[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [Wan 2.5 Image to Image](https://spiral.ai/integrations/muse-code/wan-2-5-image-to-image)

# How to Use Wan 2.5 Image to Image in Muse Code

Wan 2.5 Image to Image edits reference images with instructions while preserving the subject. Unlike Wan 2.5 Text to Image, it can combine elements from existing images for product scenes and visual revisions.

|  |  |
| --- | --- |
| Model | Wan 2.5 Image to Image |
| Available through | fal |
| Category | Image |
| Price | $0.065 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 Wan 2.5 Image to Image in Muse Code

- Use Wan 2.5 Image to Image to revise the product photo in public/assets: replace the background with a sunlit kitchen counter. Preserve the product's shape and color, request 1024 × 1024, and show the result beside the original.
- Use Wan 2.5 Image to Image on our existing article illustration to change its treatment to watercolor. Keep the main subject and composition, request 1280 × 720, and add the result to a local preview.
- Generate a product photo with Wan 2.5 Image 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 Wan 2.5 Image to Image.
- Create a 16:9 hero image of a quiet mountain cabin at dusk with Wan 2.5 Image to Image.

## How to set up Wan 2.5 Image to Image in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse 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 2.5 Image 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-25-preview/image-to-image",
    "input": {
      "prompt": "Reimagine the scene under a raging thunderstorm at night: lightning forks across the sky, illuminating the samurai in stark flashes of white light.",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: Muse Code finds Wan 2.5 Image to Image on Spiral, shows the price and runs it.

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

## Wan 2.5 Image to Image tools and prices

- [Wan 2.5 · Image to Image](https://spiral.ai/tools/fal/fal-ai/wan-25-preview/image-to-image) (fal): $0.065 per image. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  | — | Negative prompt to describe content to avoid. Max 500 characters. |
| image_size |  | square | The size of the generated image. Width and height must be between 384 and 1440 pixels. |
| num_images | 1 to 4 | 1 | Number of images to generate. Values from 1 to 4. |
| seed |  | — | Random seed for reproducibility. If None, a random seed is chosen. |

## What can you do with Wan 2.5 Image to Image in Muse Code?

Turn project briefs into artwork you can inspect in the actual page layout with Wan 2.5. Let the coding agent prepare focused image instructions and place reviewed results beside the relevant content.

### Product campaign concepts

Create a product scene from a written brief with Wan 2.5 Text to Image, or restage a supplied product photo with Wan 2.5 Image to Image. Specify the surface, lighting, and room for copy.

### Article cover artwork

Illustrate an article's central idea from text or revise supplied artwork. Use a wide composition with a clear focal point and deliberate space for the title.

### Social campaign artwork

Draft square campaign images from a brief or adapt an existing campaign image. Specify one message, a defined palette, and a simple composition for review.

### Illustration style exploration

Explore watercolor, photographic, or painterly treatments of a scene. Start from a description with Wan 2.5 Text to Image or a supplied image with Wan 2.5 Image to Image.

### Product photo background changes

Use Wan 2.5 Image to Image to place a supplied product in a different setting. State which product details should remain and describe the replacement background and lighting.

### Reference image composites

Use Wan 2.5 Image to Image to combine an object from one supplied image with a scene from another. Identify each image's role and specify placement, scale, and lighting.

## Overview

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

## Wan 2.5 Image to Image in other agents

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

## More Muse Code guides

- [Wan 2.2 A14B Text to Image LoRA](https://spiral.ai/integrations/muse-code/wan-2-2-a14b-text-to-image-lora)
- [Wan 2.5 Text to Image](https://spiral.ai/integrations/muse-code/wan-2-5-text-to-image)
- [Wan 2.2 A14B Text to Image](https://spiral.ai/integrations/muse-code/wan-2-2-a14b-text-to-image)
- [Wan 2.6 Image to Image](https://spiral.ai/integrations/muse-code/wan-2-6-image-to-image)
- [Wan 2.2 A14B Image to Image](https://spiral.ai/integrations/muse-code/wan-2-2-a14b-image-to-image)
- [Wan 2.6 Text to Image](https://spiral.ai/integrations/muse-code/wan-2-6-text-to-image)

## Questions about Wan 2.5 Image to Image in Muse Code

**Can Muse Code use Wan 2.5 Image to Image?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Wan 2.5 Image to Image like any built-in tool.

**How much does Wan 2.5 Image to Image cost in Muse Code?**

$0.065 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 Muse Code plan is separate.

**Do I need a fal account to use Wan 2.5 Image to Image in Muse Code?**

No. Spiral runs Wan 2.5 Image 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 2.5 Image to Image in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while Wan 2.5 Image to Image runs?**

Wan 2.5 Image to Image runs in the background. Muse Code starts the run, checks on it and gives you the image when it's ready.

**How should I write a Wan 2.5 prompt?**

Describe the subject, setting, visual style, camera angle, lighting, and composition. As a practical starting point, give each instruction a clear purpose, such as leaving empty space above the subject for a headline.

**Can I prompt Wan 2.5 in English or Chinese?**

Yes, Wan 2.5 accepts instructions in English and Chinese. Use concrete descriptions of what should appear in the image.

**What image dimensions should I start with?**

A practical starting point is 1024 × 1024 for square artwork or 1280 × 720 for a wide composition. Both sizes fit the documented limits for Wan 2.5 image generation and editing.

**Can Wan 2.5 produce native 4K square images?**

No. A 4096 × 4096 output exceeds the documented limits for Wan 2.5 image generation and editing; plan a separate enlargement step if you need that size.

**Will using the same seed reproduce an image exactly?**

A fixed seed helps compare results, but it does not guarantee an identical image. Save an approved output instead of relying on regenerating it later.

