How to Use HiDream O1 Image in Gemini CLI
Use HiDream O1 Image for posters with lettering, illustrated scenes, and storyboard images up to 2048 × 2048 pixels. Unlike HiDream O1 Image Edit, it can start from text alone as well as work from reference images.
Prompts to try with HiDream O1 Image in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use HiDream O1 Image to create a 1536 × 1024 illustration for this project's empty search state. Read the UI copy and theme colors, then depict a librarian inspecting an empty shelf, with the subject on the right and open space on the left.
Read the event details in this project's content and use HiDream O1 Image to create a 1024 × 1536 poster concept. Put the exact event title at the top, the date beneath it, and the venue along the bottom.
Generate a product photo with HiDream O1 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 HiDream O1 Image.
Create a 16:9 hero image of a quiet mountain cabin at dusk with HiDream O1 Image.
How to set up HiDream O1 Image in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 HiDream O1 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/hidream-o1-image", "input": { "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field." } }'
Then paste one of the prompts above: Gemini CLI finds HiDream O1 Image on Spiral, shows the price and runs it.
HiDream O1 Image providers and prices
Spiral runs HiDream O1 Image through fal. Open a card for today's price, with every fee included.
$0.013 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
HiDream O1 Image works from your prompt and reference image URLs. Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of inference steps | 1 to 50 | 50 | Number of denoising steps. |
| Guidance scale | 0 to 20 | 5 | Classifier-free guidance scale. The full model uses 5.0 by default. |
| Seed | a whole number | Random seed for reproducible generation. | |
| Number of images | 1 to 4 | 1 | Number of images to generate. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
| Keep original aspect | on or off | off | When exactly one reference image is provided, preserve its aspect ratio for the output image. |
Every API field of Hidream O1 Image is on its tool page: open its card above.
What can you do with HiDream O1 Image in Gemini CLI?
Create or revise visual assets using the project's copy and existing artwork as context. A coding agent can turn those details into explicit HiDream O1 Image instructions for lettering, composition, and reference-based edits.
Event poster concepts
Create a poster from a written brief with the event name, date, and venue placed in specified regions. Supply the exact wording for each region.
Storyboard drafts from a script
Turn a short scene description into a multi-panel storyboard image. Specify the action, shot size, and camera angle for each panel.
Seasonal product scenes
Start with a product reference and request a new setting, such as a picnic table or winter storefront. Name the product details that should stay consistent.
Product color studies
Use an existing product picture to explore a different surface color. State which object changes and which materials, markings, and surrounding objects should remain.
Localized sign concepts
Revise lettering in a supplied sign or poster using exact Chinese or English copy. Specify the text position, font treatment, and background to retain.
Recurring character illustrations
Use character references to request new scenes for a comic or illustrated campaign. Describe the identifying features to retain and the action in each scene.
Illustration style studies
Start from an existing illustration and request a watercolor, painted, or photographic treatment. Describe the composition and subject details to carry into the new image.
Reference-based storyboard exploration
Use a subject reference to explore a scene across wide, medium, and close-up compositions. Request a single storyboard image with clearly described panels.
More on HiDream O1 Image and Gemini CLI
Overview
HiDream O1 Image in other agents
Questions about HiDream O1 Image in Gemini CLI
Can Gemini CLI use HiDream O1 Image?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run HiDream O1 Image like any built-in tool.
How much does HiDream O1 Image cost in Gemini CLI?
$0.013 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 Gemini CLI plan is separate.
Do I need a fal account to use HiDream O1 Image in Gemini CLI?
No. Spiral runs HiDream O1 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 HiDream O1 Image in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while HiDream O1 Image runs?
HiDream O1 Image runs in the background. Gemini CLI starts the run, checks on it and gives you the image when it's ready.
What is HiDream O1 Image good at?
Useful starting points include images with lettering, cinematic compositions, and illustrated storyboards. Reference-based work also includes editing pictures and placing a supplied subject into a different scene.
How large can HiDream O1 Image outputs be?
Outputs reach about 2048 × 2048 pixels. Reference-based results use the nearest supported resolution, so check the returned dimensions when an exact size matters.
Can HiDream O1 Image render Chinese and English lettering?
The maker's prompting guidance explicitly covers Chinese and English text. Put the exact wording in quotation marks and specify its font, color, and position.
Can HiDream O1 Image keep a reference subject in a new scene?
Subject-driven personalization is a supported task. Describe the new scene and explicitly identify the appearance details you want retained from the references.
How should I describe the composition?
Use concrete positions such as top left, centered in the foreground, or behind the subject. For lettering, include its exact wording and placement instead of asking for a generally attractive layout.
Start using HiDream O1 Image in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


