How to Use Sana Sprint in Gemini
Sana Sprint turns text descriptions into images for concept art, illustrations, and design drafts. Its distinguishing feature is generation in one to four steps; complex lettering and perfect photorealism remain weak points.
Prompts to try with Sana Sprint in Gemini
Copy an example into Gemini, or ask in your own words.
Use Sana Sprint to create a 1024 × 1024 watercolor illustration of a fox waiting at a rural train platform at sunrise. Use two generation steps and include no lettering.
Use Sana Sprint to illustrate patient growth as a tiny greenhouse on a crowded city roof. Make a 1024 × 1024 image with soft morning light and open space above for a headline I will add later.
Use Sana Sprint to explore an invented desk lamp made from folded copper and frosted glass. Generate a 1024 × 1024 studio concept image with a plain background and no branding.
Use Sana Sprint to make a 1024 × 1024 story starter: a miniature lighthouse inside a teacup during a storm. Use two generation steps and a painted storybook style.
Use Sana Sprint to render a moonlit botanical library at 1024 × 1024 with one generation step, then four. Keep the description identical and help me compare the composition and details.
How to set up Sana Sprint in Gemini
Pick the way that suits you. Each takes about two minutes.
Use the Gemini connector
- Open Connected Apps
On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.
- Add Spiral as a custom app
Under Custom apps, click Add a custom app and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Gemini 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 Sana Sprint
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/sana/sprint", "input": { "prompt": "Underwater coral reef ecosystem during peak bioluminescent activity, multiple layers of marine life - from microscopic plankton to massive coral structures,…" } }'
Then paste one of the prompts above: Gemini finds Sana Sprint on Spiral, shows the price and runs it.
Sana Sprint providers and prices
Spiral runs Sana Sprint through fal. Open a card for today's price, with every fee included.
$0.00325 per megapixel. image_size presets count as 1 MP; custom sizes round up to whole megapixels. Default 8 MP per image. Billed on num_images, default 1.
Settings you can ask for
Sana Sprint works from your prompt. Ask Gemini for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). | |
| Number of inference steps | 1 to 20 | 2 | The number of inference steps to perform. |
| 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. | |
| Guidance scale (CFG) | 0 to 20 | 5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Output format | jpeg or png | jpeg | The format of the generated image. |
| Style name | (No style), Cinematic, Photographic, Anime, Manga, Digital Art, Pixel art, Fantasy art and 2 more | (No style) | The style to generate the image in. |
Every API field of Sana Sprint is on its tool page: open its card above.
What can you do with Sana Sprint in Gemini?
Turn a written idea into artwork you can discuss and revise in conversation. Compare composition, lighting, and medium across drafts, then choose a direction for further editing.
Game environment concepts
Use Sana Sprint to explore a fictional location through different lighting, materials, and compositions before committing to production art.
Editorial illustration drafts
Turn an article's central idea into a visual metaphor, such as a greenhouse representing patient growth. Keep headlines outside the generated artwork.
Website artwork studies
Generate candidate illustrations for a website and assess their composition in the layout. Request empty space where the page needs readable copy.
Fictional product concepts
Explore the shape, material, and setting of an invented lamp, chair, or ceramic object before building a physical prototype.
Story scene exploration
Draft individual scenes from a written story to compare atmosphere and framing. Describe each scene independently.
Classroom creative exercises
Generate fictional landscapes or visual story starters for writing activities. Add instructions and labels separately.
Campaign illustration concepts
Explore several visual treatments of a campaign idea before selecting artwork for further editing. Leave slogans and other precise lettering for the final layout.
More on Sana Sprint and Gemini
Overview
Sana Sprint in other agents
Questions about Sana Sprint in Gemini
Can Gemini use Sana Sprint?
Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Sana Sprint like any built-in tool.
How much does Sana Sprint cost in Gemini?
$0.00325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Default 8 MP 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 Gemini plan is separate.
Do I need a fal account to use Sana Sprint in Gemini?
No. Spiral runs Sana Sprint on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Sana Sprint in Gemini?
About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.
Does Gemini wait while Sana Sprint runs?
Sana Sprint runs in the background. Gemini starts the run, checks on it and gives you the image when it's ready.
What should I use Sana Sprint for?
Consider it for concept art, editorial illustrations, and visual drafts where you want to explore several directions. Its one-to-four-step design makes iterative image generation a natural use.
What image size should I start with?
Start at 1024 × 1024, the size used in NVIDIA's example. The published model is described as 1024-pixel-based; that description does not establish a maximum output size.
How many inference steps should I use?
Start with two steps, as NVIDIA's example does, then compare one and four steps on the same brief. Sana Sprint was designed for generation within that range.
Should I increase guidance to improve the image?
Higher guidance pushes the result closer to your description, but it can reduce image quality. Try a small adjustment when the result misses an important detail, then compare the images.
Can Sana Sprint make posters with readable text?
Complex legible text is a documented limitation. Generate the illustration with room for a headline, then add the lettering in a design editor.
Start using Sana Sprint in Gemini
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini:
set up https://spiral.ai/SKILL.md


