How to Use Boogu Image in Grok Build
Boogu Image creates posters, document layouts, photos, and illustrations from text, with support for Chinese and English lettering. Use detailed descriptions, and proofread dense text for missing characters or layout errors.
Prompts to try with Boogu Image in Grok Build
Copy an example into Grok Build, or ask in your own words.
Read the event brief in this project and use Boogu Image to make a 1024 × 1024 poster concept. Include only the event title as lettering, centered above a paper-cut illustration inspired by the brief.
Read the homepage copy and use Boogu Image to create a 1536 × 1024 editorial photo concept. Describe one scene that expresses the main idea, with natural window light and open space on the left.
Use the project's design notes to brief Boogu Image on a 1024 × 1024 brand guide concept. Show the approved palette and the short heading 'Color and type.' Keep the layout spacious.
Find the approved Chinese and English campaign headlines in the project. Use Boogu Image to make a 1024 × 1536 poster with those exact lines, Chinese above English, and a restrained ink illustration below.
Read the latest release notes and use Boogu Image to create a 1536 × 1024 illustrated announcement cover. Choose one visual metaphor for the main change, use a woodcut style, and leave lettering out.
How to set up Boogu Image in Grok Build
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Add --scope project to add Spiral to the current repository only. No header and no client ID or secret: Grok registers itself with Spiral.
grok mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start grok and run /mcps. Select Spiral and press i. Your browser opens: sign in to Spiral, pick the organization and click Authorize. No API key.
- Check it
grok mcp doctor spiral
Use the Spiral skill
- Send Grok Build 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 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 Boogu 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": "fal-ai/boogu-image", "input": { "prompt": "A street photography shot of an elderly scavenger with a deeply weathered face in the center of the frame, a trash can and a traffic light in the background.…" } }'
Then paste one of the prompts above: Grok Build finds Boogu Image on Spiral, shows the price and runs it.
Boogu Image providers and prices
Spiral runs Boogu Image through fal. Open a card for today's price, with every fee included.
$0.052 per megapixel. image_size presets count as 1 MP; custom sizes round up to whole megapixels. Billed on num_images, default 1.
Settings you can ask for
Boogu Image works from your prompt. Ask Grok Build for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Describes what should NOT appear in the image. Used for classifier-free guidance; leave empty to disable text negative guidance. | |
| Number of inference steps | 20 to 50 | 30 | The number of denoising steps to perform. |
| Guidance scale | 1 to 8 | 4 | Controls how closely generation follows the text instruction. Higher values stick more closely to the prompt. A value of 1.0 disables text classifier-free guidance. |
| CFG range start | 0 to 1 | 0 | Start of the timestep fraction over which CFG is applied. |
| CFG range end | 0 to 1 | 1 | End of the timestep fraction over which CFG is applied. |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Seed | a whole number | The same seed and the same prompt given to the same version of the model will output the same image every time. | |
| Output format | jpeg or png | jpeg | The format of the generated image. |
Every API field of Boogu Image · Text to Image is on its tool page: open its card above.
What can you do with Boogu Image in Grok Build?
Turn project copy and design notes into poster, cover, or editorial image concepts with Boogu Image. A coding agent can read the relevant files and turn their content into a detailed visual brief.
Event poster concepts
Draft a poster from an event description, with a clear headline and a small amount of supporting copy. Check every date and letter before using it.
Chinese and English campaign artwork
Explore artwork containing supplied Chinese and English headlines. Specify the placement and relative size of each language.
Document layout studies
Test the visual hierarchy of a title page or short information sheet before rebuilding the chosen layout in a document editor.
Brand guide concepts
Explore a brand guide page using a written palette, typography direction, and short sample headings.
Editorial photo concepts
Turn a written article brief into a photographic scene with specified framing, lighting, and background details.
Illustrated covers
Explore a cover in a chosen artistic medium, with a defined focal subject and space for the title.
More on Boogu Image and Grok Build
Overview
Boogu Image in other agents
Questions about Boogu Image in Grok Build
Can Grok Build use Boogu Image?
Yes. Add Spiral to Grok Build as an MCP server, and Grok Build can find and run Boogu Image like any built-in tool.
How much does Boogu Image cost in Grok Build?
$0.052 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. 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 Grok Build plan is separate.
Do I need a fal account to use Boogu Image in Grok Build?
No. Spiral runs Boogu 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 Boogu Image in Grok Build?
About two minutes: add the server, then sign in, then check it.
Does Grok Build wait while Boogu Image runs?
Boogu Image runs in the background. Grok Build starts the run, checks on it and gives you the image when it's ready.
What is Boogu Image useful for?
Try posters, document concepts, bilingual lettering, editorial photos, and illustrated covers. Describe the intended layout as carefully as the subject.
Can Boogu Image write Chinese and English in an image?
Yes. It supports Chinese and English text rendering, though generated lettering still needs proofreading before use.
How large can Boogu Image generate?
Its maximum native resolution is 2K. Asking for a larger image is clamped to that limit.
Why does Boogu Image sometimes misspell text?
Long passages, small fonts, dense typography, and complex layouts remain documented weaknesses. Shorten the copy and simplify the layout when letters go missing or text shifts.
How should I prompt Boogu Image?
Use a detailed description of the subject, composition, lighting, colors, and intended lettering. For example, specify where a headline belongs and provide its exact wording.
Start using Boogu Image in Grok Build
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Grok Build:
set up https://spiral.ai/SKILL.md


