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

opencode · Image

How to Use Luma Uni-1 Text to Image in opencode

Luma Uni-1 Text to Image creates new compositions from a written brief, with optional references for visual guidance. Unlike Luma Uni-1 Edit, it uses references as inspiration rather than preserving the source composition.

Prompts to try with Luma Uni-1 Text to Image in opencode

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

Use Luma Uni-1 Text to Image to create a 16:9 lead image for the homepage described in this repository. Show a ceramic mug on a wooden workbench, soft window light from the left, and open space on the right for the page heading.

Luma Uni-1 Text to Imageopencode
Try asking
  • Use Luma Uni-1 Text to Image to make one 16:9 image containing a three-panel storyboard for this project's welcome sequence. Show a person arriving, opening a package, and displaying the contents; keep the character consistent across panels.

  • Generate a product photo with Luma Uni-1 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 Luma Uni-1 Text to Image.

  • Create a 16:9 hero image of a quiet mountain cabin at dusk with Luma Uni-1 Text to Image.

How to set up Luma Uni-1 Text to Image in opencode

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

Use Spiral's MCP server

  1. Add the server

    Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

    opencode mcp add spiral --global --url https://api.spiral.ai/mcp
  2. Sign in

    Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.

    opencode mcp auth spiral
  3. Check it

    Spiral shows as connected.

    opencode mcp list

Use the Spiral skill

  1. Send opencode 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 Luma Uni-1 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": "luma/agent/uni-1/v1/text-to-image",
        "input": {
          "prompt": "A manga panel of a stoic samurai overlooking a neon cyberpunk city at dusk."
        }
      }'

Then paste one of the prompts above: opencode finds Luma Uni-1 Text to Image on Spiral, shows the price and runs it.

Luma Uni-1 Text to Image providers and prices

Spiral runs Luma Uni-1 Text to Image through fal. Open a card for today's price, with every fee included.

falImage
Luma Uni-1 Text to Image
luma/agent/uni-1/v1/text-to-image

Settings you can ask for

Luma Uni-1 Text to Image works from your prompt and reference image URLs. Ask opencode for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Aspect ratio3:1, 2:1, 16:9, 3:2, 1:1, 2:3, 9:16, 1:2 and 1 more

Aspect ratio of the generated image.

Styleauto or mangaauto

Visual style of the generated image.

Output formatpng or jpeg

Encoding format of the generated image.

Enable web searchon or offoff

When true, the model may consult the web for references.

Every API field of Luma Uni-1 Text to Image is on its tool page: open its card above.

What can you do with Luma Uni-1 Text to Image in opencode?

Turn a project's visual brief into images for a website, product campaign, or storyboard. A coding agent can use project assets to guide a new composition or revise an existing image.

Product campaign images

Use product references to develop a new campaign composition, or revise an existing product shot. Keep the brief specific about the product, setting, and intended change.

Posters with short headlines

Create a poster or revise an existing layout with a brief headline in quotation marks. Keep the wording short enough to inspect easily before publication.

Storyboard development

Create a sequence of panels for a pitch, or revise an existing storyboard. Describe each panel separately and request consistent character appearance.

Website lead images

Develop a new image for the top of a website or refine an existing composition for the page. Max is useful when preparing the finished visual.

Book cover concepts

Explore a cover composition or revise a supplied cover image. Use a short quoted title and inspect the lettering before treating the image as finished.

Questions about Luma Uni-1 Text to Image in opencode

Can opencode use Luma Uni-1 Text to Image?

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Luma Uni-1 Text to Image like any built-in tool.

How much does Luma Uni-1 Text to Image cost in opencode?

$0.0039 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

Do I need a fal account to use Luma Uni-1 Text to Image in opencode?

No. Spiral runs Luma Uni-1 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 Luma Uni-1 Text to Image in opencode?

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

Does opencode wait while Luma Uni-1 Text to Image runs?

Luma Uni-1 Text to Image runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

What resolution does Luma Uni-1 produce?

Luma documents 2048-pixel, or 2K, output for Uni-1 and Uni-1 Max. Max improves output quality without increasing that documented resolution.

Can Luma Uni-1 put readable text in an image?

Yes. Put the exact wording in quotation marks and favor short headings or labels under 20 characters; long passages are less reliable.

Should I write Luma Uni-1 prompts in English?

English is the recommended choice. Luma says prompts in other languages produce less reliable results.

What does Max improve?

Uni-1 Max targets higher output quality with the same prompts and parameters. It is a useful choice when preparing a finished image or a detailed final revision.

Can Luma Uni-1 help with storyboards?

Yes. Describe the action in each panel and explicitly request the same character throughout; for revisions, identify the panels and details that should change.

Get started

Start using Luma Uni-1 Text to Image in opencode

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

Paste this into opencode:

Set up opencode

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