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

Codex · Image

How to Use Krea 3 Text to Image in Codex

Krea 3 Text to Image creates images from written briefs, including photographic concepts with specific lighting and materials. Unlike Krea 3 Edit, it starts from text alone rather than an existing image.

Prompts to try with Krea 3 Text to Image in Codex

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

Read the homepage brief in this project and use Krea 3 Text to Image to create a 1536 × 1024 editorial photograph for it. Specify a concrete subject and light source, leave the right third clear for HTML copy, and save the result in the image assets directory.

Krea 3 Text to ImageCodex
Try asking
  • Use Krea 3 Text to Image to create a 2048 × 2048 ink illustration for the gardening article in this project. Show hands planting a seedling, use black ink on white, and keep all article text outside the image.

  • Review this project's campaign brief and use Krea 3 Text to Image to draft a 1536 × 1024 studio photograph of a ceramic cup on linen. Use morning window light from the left and a softly blurred background.

  • Generate a product photo with Krea 3 Text to Image: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.

  • Make four logo concepts for a coffee brand called "Northline" with Krea 3 Text to Image.

How to set up Krea 3 Text 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 Krea 3 Text 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": "krea/v3/text-to-image",
        "input": {
          "prompt": "A red fox curled up asleep in fresh snow at dawn, soft pink light on the pine trees behind it"
        }
      }'

Then paste one of the prompts above: Codex finds Krea 3 Text to Image on Spiral, shows the price and runs it.

Krea 3 Text to Image providers and prices

Spiral runs Krea 3 Text to Image through fal. Open a card for today's price, with every fee included.

falImage
Krea 3 Text to Image
krea/v3/text-to-image

Settings you can ask for

Krea 3 Text to Image works from your prompt. Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Modelberry or jamberry

Model variant: berry favors quality, jam favors speed.

Reasoning levellow or mediummedium

How much effort the harness spends reasoning about the given prompt. Higher reasoning effort means slower generation time. Both levels bill $0.025 per output megapixel.

Negative promptwhat to leave out, in words

What to keep out of the image. Used by berry only.

Seeda whole number

Latent noise seed. Use a new seed when editing a previous output again.

Output formatpng or jpegpng

Output image format.

Every API field of Krea 3 Text to Image is on its tool page: open its card above.

What can you do with Krea 3 Text to Image in Codex?

Turn project design briefs into images for pages, documentation, and presentations with Krea 3. Use the project's visual requirements to specify composition, materials, lighting, and the details each result must retain.

Editorial photography concepts

Use Krea 3 Text to Image to explore an article image with a defined subject, camera view, and light source. Leave room for the publication's headline instead of generating a page of copy.

Product campaign concepts

Use Krea 3 Text to Image to draft a product scene before a shoot, such as glazed ceramics on linen or a bottle against hard afternoon shadows.

Interior mood studies

Use Krea 3 Text to Image to explore a room described through materials, furniture placement, daylight, and camera position before choosing a design direction.

Illustrated publishing assets

Use Krea 3 Text to Image to draft an ink drawing or painted illustration for an article, presentation, or campaign.

Questions about Krea 3 Text to Image in Codex

Can Codex use Krea 3 Text to Image?

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Krea 3 Text to Image like any built-in tool.

How much does Krea 3 Text to Image cost in Codex?

$0.130975 per megapixel. 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 Krea 3 Text to Image in Codex?

No. Spiral runs Krea 3 Text 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 Krea 3 Text to Image in Codex?

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

Does Codex wait while Krea 3 Text to Image runs?

Krea 3 Text to Image runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

How should I describe a photographic result?

Specify the scene, the light source, and the camera view. For example, describe a ceramic cup on linen, morning light from the left, and a close view with a softly blurred background.

What output size can I request?

The listed Krea 3 endpoints support up to 4,220,160 pixels. Dimensions are rounded up to multiples of 16, so 2048 × 2048 fits within the limit.

Can I rely on Krea 3 for dense text layouts?

Krea identifies extremely dense small text as a remaining weakness. Use larger, shorter text in the image, and add detailed copy separately when accuracy matters.

Does using the same seed reproduce the same image?

It does not guarantee an identical result. Krea says prompt expansion can vary between runs even when the seed stays the same.

When should I increase reasoning effort?

Try more reasoning when a detailed brief needs additional planning. It takes longer, so compare the result with your usual setting before making it your default.

Get started

Start using Krea 3 Text 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