[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Nano Banana Pro Text to Image](https://spiral.ai/integrations/opencode/nano-banana-pro-text-to-image)

# How to Use Nano Banana Pro Text to Image in opencode

Use Nano Banana Pro Text to Image for posters, labeled diagrams, and illustrated scenes from a written brief. Choose Nano Banana Pro Edit when the job centers on changing an existing design.

|  |  |
| --- | --- |
| Model | Nano Banana Pro Text to Image |
| Available through | fal |
| Category | Image |
| Price | `resolution`: 1K (default) $0.195, 2K $0.195, 4K $0.39 per image. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Nano Banana Pro Text to Image in opencode

- Use Nano Banana Pro Text to Image to turn the onboarding explanation in README.md into a 2K diagram. Use four large labels copied from the documentation and describe their positions explicitly.
- Use Nano Banana Pro Text to Image to make a storyboard from scripts/launch-scene.md. Show four panels: establishing shot, medium shot, close-up, and point-of-view shot, with short captions.
- Generate a product photo with Nano Banana Pro Text to 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 Nano Banana Pro Text to Image.
- Create a 16:9 hero image of a quiet mountain cabin at dusk with Nano Banana Pro Text to Image.

## How to set up Nano Banana Pro Text to Image in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **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.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **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.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Nano Banana Pro Text to Image**: One request; the result comes back by polling or a webhook.

```bash
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/gemini-3-pro-image-preview",
    "input": {
      "prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half,…"
    }
  }'
```

Then paste one of the prompts above: opencode finds Nano Banana Pro Text to Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## Nano Banana Pro Text to Image tools and prices

- [Gemini 3 Pro Image Preview · Text to Image](https://spiral.ai/tools/fal/fal-ai/gemini-3-pro-image-preview) (fal): `resolution`: 1K (default) $0.195, 2K $0.195, 4K $0.39 per image. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| history |  | — | Previous native user/model turns. Replay a returned conversation's messages unchanged, including thought signatures; the current prompt is appended as a new user turn. |
| context |  | — | Ordered text, original images, PDF or UTF-8 text documents appended to the current prompt. Uses a native provider. Images count toward the total 14-reference limit. |
| return_history |  | false | 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 |  | — | Thinking effort. Pro Image supports only high; omit to retain its provider default. An explicit level requests summaries unless include_thoughts overrides it. Thinking cannot be disabled. |
| image_passthrough |  | false | 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 |  | — | 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. |

## What can you do with Nano Banana Pro Text to Image in opencode?

Turn project briefs and documentation into posters, diagrams, and visual concepts with Nano Banana Pro. A coding agent can gather the relevant project context and prepare a specific image brief with approved text.

### Event posters from a brief

Create a poster with a short event name, date, and location. Specify where each line belongs, then inspect the rendered lettering.

### Labeled educational diagrams

Turn an approved explanation into a diagram with a small set of large labels. Check the positions of arrows and labels against the source explanation.

### Localized campaign concepts

Create a graphic using approved Spanish, Japanese, or Korean copy. Keep the wording short enough to inspect letter by letter.

### Film and ad storyboards

Translate a written scene into a storyboard showing an establishing shot, medium shot, close-up, and point-of-view shot.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Nano Banana Pro Text to Image in other agents

