How to Use Wan 2.2 A14B Image to Image in Claude Code
Wan 2.2 A14B Image to Image reworks an existing image using a written description. Unlike Wan 2.2 A14B Text to Image, it lets you control how much of the original image survives.
Prompts to try with Wan 2.2 A14B Image to Image in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Wan 2.2 A14B Image to Image with the kitchen photograph in the project's assets. Explore warm evening light and muted wood tones at strength 0.25, then compare the result with the source composition.
Use Wan 2.2 A14B Image to Image with the project's approved reading-room image. Compare reconstruction strengths of 0.25 and 0.5 for a brief requesting oak shelves, olive upholstery, and soft window light; keep the seed fixed.
Generate a product photo with Wan 2.2 A14B 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 2.2 A14B Image to Image.
Create a 16:9 hero image of a quiet mountain cabin at dusk with Wan 2.2 A14B Image to Image.
How to set up Wan 2.2 A14B Image to Image in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- 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
- Send Claude Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Wan 2.2 A14B Image to Image
One request; the result comes back by polling or a webhook.
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-a14b/image-to-image", "input": { "image_url": "https://storage.googleapis.com/falserverless/example_inputs/wan-image-to-image-input.png", "prompt": "A cinematic shot of an ancient city at sunset, intricate stone buildings, warm golden light" } }'
Then paste one of the prompts above: Claude Code finds Wan 2.2 A14B Image to Image on Spiral, shows the price and runs it.
Wan 2.2 A14B Image to Image providers and prices
Spiral runs Wan 2.2 A14B Image to Image through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Wan 2.2 A14B Image to Image works from your image URL and prompt. Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Strength | 0 to 1 | 0.5 | Denoising strength. 1.0 = fully remake; 0.0 = preserve original. |
| Negative prompt | what to leave out, in words | Negative prompt for video generation. | |
| Seed | a whole number | Random seed for reproducibility. If None, a random seed is chosen. | |
| Aspect ratio | auto, 16:9, 9:16, or 1:1 | auto | Aspect ratio of the generated image. If 'auto', the aspect ratio will be determined automatically based on the input image. |
| Number of inference steps | 2 to 40 | 27 | Number of inference steps for sampling. Higher values give better quality but take longer. |
| Enable prompt expansion | on or off | off | Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. |
| Acceleration | none or regular | regular | Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. |
| Guidance scale | 1 to 10 | 3.5 | Classifier-free guidance scale. |
| Guidance scale (2nd stage) | 1 to 10 | 4 | Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model. |
| Shift | 1 to 10 | 2 | |
| Image format | png or jpeg | jpeg | The format of the output image. |
Every API field of Wan is on its tool page: open its card above.
What can you do with Wan 2.2 A14B Image to Image in Claude Code?
Create photographic assets while working on a website or app. Turn the project's visual brief into scene descriptions and compare lighting or composition treatments before choosing an image.
Editorial scene illustrations
Develop photographic concepts for an article, such as a bicycle outside a neighborhood repair shop. Specify the setting, lighting, and space needed for a headline.
Product staging concepts
Explore how an unbranded ceramic mug might look on linen, stone, or a wooden counter. Use the results to compare photographic direction before planning a shoot.
Interior mood studies
Compare room concepts through wood tones, upholstery, daylight, and contrast. Treat each image as a visual direction to review.
Film still concepts
Explore a single scene's framing, lighting, and color treatment before production. Describe one photographic composition, such as an empty train platform at dawn.
Lighting studies from an existing image
Start with a supplied room or scene image and explore a different lighting treatment. Compare lower and higher reconstruction strengths to judge how much source detail changes.
More on Wan 2.2 A14B Image to Image and Claude Code
Overview
Wan 2.2 A14B Image to Image in other agents
Questions about Wan 2.2 A14B Image to Image in Claude Code
Can Claude Code use Wan 2.2 A14B Image to Image?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Wan 2.2 A14B Image to Image like any built-in tool.
How much does Wan 2.2 A14B Image to Image cost in Claude Code?
$0.065 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 A14B Image to Image in Claude Code?
No. Spiral runs Wan 2.2 A14B 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 2.2 A14B Image to Image in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Wan 2.2 A14B Image to Image runs?
Wan 2.2 A14B Image to Image runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.
Does Wan 2.2 A14B produce still images?
Yes. The image models covered here produce still images, despite the Wan name also appearing on video models.
What is Wan 2.2 A14B useful for?
Photographic scene concepts are a good starting point: editorial illustrations, product staging ideas, interior mood studies, and film still concepts. Its image descriptions emphasize realism and fine visual detail.
How should I describe the image I want?
A practical starting point is to name the subject and setting, then specify lighting, framing, contrast, and color tone. This recommendation follows the Wan team's description of its aesthetic training labels.
Will stronger guidance always improve the result?
No. Stronger guidance can improve prompt adherence while reducing image quality, so compare modest changes against the original result.
When should I use prompt expansion?
Try it when your brief is short and you want additional descriptive detail. For a carefully specified composition, compare it with expansion turned off so you can judge whether the additions help.
Start using Wan 2.2 A14B Image to Image in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


