[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Z-Image Turbo LoRA](https://spiral.ai/integrations/opencode/z-image-turbo-lora)

# How to Use Z-Image Turbo LoRA in opencode

Z-Image Turbo LoRA creates images with custom style adapters applied during generation. Unlike Z-Image Turbo, it lets you carry a trained visual style into new scenes without retraining the underlying model.

|  |  |
| --- | --- |
| Model | Z-Image Turbo LoRA |
| Available through | fal |
| Category | Image |
| Price | $0.01105 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Z-Image Turbo LoRA in opencode

- Use Z-Image Turbo LoRA with the compatible style adapter already specified in this project's asset configuration. Generate a 1024 by 1024 image of a desk lamp on an oak table, with warm directional light and clearly visible brushed metal. Add the result to the product concept page.
- Read this project's design brief. Use Z-Image Turbo LoRA with its configured compatible style adapter to create a 1024 by 1024 reading-room concept: low oak shelves, a rust-colored chair beside a window, late-afternoon light, and an eye-level camera. Add it to the design review page.
- Generate a product photo with Z-Image Turbo LoRA: 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 Z-Image Turbo LoRA.
- Create a 16:9 hero image of a quiet mountain cabin at dusk with Z-Image Turbo LoRA.

## How to set up Z-Image Turbo LoRA 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 Z-Image Turbo LoRA**: 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/z-image/turbo/lora",
    "input": {
      "prompt": "A hyper-realistic, close-up portrait of a tribal elder from the Omo Valley, painted with intricate white chalk patterns and adorned with a headdress made of…"
    }
  }'
```

Then paste one of the prompts above: opencode finds Z-Image Turbo LoRA on Spiral, shows the price and runs it.

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

## Z-Image Turbo LoRA tools and prices

- [Z Image Turbo Lora · Text to Image](https://spiral.ai/tools/fal/fal-ai/z-image/turbo/lora) (fal): $0.01105 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | landscape_4_3 | The size of the generated image. |
| num_inference_steps | 1 to 8 | 8 | 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. |
| num_images | 1 to 4 | 1 | The number of images to generate. |
| output_format | jpeg, png, webp | png | The format of the generated image. |
| acceleration | none, regular, high | regular | The acceleration level to use. |

## What can you do with Z-Image Turbo LoRA in opencode?

Create photographic assets and bilingual graphic drafts alongside the project you are building. Your coding agent can turn repository copy and layout requirements into detailed Z-Image Turbo briefs, then place the results in the interface.

### Product scene concepts

Explore a product idea from a written description. Specify materials, camera position, surface, and lighting to compare studio and lifestyle treatments.

### Portrait art direction

Draft fictional portraits for a campaign or story. Describe age, expression, clothing, setting, and light to make each direction concrete.

### English and Chinese poster drafts

Create poster concepts with specified English or Chinese lettering. Give the exact headline, its placement, and the scene around it, then proofread the result.

### Editorial cover images

Turn an article's central idea into a concrete photographic scene. Define the subject and composition before generating, especially when the topic involves factual details.

### Website image concepts

Generate imagery for a landing page or feature section from a written brief. Describe where the subject sits and reserve clear space for HTML headings.

### Interior mood studies

Compare room concepts through explicit descriptions of furniture, finishes, daylight, and camera angle. Use the results to discuss a visual direction.

### Campaign images with a trained style

Apply a compatible custom style LoRA to new campaign scenes. Keep the visual brief consistent while changing subjects, settings, and compositions.

## Overview

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

## Z-Image Turbo LoRA in other agents

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

## More opencode guides

- [Z-Image Turbo](https://spiral.ai/integrations/opencode/z-image-turbo)
- [fal Blur](https://spiral.ai/integrations/opencode/fal-blur)
- [Z-Image Base LoRA](https://spiral.ai/integrations/opencode/z-image-base-lora)
- [fal Desaturate](https://spiral.ai/integrations/opencode/fal-desaturate)
- [Z-Image Base](https://spiral.ai/integrations/opencode/z-image-base)
- [fal Expression Change](https://spiral.ai/integrations/opencode/fal-expression-change)

## Questions about Z-Image Turbo LoRA in opencode

**Can opencode use Z-Image Turbo LoRA?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Z-Image Turbo LoRA like any built-in tool.

**How much does Z-Image Turbo LoRA cost in opencode?**

$0.01105 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. 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 Z-Image Turbo LoRA in opencode?**

No. Spiral runs Z-Image Turbo LoRA on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Z-Image Turbo LoRA in opencode?**

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

**Does opencode wait while Z-Image Turbo LoRA runs?**

Z-Image Turbo LoRA runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

**What is Z-Image Turbo good at?**

Photorealistic images and designs containing English or Chinese text are its clearest strengths. Try portraits, product scene concepts, editorial images, and poster drafts.

**Which languages does Z-Image Turbo support?**

Tongyi specifically documents English and Chinese instruction following and text rendering. Those are the best-supported choices for prompts and lettering inside images.

**How should I write a Z-Image Turbo prompt?**

Use a detailed visual description: identify the subject, its action, the setting, lighting, materials, and framing. For lettering, spell out the exact words and describe where they belong.

**Does Z-Image Turbo support negative prompts?**

No. Describe the desired result directly, such as a plain backdrop, sharp focus, or an empty tabletop.

**How many generation steps should I use?**

Start with eight steps, the generation process documented by Tongyi. Use that as your baseline while refining the description and composition.