- [Amp](https://spiral.ai/integrations/amp/nano-banana-pro-text-to-image)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/nano-banana-pro-text-to-image)
- [Claude](https://spiral.ai/integrations/claude-desktop/nano-banana-pro-text-to-image)
- [Claude Code](https://spiral.ai/integrations/claude-code/nano-banana-pro-text-to-image)
- [Cline](https://spiral.ai/integrations/cline/nano-banana-pro-text-to-image)
- [Codex](https://spiral.ai/integrations/codex/nano-banana-pro-text-to-image)
- [Cursor](https://spiral.ai/integrations/cursor/nano-banana-pro-text-to-image)
- [Devin](https://spiral.ai/integrations/devin/nano-banana-pro-text-to-image)
- [dots](https://spiral.ai/integrations/dots/nano-banana-pro-text-to-image)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/nano-banana-pro-text-to-image)
- [Gemini](https://spiral.ai/integrations/gemini/nano-banana-pro-text-to-image)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/nano-banana-pro-text-to-image)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/nano-banana-pro-text-to-image)
- [goose](https://spiral.ai/integrations/goose/nano-banana-pro-text-to-image)
- [Grok](https://spiral.ai/integrations/grok/nano-banana-pro-text-to-image)
- [Grok Build](https://spiral.ai/integrations/grok-build/nano-banana-pro-text-to-image)
- [Hermes](https://spiral.ai/integrations/hermes/nano-banana-pro-text-to-image)
- [Instinct](https://spiral.ai/integrations/instinct/nano-banana-pro-text-to-image)
- [Manus](https://spiral.ai/integrations/manus/nano-banana-pro-text-to-image)
- [Muse](https://spiral.ai/integrations/muse/nano-banana-pro-text-to-image)
- [Muse Code](https://spiral.ai/integrations/muse-code/nano-banana-pro-text-to-image)
- [n8n](https://spiral.ai/integrations/n8n/nano-banana-pro-text-to-image)
- [Notion](https://spiral.ai/integrations/notion/nano-banana-pro-text-to-image)
- [OpenClaw](https://spiral.ai/integrations/openclaw/nano-banana-pro-text-to-image)
- [Perplexity](https://spiral.ai/integrations/perplexity/nano-banana-pro-text-to-image)
- [Raycast](https://spiral.ai/integrations/raycast/nano-banana-pro-text-to-image)
- [VS Code](https://spiral.ai/integrations/vscode/nano-banana-pro-text-to-image)
- [Windsurf](https://spiral.ai/integrations/windsurf/nano-banana-pro-text-to-image)
- [Zapier](https://spiral.ai/integrations/zapier/nano-banana-pro-text-to-image)

## More opencode guides

- [Nano Banana Pro Image Editing](https://spiral.ai/integrations/opencode/nano-banana-pro-image-editing)
- [Object Removal](https://spiral.ai/integrations/opencode/object-removal)
- [Nano Banana Pro Edit](https://spiral.ai/integrations/opencode/nano-banana-pro-edit)
- [Object Removal Bounding Box](https://spiral.ai/integrations/opencode/object-removal-bounding-box)
- [Nano Banana Pro](https://spiral.ai/integrations/opencode/nano-banana-pro)
- [Object Removal Mask](https://spiral.ai/integrations/opencode/object-removal-mask)

## Questions about Nano Banana Pro Text to Image in opencode

**Can opencode use Nano Banana Pro Text to Image?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Nano Banana Pro Text to Image like any built-in tool.

**How much does Nano Banana Pro Text to Image cost in opencode?**

`resolution`: 1K (default) $0.195, 2K $0.195, 4K $0.39 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 opencode plan is separate.

**Do I need a fal account to use Nano Banana Pro Text to Image in opencode?**

No. Spiral runs Nano Banana Pro Text to 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 Nano Banana Pro Text to Image in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while Nano Banana Pro Text to Image runs?**

Nano Banana Pro Text to Image runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

**What is Nano Banana Pro good at?**

Posters with readable headlines, labeled diagrams, product mockups, and multilingual graphics are useful starting points. Give it a concrete brief with the exact wording and layout you want.

**How large can Nano Banana Pro images be?**

Nano Banana Pro supports 1K, 2K, and 4K output. Choose the output size deliberately rather than asking for a vague description such as high resolution.

**Can Nano Banana Pro write text inside an image?**

Yes, including text for posters and diagrams. Small lettering and long paragraphs remain weak spots, so keep essential copy short and inspect it before use.

**Can Nano Banana Pro make graphics in different languages?**

Yes, it can generate localized text and translate text inside images. Supply the approved wording when exact phrasing matters.

**How should I write a Nano Banana Pro prompt?**

Write a complete description of the scene instead of a string of keywords. Include the subject, intended use, composition, lighting, and exact text so the brief leaves fewer decisions unspecified.

