How to Use Wan 2.6 Text to Image in Claude Code
Wan 2.6 Text to Image creates illustrations and scene concepts from a written description, with an optional image for style guidance. Unlike Wan 2.6 Image to Image, it can start without a reference image.
Prompts to try with Wan 2.6 Text to Image in Claude Code
Copy an example into Claude Code, or ask in your own words.
Read the homepage brief in this project. Use Wan 2.6 Text to Image to create a 1280 by 720 pixel editorial image of a coastal observatory at dusk, with the building on the right and open sky on the left for the headline.
Use Wan 2.6 Text to Image to create a 1024 by 1024 pixel watercolor illustration of a small greenhouse after rain. Match the palette described in the project's design brief, use an eye-level view, and save the result with the other article images.
Generate a product photo with Wan 2.6 Text 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 2.6 Text to Image.
Create a 16:9 hero image of a quiet mountain cabin at dusk with Wan 2.6 Text to Image.
How to set up Wan 2.6 Text 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 2.6 Text 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": "wan/v2.6/text-to-image", "input": { "prompt": "An ancient library floating among clouds, golden hour light streaming through massive windows, photorealistic" } }'
Then paste one of the prompts above: Claude Code finds Wan 2.6 Text to Image on Spiral, shows the price and runs it.
Wan 2.6 Text to Image providers and prices
Spiral runs Wan 2.6 Text to Image through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Wan 2.6 Text to Image works from your prompt and image URL. Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Content to avoid in the generated image. Max 500 characters. | |
| Max images | 1 to 5 | 1 | Maximum number of images to generate (1-5). Actual count may be less depending on model inference. |
| Seed | a whole number | Random seed for reproducibility (0-2147483647). |
Every API field of Wan v2.6 Text to Image is on its tool page: open its card above.
What can you do with Wan 2.6 Text to Image in Claude Code?
Create image assets that follow a project's art direction, framing, and lighting requirements. A coding agent can turn a design brief into image prompts and place the resulting assets in the interface.
Illustration style studies
Explore watercolor, ink, or photographic treatments for the same scene. Supply a style reference and keep the subject description and framing consistent between attempts.
Editorial cover imagery
Create an image for an article or newsletter, using a reference to guide the visual treatment. Specify where the main subject belongs and reserve open space for a headline added later.
Packaging mood boards
Explore materials, colors, lighting, and settings around a packaging concept. Use a visual reference for art direction and treat the result as a design study.
Seasonal social imagery
Develop seasonal compositions around a supplied style reference. Keep the palette and camera angle consistent while changing props, weather, or time of day.
Scene concepts from a written brief
Create an environment or illustration without preparing a reference image. Describe the subject, setting, art style, camera position, and lighting.
More on Wan 2.6 Text to Image and Claude Code
Overview
Wan 2.6 Text to Image in other agents
Questions about Wan 2.6 Text to Image in Claude Code
Can Claude Code use Wan 2.6 Text to Image?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Wan 2.6 Text to Image like any built-in tool.
How much does Wan 2.6 Text to Image cost in Claude Code?
$0.039 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 2.6 Text to Image in Claude Code?
No. Spiral runs Wan 2.6 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 2.6 Text to Image in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Wan 2.6 Text to Image runs?
Wan 2.6 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 2.6 good at?
Wan 2.6 is useful for exploring visual styles and directing composition, camera angle, and lighting. Product scenes, editorial illustrations, and art direction studies are practical uses.
How should I write a Wan 2.6 image prompt?
Describe the subject, setting, and style first, then add the camera angle, lighting, and details that matter. For example, specify a ceramic cup on a wooden table, photographed from above in soft window light.
Can I prompt Wan 2.6 in English or Chinese?
Yes, both languages are supported. Keep the image description within 2,000 characters.
What image dimensions should I use?
A 1280 by 1280 pixel square is a practical choice. For wider or taller compositions, 1280 by 720 or 720 by 1280 pixels also fit the documented output limits.
Does a fixed seed guarantee an identical image?
No. Alibaba says results can vary even with the same seed, so save an approved image instead of relying on regeneration to reproduce it exactly.
Start using Wan 2.6 Text 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


