How to Use Nano Banana Pro Image Editing in Muse Code
Use Nano Banana Pro Edit to turn references into product mockups, localized artwork, or detailed compositions. It brings Pro's text rendering and higher resolutions to edits of existing images.
Prompts to try with Nano Banana Pro Image Editing in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use Nano Banana Pro Edit with the project's layout sketch and product photo. Follow the sketch for placement and the photo for product appearance, producing a 2K visual mockup with space for the page's HTML headline.
Use Nano Banana Pro Edit to adapt the project's campaign artwork using its approved Spanish translation. Preserve the composition and product, replace only the wording, request 2K output, and flag any spelling differences.
Use Nano Banana Pro Edit with the product photo in the project's assets. Replace the background with a softly lit workshop while preserving the product's shape, color, markings, and camera angle; make the image square.
Remove the background from the photo I attach with Nano Banana Pro Image Editing and give me a transparent PNG. Save the result in ./assets.
Use Nano Banana Pro Image Editing to clean up these product shots so they sit on pure white.
How to set up Nano Banana Pro Image Editing in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code 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 Nano Banana Pro Image Editing
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/nano-banana-pro/edit", "input": { "prompt": "make a photo of the man driving the car down the california coastline" } }'
Then paste one of the prompts above: Muse Code finds Nano Banana Pro Image Editing on Spiral, shows the price and runs it.
Nano Banana Pro Image Editing providers and prices
Spiral runs Nano Banana Pro Image Editing through fal. Open a card for today's price, with every fee included.
$0.195 per image at 1K or 2K ($0.39 at 4K). Web search: $0.0195 per request.
Settings you can ask for
Nano Banana Pro Image Editing works from your prompt, image URLs, and system prompt. Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Return history | on or off | off | Return reusable native conversations with original image parts and provider thought signatures. Uses a native provider. Each generated conversation is independent; send its messages as history for the next turn. |
| Image passthrough | on or off | off | Send reference images and return provider images without resizing or re-encoding, preserving transparency and metadata. Uses direct Google or Vertex APIs; the returned image format may differ from output_format. |
| Include thoughts | on or off | Whether to include thought summaries. Omit to preserve the existing behavior: an explicit thinking_level requests summaries. Set limit_generations=false to return summary text in description. This does not disable thinking or return intermediate thought images. | |
| Temperature | 0 to 2 | Sampling temperature. Omit to use the provider default of 1. Explicit values use a direct Google or Vertex API. | |
| Top p | 0 to 1 | Nucleus sampling probability. Omit to use the provider default of 0.95. Explicit values use a direct Google or Vertex API. | |
| Max output tokens | 1 to 32768 | Maximum output tokens for the generation. Omit to retain the provider default. Explicit values use a direct Google or Vertex API. | |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Seed | a whole number | The seed for the random number generator. | |
| Aspect ratio | auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5 and 7 more | auto | The aspect ratio of the generated image, including 1:4, 4:1, 1:8 and 8:1. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
| Safety tolerance | 1 to 6 | 4 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |
| Resolution | 1K, 2K, or 4K | 1K | The resolution of the image to generate. |
| Limit generations | on or off | on | Experimental parameter to limit the number of generations from each round of prompting to 1. Set to |
| Enable web search | on or off | off | Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image. |
Every API field of Nano Banana Pro · Image Editing is on its tool page: open its card above.
What can you do with Nano Banana Pro Image Editing in Muse Code?
Create illustrations and visual mockups that fit the project you are building. Use project assets as references, then inspect the results for text errors and unwanted changes.
Product scenes from reference photos
Place an existing product into different settings while asking to preserve its shape, color, and identifying details. Compare each result with the original photo.
Posters with exact wording
Use Pro for artwork that includes a headline or short message. Supply the wording in quotes and describe its position and typography.
Localized campaign artwork
Use Pro Edit to replace text in an existing design with approved translations. Ask to preserve the product, layout, and background.
Sketches turned into mockups
Give Pro Edit a layout sketch and a product reference to create a visual mockup. Assign a specific role to each reference.
Explanatory diagrams
Turn supplied notes into a labeled visual with Pro. Review the relationships and labels against the notes before sharing it.
Photo restyling
Use the editing models to reinterpret a photo as an illustration or change its setting. State which subject details should remain recognizable.
Nano Banana Pro Image Editing success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| Nano Banana Pro · Image Editing | 47.1% | 28.1s | 121 |
More on Nano Banana Pro Image Editing and Muse Code
Overview
Nano Banana Pro Image Editing in other agents
Questions about Nano Banana Pro Image Editing in Muse Code
Can Muse Code use Nano Banana Pro Image Editing?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Nano Banana Pro Image Editing like any built-in tool.
How much does Nano Banana Pro Image Editing cost in Muse Code?
$0.195 per image at 1K or 2K ($0.39 at 4K). Web search: $0.0195 per request. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.
Do I need a fal account to use Nano Banana Pro Image Editing in Muse Code?
No. Spiral runs Nano Banana Pro Image Editing on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Nano Banana Pro Image Editing in Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while Nano Banana Pro Image Editing runs?
Nano Banana Pro Image Editing runs in the background. Muse Code starts the run, checks on it and gives you the image when it's ready.
When should I choose Nano Banana Pro?
Choose Pro for text-heavy artwork, detailed compositions, or output above the original model's roughly 1K range. It supports native generation from 1K to 4K.
Can Nano Banana keep the same person or product across images?
Maintaining a subject's appearance across edits is a core strength. Use a clear reference and check each result, because consistency is not guaranteed.
Can it create readable text in other languages?
Pro can generate multilingual text and translate existing artwork. Provide the exact translated wording when it matters, then check the rendered spelling before using the image.
How many reference images should I use?
Google says the original works best with up to three input images. Pro supports up to 14 references, but each reference should have a clear purpose, such as the subject, layout, or background.
Can I trust the facts in a generated infographic?
Check every label, number, and relationship against your source material. Pro can misinterpret information or produce incorrect facts even when the graphic looks convincing.
Start using Nano Banana Pro Image Editing in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


