[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Wan 2.2 5B Text to Image](https://spiral.ai/integrations/claude-code/wan-2-2-5b-text-to-image)

# How to Use Wan 2.2 5B Text to Image in Claude Code

Wan 2.2 5B Text to Image creates photorealistic still images from written descriptions, with an emphasis on fine visual detail. Use it for scene concepts and photographic compositions where lighting and texture matter.

|  |  |
| --- | --- |
| Model | Wan 2.2 5B Text to Image |
| Available through | fal |
| Category | Image |
| Price | $0.0208 per image. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Wan 2.2 5B Text to Image in Claude Code

- Read the homepage copy and design notes in this project. Use Wan 2.2 5B Text to Image to create a 1280 by 720 photographic hero concept that reflects the main subject, with the subject on the right and open space on the left for the headline.
- Read the product brief in this project. Use Wan 2.2 5B Text to Image to create a photographic tabletop concept of the described object, specifying its materials, a matte background, and soft side lighting. Treat it as a shoot concept.
- Read the latest article draft in this project and propose one concrete photographic scene for it. Use Wan 2.2 5B Text to Image to generate that scene at 1280 by 720, with natural light and a clear focal subject.
- Use the room description in this project's design brief to create an interior concept with Wan 2.2 5B Text to Image. Describe the viewpoint, furniture materials, wall finish, and direction of daylight before generating it.
- Use Wan 2.2 5B Text to Image to create two photographic concepts for this project's repair article: a worn wooden workbench with metal tools and a ceramic lamp under repair. Keep the scene description and 40 sampling steps unchanged; increase guidance slightly for the second image and compare prompt adherence and visible quality.

