet Deblur on the homepage photograph. Show the original and restored copy at the page's actual display size before changing the asset reference.

  • Use NAFNet Deblur on three event photos from this project's media folder. Make a contact sheet pairing each original with its restored result.

  • Use NAFNet Deblur on the selected travel photo in the repository. Compare building edges at equal zoom and leave the choice of final image to me.

  • Use NAFNet Deblur on a sample of the blurry editorial photos in this project. Preserve the originals and prepare a review page before processing the rest.

How to set up NAFNet Deblur 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 NAFNet Deblur

    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/nafnet/deblur",
        "input": {
          "image_url": "https://storage.googleapis.com/falserverless/nafnet/blurry.png"
        }
      }'

Then paste one of the prompts above: Codex finds NAFNet Deblur on Spiral, shows the price and runs it.

NAFNet Deblur providers and prices

Spiral runs NAFNet Deblur through fal. Open a card for today's price, with every fee included.

falImage

Settings you can ask for

NAFNet Deblur works from your image URL. Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number

seed to be used for generation

Every API field of NAFNet-deblur · Image to Image is on its tool page: open its card above.

What can you do with NAFNet Deblur in Codex?

Restore blurry project photographs and compare candidates before updating site assets. A coding agent can organize originals, build a comparison view, and help you review the results.

Product photo review

Try deblurring a product shot affected by camera movement. Compare edges and surface details before selecting it for a listing.

Event photo selection

Restore candidate event photos with motion blur, then review each result beside the original when choosing images for a recap.

Travel photo restoration

Try restoring a handheld travel photo with blurred building edges. Inspect matching crops before adding the result to an album.

Editorial image preparation

Create a restored candidate from a blurry article photo. Keep the original alongside it for editorial review.

Website asset cleanup

Test blurry photographs intended for a website. Review the restored images at their intended display size before replacing assets.

Photo archive review

Make restored copies of blurry archive photographs. Compare them with the originals and retain only the results you prefer.

Questions about NAFNet Deblur in Codex

Can Codex use NAFNet Deblur?

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

How much does NAFNet Deblur cost in Codex?

Up to $0.02925 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 Codex plan is separate.

Do I need a fal account to use NAFNet Deblur in Codex?

No. Spiral runs NAFNet Deblur on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up NAFNet Deblur in Codex?

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

Does Codex wait while NAFNet Deblur runs?

NAFNet Deblur runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

What kinds of blur does NAFNet Deblur address?

It targets motion blur and focus issues in existing photos. Try it on a blurry shot, then compare the restored image with the original before choosing it.

Does NAFNet Deblur upscale the image?

No. The output keeps the original dimensions, so a sharper result does not contain more pixels.

How should I prompt an agent to use NAFNet Deblur?

Identify the photo to restore and explain how you want to review the result. For example, ask for matching before-and-after crops of the subject rather than a description of a new scene.

How does NAFNet Deblur differ from NAFNet-denoise?

NAFNet Deblur targets blur and focus issues. NAFNet-denoise addresses sensor noise and grain, so choose according to the problem visible in the photo.

Will NAFNet Deblur recover every blurry photo?

The published benchmark results do not establish that. Treat each restoration as a candidate and inspect the details that matter before using it.

Get started

Start using NAFNet Deblur 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