[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Sana 1.5 1.6B](https://spiral.ai/integrations/opencode/sana-1-5-1-6b)

# How to Use Sana 1.5 1.6B in opencode

Sana 1.5 1.6B turns written briefs into illustrations and image concepts, with outputs up to 4K. It uses 1.6 billion parameters, compared with Sana 1.5 4.8B's 4.8 billion.

|  |  |
| --- | --- |
| Model | Sana 1.5 1.6B |
| Available through | fal |
| Category | Image |
| Price | $0.00975 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. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Sana 1.5 1.6B in opencode

- Read the homepage copy and design tokens, then use Sana 1.5 1.6B to create a hero illustration of a small greenhouse at dawn. Match the project's colors, place the greenhouse on the right, and leave the left side empty for HTML text.
- Use Sana 1.5 1.6B to generate a 1024 by 1024 illustration for this app's empty library screen: a wooden shelf with one closed book, soft side lighting, muted green and brown colors, no lettering. Add it to the existing empty state.
- Read the game's location brief and use Sana 1.5 1.6B to create a Digital Art concept of its abandoned mountain observatory. Describe the stone walls, copper telescope, snow, and doorway placement explicitly.
- Use Sana 1.5 1.6B to create cover artwork for the sample story in this repository: a red canoe beside a misty pine forest lake. Keep the upper third clear and render the title separately in the page.
- Use Sana 1.5 1.6B to generate a square concept image of an invented desk lamp with a ribbed ceramic base and a linen shade. Save the prompt with the asset so we can compare future design changes.

## How to set up Sana 1.5 1.6B 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 Sana 1.5 1.6B**: 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/sana/v1.5/1.6b",
    "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: opencode finds Sana 1.5 1.6B on Spiral, shows the price and runs it.

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

## Sana 1.5 1.6B tools and prices

- [Sana v1.5 1.6B · Text to Image](https://spiral.ai/tools/fal/fal-ai/sana/v1.5/1.6b) (fal): $0.00975 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

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | 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). |
| image_size |  | {"width":3840,"height":2160} | The size of the generated image. |
| num_inference_steps | 1 to 50 | 18 | The number of inference steps to perform. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| guidance_scale | 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. |
| num_images | 1 to 4 | 1 | The number of images to generate. |

## What can you do with Sana 1.5 1.6B in opencode?

Create illustrations and concept images while building a website or app. A coding agent can turn the project's design notes into visual briefs and place selected artwork in the interface.

### Website hero artwork

Generate a scene from a written brief, placing the subject to one side and leaving room for a headline added during layout.

### Editorial illustration

Turn an article's central idea into a visual metaphor, such as a greenhouse representing steady business growth.

### Game environment concepts

Explore written descriptions of locations, including their architecture, weather, lighting, and materials.

### Fictional product concepts

Sketch ideas for an invented lamp, chair, or vessel by describing its shape, surface, color, and setting.

### Book cover artwork

Create an illustrated setting or symbolic object from a story brief. Reserve space for the title and add the lettering separately.

### Classroom story illustrations

Illustrate fictional scenes for writing exercises, then have students describe the setting or invent what happens next.

### Campaign art direction

Explore different materials, palettes, and compositions for a campaign before selecting a direction for production.

## Overview

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

## Sana 1.5 1.6B in other agents

- [Amp](https://spiral.ai/integrations/amp/sana-1-5-1-6b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/sana-1-5-1-6b)
- [Claude](https://spiral.ai/integrations/claude-desktop/sana-1-5-1-6b)
- [Claude Code](https://spiral.ai/integrations/claude-code/sana-1-5-1-6b)
- [Cline](https://spiral.ai/integrations/cline/sana-1-5-1-6b)
- [Codex](https://spiral.ai/integrations/codex/sana-1-5-1-6b)
- [Cursor](https://spiral.ai/integrations/cursor/sana-1-5-1-6b)
- [Devin](https://spiral.ai/integrations/devin/sana-1-5-1-6b)
- [dots](https://spiral.ai/integrations/dots/sana-1-5-1-6b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/sana-1-5-1-6b)
- [Gemini](https://spiral.ai/integrations/gemini/sana-1-5-1-6b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/sana-1-5-1-6b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/sana-1-5-1-6b)
- [goose](https://spiral.ai/integrations/goose/sana-1-5-1-6b)
- [Grok](https://spiral.ai/integrations/grok/sana-1-5-1-6b)
- [Grok Build](https://spiral.ai/integrations/grok-build/sana-1-5-1-6b)
- [Hermes](https://spiral.ai/integrations/hermes/sana-1-5-1-6b)
- [Instinct](https://spiral.ai/integrations/instinct/sana-1-5-1-6b)
- [Manus](https://spiral.ai/integrations/manus/sana-1-5-1-6b)
- [Muse](https://spiral.ai/integrations/muse/sana-1-5-1-6b)
- [Muse Code](https://spiral.ai/integrations/muse-code/sana-1-5-1-6b)
- [n8n](https://spiral.ai/integrations/n8n/sana-1-5-1-6b)
- [Notion](https://spiral.ai/integrations/notion/sana-1-5-1-6b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/sana-1-5-1-6b)
- [Perplexity](https://spiral.ai/integrations/perplexity/sana-1-5-1-6b)
- [Raycast](https://spiral.ai/integrations/raycast/sana-1-5-1-6b)
- [VS Code](https://spiral.ai/integrations/vscode/sana-1-5-1-6b)
- [Windsurf](https://spiral.ai/integrations/windsurf/sana-1-5-1-6b)
- [Zapier](https://spiral.ai/integrations/zapier/sana-1-5-1-6b)

## More opencode guides

- [Sana](https://spiral.ai/integrations/opencode/sana)
- [Sana 1.5 4.8B](https://spiral.ai/integrations/opencode/sana-1-5-4-8b)
- [SAM 3.1 Image to RLE](https://spiral.ai/integrations/opencode/sam-3-1-image-to-rle)
- [Sana Sprint](https://spiral.ai/integrations/opencode/sana-sprint)
- [SAM 3.1 Image](https://spiral.ai/integrations/opencode/sam-3-1-image)
- [Seedream 4.0 Edit](https://spiral.ai/integrations/opencode/seedream-4-0-edit)

## Questions about Sana 1.5 1.6B in opencode

**Can opencode use Sana 1.5 1.6B?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Sana 1.5 1.6B like any built-in tool.

**How much does Sana 1.5 1.6B cost in opencode?**

$0.00975 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 opencode plan is separate.

**Do I need a fal account to use Sana 1.5 1.6B in opencode?**

No. Spiral runs Sana 1.5 1.6B 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 1.5 1.6B in opencode?**

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

**Does opencode wait while Sana 1.5 1.6B runs?**

Sana 1.5 1.6B runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

**What image resolution can Sana 1.5 1.6B produce?**

Sana 1.5 1.6B supports output up to 4K. Start with a smaller draft to judge the composition before requesting the final image.

**Can Sana 1.5 1.6B generate readable text inside an image?**

Complex readable text is a documented weakness. Generate the artwork with space for a headline, then add the lettering in your layout tool.

**How reliable are realistic people and hands?**

The maker documents imperfect photorealism and errors in fingers. Inspect portraits and visible hands before using an image.

**How should I write a Sana 1.5 prompt?**

Describe the subject, colors, materials, and where objects sit relative to each other. Use concrete visual details, such as a small red ceramic bowl beside a tall clear glass.

**Should I increase guidance when the image misses my prompt?**

Higher guidance encourages closer prompt adherence, but it can reduce image quality. Try a small increase and compare the result before pushing it further.