## How to set up Wan 2.2 5B Text to Image in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code 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 Wan 2.2 5B 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/wan/v2.2-5b/text-to-image",
    "input": {
      "prompt": "In this breathtaking wildlife documentary, we are drawn into an intimate close-up of a majestic lion'\''s face, framed against the backdrop of a vast African…"
    }
  }'
```

Then paste one of the prompts above: Claude Code finds Wan 2.2 5B Text to Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## Wan 2.2 5B Text to Image tools and prices

- [Wan 5B · Text to Image](https://spiral.ai/tools/fal/fal-ai/wan/v2.2-5b/text-to-image) (fal): $0.0208 per image.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | Negative prompt for video generation. |
| seed |  | — | Random seed for reproducibility. If None, a random seed is chosen. |
| num_inference_steps | 2 to 50 | 40 | Number of inference steps for sampling. Higher values give better quality but take longer. |
| enable_prompt_expansion |  | false | Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. |
| guidance_scale | 1 to 10 | 3.5 | Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. |
| shift | 1 to 10 | 2 | Shift value for the image. Must be between 1.0 and 10.0. |

## What can you do with Wan 2.2 5B Text to Image in Claude Code?

Create photographic assets from the project's written content and design requirements. Translate those requirements into specific subjects, framing, lighting, and texture before generating images.

### Website hero photography concepts

Generate a photographic scene from a written brief, specifying the subject placement and leaving space for a headline added during design.

### Product photography planning

Explore a proposed tabletop shoot through text descriptions of an unbranded object, its materials, the backdrop, and the lighting.

### Editorial image concepts

Turn an article's theme into a photographic scene, such as a crowded workbench for a story about repair or reuse.

### Interior design mood studies

Explore imagined rooms by describing furniture, finishes, daylight direction, and the viewpoint.

### Food photography concepts

Plan a food scene with specific ingredients, ceramic textures, table surfaces, and window light.

### Film preproduction stills

Describe one proposed shot to explore its framing, location, lighting, and color before a shoot.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## Wan 2.2 5B Text to Image in other agents

- [Amp](https://spiral.ai/integrations/amp/wan-2-2-5b-text-to-image)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/wan-2-2-5b-text-to-image)
- [Claude](https://spiral.ai/integrations/claude-desktop/wan-2-2-5b-text-to-image)
- [Cline](https://spiral.ai/integrations/cline/wan-2-2-5b-text-to-image)
- [Codex](https://spiral.ai/integrations/codex/wan-2-2-5b-text-to-image)
- [Cursor](https://spiral.ai/integrations/cursor/wan-2-2-5b-text-to-image)
- [Devin](https://spiral.ai/integrations/devin/wan-2-2-5b-text-to-image)
- [dots](https://spiral.ai/integrations/dots/wan-2-2-5b-text-to-image)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/wan-2-2-5b-text-to-image)
- [Gemini](https://spiral.ai/integrations/gemini/wan-2-2-5b-text-to-image)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/wan-2-2-5b-text-to-image)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/wan-2-2-5b-text-to-image)
- [goose](https://spiral.ai/integrations/goose/wan-2-2-5b-text-to-image)
- [Grok](https://spiral.ai/integrations/grok/wan-2-2-5b-text-to-image)
- [Grok Build](https://spiral.ai/integrations/grok-build/wan-2-2-5b-text-to-image)
- [Hermes](https://spiral.ai/integrations/hermes/wan-2-2-5b-text-to-image)
- [Instinct](https://spiral.ai/integrations/instinct/wan-2-2-5b-text-to-image)
- [Manus](https://spiral.ai/integrations/manus/wan-2-2-5b-text-to-image)
- [Muse](https://spiral.ai/integrations/muse/wan-2-2-5b-text-to-image)
- [Muse Code](https://spiral.ai/integrations/muse-code/wan-2-2-5b-text-to-image)
- [n8n](https://spiral.ai/integrations/n8n/wan-2-2-5b-text-to-image)
- [Notion](https://spiral.ai/integrations/notion/wan-2-2-5b-text-to-image)
- [OpenClaw](https://spiral.ai/integrations/openclaw/wan-2-2-5b-text-to-image)
- [opencode](https://spiral.ai/integrations/opencode/wan-2-2-5b-text-to-image)
- [Perplexity](https://spiral.ai/integrations/perplexity/wan-2-2-5b-text-to-image)
- [Raycast](https://spiral.ai/integrations/raycast/wan-2-2-5b-text-to-image)
- [VS Code](https://spiral.ai/integrations/vscode/wan-2-2-5b-text-to-image)
- [Windsurf](https://spiral.ai/integrations/windsurf/wan-2-2-5b-text-to-image)
- [Zapier](https://spiral.ai/integrations/zapier/wan-2-2-5b-text-to-image)

## More Claude Code guides

- [Vidu Reference to Image](https://spiral.ai/integrations/claude-code/vidu-reference-to-image)
- [Wan 2.2 A14B Image to Image](https://spiral.ai/integrations/claude-code/wan-2-2-a14b-image-to-image)
- [Vidu Q2 Text to Image](https://spiral.ai/integrations/claude-code/vidu-q2-text-to-image)
- [Wan 2.2 A14B Text to Image](https://spiral.ai/integrations/claude-code/wan-2-2-a14b-text-to-image)
- [Vidu Q2 Reference to Image](https://spiral.ai/integrations/claude-code/vidu-q2-reference-to-image)
- [Wan 2.2 A14B Text to Image LoRA](https://spiral.ai/integrations/claude-code/wan-2-2-a14b-text-to-image-lora)

## Questions about Wan 2.2 5B Text to Image in Claude Code

**Can Claude Code use Wan 2.2 5B Text to Image?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Wan 2.2 5B Text to Image like any built-in tool.

**How much does Wan 2.2 5B Text to Image cost in Claude Code?**

$0.0208 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need a fal account to use Wan 2.2 5B Text to Image in Claude Code?**

No. Spiral runs Wan 2.2 5B 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 Wan 2.2 5B Text to Image in Claude Code?**

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

**Does Claude Code wait while Wan 2.2 5B Text to Image runs?**

Wan 2.2 5B Text to Image runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.

**What is Wan 2.2 5B Text to Image good for?**

Its documented focus is photorealistic imagery with fine visual detail. Consider it for photographic scene concepts where materials, lighting, and composition carry the idea.

**Does Wan 2.2 5B Text to Image make videos?**

It generates still images from text. Write the prompt around the frame you want to see.

**How should I write a photographic prompt?**

Describe the subject, framing, setting, light, and visible textures. The published example uses a lion close-up with specific fur detail and dawn lighting.

**Will stronger guidance always improve the image?**

Higher guidance can improve adherence to your description, but the documentation warns that quality may decrease. Try a small increase when an important detail is missing, then compare the results.

**Is it worth using more sampling steps?**

The documentation says higher step counts improve quality while taking longer, and gives 40 as the default. Compare results on your actual scene before choosing a higher count.

