How to Use Nano Banana 2 Image Editing fal in opencode
Nano Banana 2 Image Editing changes photos, combines references, and transfers styles with written instructions. Unlike Nano Banana 2 Text to Image, it centers the work on existing visuals.
Prompts to try with Nano Banana 2 Image Editing fal in opencode
Copy an example into opencode, or ask in your own words.
Use Nano Banana 2 Image Editing to restage the product photo in public/images on a wooden desk with soft window light. Preserve the product's shape and label.
Use Nano Banana 2 Image Editing to turn the onboarding diagram in docs/assets into a hand-drawn illustration. Keep its approved labels and connections.
Remove the background from the photo I attach with Nano Banana 2 Image Editing fal and give me a transparent PNG. Save the result in ./assets.
Use Nano Banana 2 Image Editing fal to clean up these product shots so they sit on pure white.
Edit this image with Nano Banana 2 Image Editing fal: keep the subject, swap the background for a sunlit studio.
How to set up Nano Banana 2 Image Editing fal in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode 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 2 Image Editing fal
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-2/edit", "input": { "prompt": "make a photo of the man driving the car down the california coastline", "image_urls": [ "<image_urls>" ] } }'
Then paste one of the prompts above: opencode finds Nano Banana 2 Image Editing fal on Spiral, shows the price and runs it.
Nano Banana 2 Image Editing fal providers and prices
Spiral runs Nano Banana 2 Image Editing fal through fal. Open a card for today's price, with every fee included.
$0.104 per image at 1K ($0.078 at 0.5K, $0.156 at 2K, $0.208 at 4K). Web search: $0.0195 per request. High thinking: $0.0026 per request.
Settings you can ask for
Nano Banana 2 Image Editing fal works from your prompt, image URLs, system prompt, video URL, audio URL, and PDF URL. Ask opencode 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. |
| Thinking level | minimal or high | Controls thinking effort ('minimal' or 'high') and requests thought summaries. Omit to use the provider default ('minimal'); thinking cannot be disabled. | |
| 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. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. |
| 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 | 0.5K, 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. |
| Enable image search | on or off | off | Ground image generation with Google Image Search. Can be combined with enable_web_search; source attribution is returned in grounding_metadata. Uses direct Google or Vertex APIs. |
Every API field of Nano Banana 2 · Image Editing is on its tool page: open its card above.
What can you do with Nano Banana 2 Image Editing fal in opencode?
Turn project briefs into campaign art, product concepts, and illustrated documentation with Nano Banana 2. A coding agent can use repository content to prepare detailed visual instructions and place the resulting assets in the project.
Campaign graphics
Create a campaign concept from a brief or adapt an approved design with new wording and imagery.
Product presentations
Visualize a product concept or restage an existing product photo for a presentation.
Illustrated explainers
Turn a written explanation into a labeled illustration or revise an existing diagram.
Posters and greeting cards
Build a design around exact quoted wording, with specified lettering and composition.
Storyboard development
Explore scenes from a written treatment or use character references to guide successive frames.
Localized artwork
Replace the text in an existing campaign image with approved translated copy.
Style exploration
Reinterpret an existing scene as a watercolor, cartoon, or photographic composition.
Nano Banana 2 Image Editing fal 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 2 · Image Editing | 11.3% | 25.7s | 203 |
More on Nano Banana 2 Image Editing fal and opencode
Overview
Nano Banana 2 Image Editing fal in other agents
Questions about Nano Banana 2 Image Editing fal in opencode
Can opencode use Nano Banana 2 Image Editing fal?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Nano Banana 2 Image Editing fal like any built-in tool.
How much does Nano Banana 2 Image Editing fal cost in opencode?
$0.104 per image at 1K ($0.078 at 0.5K, $0.156 at 2K, $0.208 at 4K). Web search: $0.0195 per request. High thinking: $0.0026 per request. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need a fal account to use Nano Banana 2 Image Editing fal in opencode?
No. Spiral runs Nano Banana 2 Image Editing fal 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 2 Image Editing fal in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Nano Banana 2 Image Editing fal runs?
Nano Banana 2 Image Editing fal runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.
What is Nano Banana 2 good at?
Use it for marketing graphics, product concepts, illustrated explainers, and text inside images. It also suits storyboards and repeated visual exploration.
How large can Nano Banana 2 images be?
Nano Banana 2 supports output tiers from 0.5K through 4K, with 1K as the default. Start with a smaller draft to settle the composition before requesting a larger result.
Can Nano Banana 2 put readable words in an image?
Yes. Put the exact wording in quotes and specify the typography, such as bold sans-serif lettering.
Can Nano Banana 2 make visuals in other languages?
Yes. It can generate and translate text within images, making it useful for localized posters, cards, and campaign graphics.
When does higher thinking effort help?
Use it for a composition with several constraints, such as specific object placement, labels, and visual relationships. Google says reasoning before rendering can improve complex prompt adherence.
Start using Nano Banana 2 Image Editing fal in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


