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

OpenClaw · Image

How to Use Bria Expand in OpenClaw

Bria Expand adds generated content around an existing image for banners, product listings, and social posts. It extends the scene to fit a new layout, giving you room around the subject without cropping away important details.

Prompts to try with Bria Expand in OpenClaw

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

Every Monday, use Bria Expand on newly approved campaign photos to create 1:1 and 4:5 compositions. Match each photo's existing surroundings and collect the results for review.

Bria ExpandOpenClaw
Try asking
  • Each morning, use Bria Expand to prepare square compositions from new product photos. Keep the main subject above 15% of the final image area.

  • Each Friday, use Bria Expand to make 16:9 banners from this week's approved lifestyle photos. Continue the existing scene and match its light and texture.

  • When a new campaign photo is approved, use Bria Expand to prepare a composition with open space on the left for text. Use manual placement and collect the result for review.

  • Every Tuesday, use Bria Expand to create 9:16 compositions from newly approved landscape photos. Leave the expansion description empty and collect the results for review.

How to set up Bria Expand in OpenClaw

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

Use the Spiral skill

  1. Send OpenClaw 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 Spiral's MCP server

  1. Add the server

    On the machine that runs OpenClaw's Gateway:

    openclaw mcp add spiral \
      --url https://api.spiral.ai/mcp \
      --transport streamable-http \
      --auth oauth
  2. Sign in

    In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

    openclaw mcp login spiral
  3. Reload and check

    A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

    openclaw mcp reload
    openclaw mcp doctor spiral --probe

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 Bria Expand

    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/bria/expand",
        "input": {
          "image_url": "https://storage.googleapis.com/falserverless/model_tests/orange.png",
          "canvas_size": [
            1
          ]
        }
      }'

Then paste one of the prompts above: OpenClaw finds Bria Expand on Spiral, shows the price and runs it.

Bria Expand providers and prices

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

falImage
Bria Expand Image
fal-ai/bria/expand

Settings you can ask for

Bria Expand works from your image URL and prompt. Ask OpenClaw for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Aspect ratio1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16 and 1 more

The desired aspect ratio of the final image. Will be used over original_image_size and original_image_location if provided.

Seed0 to 2147483647

You can choose whether you want your generated expension to be random or predictable. You can recreate the same result in the future by using the seed value of a result from the response. You can exclude this parameter if you are not interested in recreating your results. This parameter is optional.

Negative promptwhat to leave out, in words

The negative prompt you would like to use to generate images.

Every API field of Bria Expand Image is on its tool page: open its card above.

What can you do with Bria Expand in OpenClaw?

Prepare recurring sets of image compositions from newly approved photos. A scheduled agent can apply a consistent visual brief and collect the expanded images for review.

Website hero images

Expand an existing campaign photo into a wide composition with room beside the subject for a headline.

Vertical social posts

Extend a landscape photo above and below for a vertical post, keeping the main subject prominent.

Product listing images

Add surrounding space to a tightly framed product photo so it fits a square listing layout.

Display ad layouts

Adapt an existing advertising image to wide and portrait placements by generating more of the surrounding scene.

Text space for promotions

Position the source photo to one side and extend a quiet background where promotional copy can be added.

Campaign image sets

Turn one approved source photo into square, portrait, and landscape compositions for different campaign placements.

Questions about Bria Expand in OpenClaw

Can OpenClaw use Bria Expand?

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Bria Expand like any built-in tool.

How much does Bria Expand cost in OpenClaw?

$0.052 per generation. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

Do I need a fal account to use Bria Expand in OpenClaw?

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

How long does it take to set up Bria Expand in OpenClaw?

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

Does OpenClaw wait while Bria Expand runs?

Bria Expand runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

What does Bria Expand do?

It generates content beyond the borders of an existing image. Use it to adapt a photo to a wider or taller layout while retaining important content in the original frame.

How large can the output be?

Bria documents a maximum canvas area of 25 million pixels. Check width multiplied by height when planning an expansion.

What makes an expansion harder?

A very small subject on a large canvas falls outside Bria's recommended composition. For best results, keep the foreground or main subject above 15% of the total canvas area.

Which prompt languages does Bria Expand support?

Use English without special characters. Bria documents English as the only supported prompt language.

Do I need to write a prompt?

No. If you leave it blank, Bria Expand generates a prompt from the source image.

Get started

Start using Bria Expand in OpenClaw

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

Paste this into OpenClaw:

Set up OpenClaw

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