[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Sana 1.5 4.8B](https://spiral.ai/integrations/opencode/sana-1-5-4-8b)

# How to Use Sana 1.5 4.8B in opencode

Sana 1.5 4.8B turns written scenes into illustrations and concept art. It has three times the parameters of Sana 1.5 1.6B and emphasizes matching images to their descriptions.

|  |  |
| --- | --- |
| Model | Sana 1.5 4.8B |
| Available through | fal |
| Category | Image |
| Price | $0.013 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 4.8B in opencode

- Read the homepage copy and use Sana 1.5 4.8B to create a 1024 × 1024 illustration concept for the gardening service: a small rooftop greenhouse at sunrise, terracotta pots, and soft green foliage. Keep lettering out of the artwork and save the result in the project's image assets.
- Use Sana 1.5 4.8B to generate a 1024 × 1024 illustration for the reading app's empty library screen: an open book beside a sleeping cat, warm desk light, and a simple background. Match the palette defined in the project's styles.
- Read the game design brief and use Sana 1.5 4.8B to create a 1024 × 1024 environment concept of its abandoned mountain observatory. Emphasize weathered copper, snow on stone steps, and a low viewpoint.
- Use Sana 1.5 4.8B to create a 1024 × 1024 background for the event page: a moonlit outdoor cinema with empty chairs and a screen. Keep the upper third quiet, then render the event title as HTML over that area.
- Use Sana 1.5 4.8B to explore the project's fictional tea packaging art at 1024 × 1024: ink illustrations of tea leaves and a mountain stream. Keep the label text in the existing layout, and compare results at guidance 4 and 5 before selecting an image.

## How to set up Sana 1.5 4.8B 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 4.8B**: 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/v1.5/4.8b",
    "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 4.8B on Spiral, shows the price and runs it.

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

## Sana 1.5 4.8B tools and prices

- [Sana v1.5 4.8B · Text to Image](https://spiral.ai/tools/fal/fal-ai/sana/v1.5/4.8b) (fal): $0.013 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 4.8B in opencode?

Create illustration concepts from the project's written brief and place selected artwork in the interface. Use the agent to keep typography in code and review generated details before adding assets.

### Website illustration concepts

Explore artwork for a gardening service, travel guide, or reading app. Describe the subject and leave clear space for the page's headline.

### Editorial artwork

Turn an article's central idea into a visual metaphor, such as a crowded greenhouse for a story about urban growing. Add captions separately.

### Game environment concepts

Explore fictional settings before production: a flooded observatory, a desert railway station, or a mountain village. Specify viewpoint, materials, and lighting.

### Poster backgrounds

Create artwork for a film night or community event with an intentional empty area for typography. Finish the title, date, and venue in a layout tool.

### Fiction illustrations

Sketch a scene from a story using its setting, mood, and focal subject. Review the result against the passage before choosing it.

### Packaging art exploration

Develop decorative artwork for an imaginary tea, coffee, or stationery collection. Keep labels and required lettering outside the generated image.

### Lesson illustration drafts

Create imaginative scenes for writing exercises or classroom discussion. Review any factual details before using the artwork in teaching materials.

## Overview

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

## Sana 1.5 4.8B in other agents

- [Amp](https://spiral.ai/integrations/amp/sana-1-5-4-8b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/sana-1-5-4-8b)
- [Claude](https://spiral.ai/integrations/claude-desktop/sana-1-5-4-8b)
- [Claude Code](https://spiral.ai/integrations/claude-code/sana-1-5-4-8b)
- [Cline](https://spiral.ai/integrations/cline/sana-1-5-4-8b)
- [Codex](https://spiral.ai/integrations/codex/sana-1-5-4-8b)
- [Cursor](https://spiral.ai/integrations/cursor/sana-1-5-4-8b)
- [Devin](https://spiral.ai/integrations/devin/sana-1-5-4-8b)
- [dots](https://spiral.ai/integrations/dots/sana-1-5-4-8b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/sana-1-5-4-8b)
- [Gemini](https://spiral.ai/integrations/gemini/sana-1-5-4-8b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/sana-1-5-4-8b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/sana-1-5-4-8b)
- [goose](https://spiral.ai/integrations/goose/sana-1-5-4-8b)
- [Grok](https://spiral.ai/integrations/grok/sana-1-5-4-8b)
- [Grok Build](https://spiral.ai/integrations/grok-build/sana-1-5-4-8b)
- [Hermes](https://spiral.ai/integrations/hermes/sana-1-5-4-8b)
- [Instinct](https://spiral.ai/integrations/instinct/sana-1-5-4-8b)
- [Manus](https://spiral.ai/integrations/manus/sana-1-5-4-8b)
- [Muse](https://spiral.ai/integrations/muse/sana-1-5-4-8b)
- [Muse Code](https://spiral.ai/integrations/muse-code/sana-1-5-4-8b)
- [n8n](https://spiral.ai/integrations/n8n/sana-1-5-4-8b)
- [Notion](https://spiral.ai/integrations/notion/sana-1-5-4-8b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/sana-1-5-4-8b)
- [Perplexity](https://spiral.ai/integrations/perplexity/sana-1-5-4-8b)
- [Raycast](https://spiral.ai/integrations/raycast/sana-1-5-4-8b)
- [VS Code](https://spiral.ai/integrations/vscode/sana-1-5-4-8b)
- [Windsurf](https://spiral.ai/integrations/windsurf/sana-1-5-4-8b)
- [Zapier](https://spiral.ai/integrations/zapier/sana-1-5-4-8b)

## More opencode guides

- [Sana 1.5 1.6B](https://spiral.ai/integrations/opencode/sana-1-5-1-6b)
- [Sana Sprint](https://spiral.ai/integrations/opencode/sana-sprint)
- [Sana](https://spiral.ai/integrations/opencode/sana)
- [Seedream 4.0 Edit](https://spiral.ai/integrations/opencode/seedream-4-0-edit)
- [SAM 3.1 Image to RLE](https://spiral.ai/integrations/opencode/sam-3-1-image-to-rle)
- [Seedream 4.0 Text to Image](https://spiral.ai/integrations/opencode/seedream-4-0-text-to-image)

## Questions about Sana 1.5 4.8B in opencode

**Can opencode use Sana 1.5 4.8B?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Sana 1.5 4.8B like any built-in tool.

**How much does Sana 1.5 4.8B cost in opencode?**

$0.013 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 4.8B in opencode?**

No. Spiral runs Sana 1.5 4.8B 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 4.8B in opencode?**

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

**Does opencode wait while Sana 1.5 4.8B runs?**

Sana 1.5 4.8B runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

**What is Sana 1.5 4.8B useful for?**

Use it for illustrations, concept art, and visual design exploration from written descriptions. Start with tasks where you can review the composition and refine the brief.

**Does Sana 1.5 4.8B generate 4K images?**

The served model is advertised for 4K output. The maker describes the underlying checkpoint as using a 1024-pixel base resolution, so distinguish output dimensions from native training resolution.

**Can Sana 1.5 4.8B make posters with readable text?**

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

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

The maker documents imperfect photorealism and possible errors in fingers. Check hands closely before using a portrait or a scene with people.

**Should I increase guidance or generation steps?**

More steps usually improve image quality. Higher guidance pushes the image toward the description but can hurt quality, so change one setting at a time and compare the results.

