How to Use Grok Imagine Image in OpenClaw
Grok Imagine Image turns written briefs into illustrations, editorial images, and game concepts. Unlike Grok Imagine Image Edit, it starts from text alone, making it useful when you have an idea but no source artwork.
Prompts to try with Grok Imagine Image in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Every Monday, use Grok Imagine Image to create one wide 16:9 illustration at 1K for the week's gardening theme. Show one practical activity in a small urban garden, use soft daylight and a flat illustrated finish, and leave the upper left clear for copy.
Each Friday, use Grok Imagine Image to create a square 1K concept for a weekend reading post. Show one reader in a different quiet setting each week, with simple shapes, warm directional light, and no lettering. Collect the result for review.
At the start of each month, use Grok Imagine Image to create a vertical 9:16 illustration at 2K for the seasonal cycling campaign. Show a cyclist preparing a bicycle in weather appropriate to the month, with open space above for campaign copy.
Every Monday at 9am: generate a product photo with Grok Imagine Image: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first.
Make four logo concepts for a coffee brand called "Northline" with Grok Imagine Image.
How to set up Grok Imagine Image in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- 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
- 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
- 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
- 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
- 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
- Create an API key
In the console, under API keys.
- Run Grok Imagine 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": "xai/grok-imagine-image", "input": { "prompt": "Abstract human silhouette, golden particles ready to burst outward representing joy, data visualization style, emotional expression through particles, artistic…" } }'
Then paste one of the prompts above: OpenClaw finds Grok Imagine Image on Spiral, shows the price and runs it.
Grok Imagine Image providers and prices
Spiral runs Grok Imagine Image through fal. Open a card for today's price, with every fee included.
resolution: 1k (default) $0.026, 2k $0.026 per image. Billed on num_images, default 1.
Settings you can ask for
Grok Imagine Image works from your prompt. Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Image passthrough | on or off | off | Send edit references and return provider images without resizing or re-encoding, preserving transparency and metadata. The returned native format may differ from output_format. |
| Number of images | 1 to 4 | 1 | Number of images to generate. |
| Aspect ratio | 2:1, 20:9, 19.5:9, 16:9, 4:3, 3:2, 1:1, 2:3 and 5 more | 1:1 | Aspect ratio of the generated image. |
| Resolution | 1k or 2k | 1k | Resolution of the generated image. |
| Output format | jpeg, png, or webp | jpeg | The format of the generated image. |
Every API field of Grok Imagine Image · Text to Image is on its tool page: open its card above.
What can you do with Grok Imagine Image in OpenClaw?
Prepare recurring still artwork for an editorial calendar or campaign. Give the agent a stable visual brief and have it collect the results for review before publication.
Website illustrations
Develop an illustration for a feature page, with a clear focal subject and space reserved for the heading. Create new artwork from a brief or revise an existing illustration.
Editorial artwork
Illustrate an article's central idea with a single readable scene. Specify the setting, viewpoint, and lighting, or adapt existing artwork to the article's subject.
Game environment concepts
Explore a harbor, workshop, or research station before committing to production art. Use a written scene brief or develop an existing environment concept.
Social campaign artwork
Develop still illustrations around a campaign theme. Define the subject and composition, and leave room for final campaign copy to be added during design.
Character concepts from a brief
Turn a character description into concept art without a reference image. Describe clothing, posture, held objects, and the setting in complete sentences.
Early visual direction
Create initial artwork for an idea that exists only in writing. Compare different compositions or lighting directions before selecting a look.
More on Grok Imagine Image and OpenClaw
Overview
Grok Imagine Image in other agents
Questions about Grok Imagine Image in OpenClaw
Can OpenClaw use Grok Imagine Image?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Grok Imagine Image like any built-in tool.
How much does Grok Imagine Image cost in OpenClaw?
`resolution`: 1k (default) $0.026, 2k $0.026 per image. Billed on `num_images`, default 1. 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 Grok Imagine Image in OpenClaw?
No. Spiral runs Grok Imagine 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 Grok Imagine Image in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Grok Imagine Image runs?
Grok Imagine Image runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.
What is Grok Imagine Image useful for?
Try it for illustrations, editorial artwork, and game concepts. Layer's comparison describes its output as cleaner, flatter, and more cartoon-like than Grok Imagine Image 2.0, making stylized briefs a useful starting point.
What is the largest output resolution?
Grok Imagine Image supports output up to 2K. Use 1K to explore a composition, then request 2K for the selected direction.
How should I write a Grok Imagine Image prompt?
Describe the subject, setting, composition, lighting, and visual finish in full sentences. For example, specify an overhead view and soft light from the left instead of asking for a good-looking image.
What needs extra review?
Review photorealistic details and any lettering before using the result. Fal positions Grok Imagine Image (Quality) as offering higher fidelity for photorealism and text rendering, so allow room for revisions on those tasks.
Does Grok Imagine Image make video?
No. Grok Imagine Image produces still images; write the brief around one composition rather than a sequence of actions.
Start using Grok Imagine Image in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


