How to Use Recraft V3 Image to Image in Muse Code
Use Recraft V3 Image to Image to restyle an existing visual or explore changes to its composition and colors. Unlike Recraft V3 Text to Image, it starts with a source image, with strength controlling how far the result moves from it.
Prompts to try with Recraft V3 Image to Image in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use Recraft V3 Image to Image to restyle the existing onboarding illustration in the project's assets as a hand-drawn illustration. Ask to retain its subject placement and compare change strengths of 0.3 and 0.6.
Use Recraft V3 Image to Image to reinterpret the project's hero photo as an editorial illustration in the site's palette. Ask to keep the composition, start with a change strength of 0.5, and show the result beside the original.
Generate a product photo with Recraft V3 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 Recraft V3 Image to Image.
Create a 16:9 hero image of a quiet mountain cabin at dusk with Recraft V3 Image to Image.
How to set up Recraft V3 Image to Image in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse 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 Recraft V3 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/recraft/v3/image-to-image", "input": { "prompt": "winter", "image_url": "https://storage.googleapis.com/falserverless/model_tests/recraft/recraft-upscaler-1.jpeg" } }'
Then paste one of the prompts above: Muse Code finds Recraft V3 Image to Image on Spiral, shows the price and runs it.
Recraft V3 Image to Image providers and prices
Spiral runs Recraft V3 Image to Image through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Recraft V3 Image to Image works from your prompt and image URL. Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Strength | 0 to 1 | 0.5 | Defines the difference with the original image, should lie in [0, 1], where 0 means almost identical, and 1 means miserable similarity |
| Style | any, realistic_image, digital_illustration, vector_illustration, realistic_image/b_and_w, realistic_image/hard_flash, realistic_image/hdr, realistic_image/natural_light and 77 more | realistic_image | The style of the generated images. Vector images cost 2X as much. |
| Negative prompt | what to leave out, in words | A text description of undesired elements on an image |
Every API field of Recraft V3 · Image to Image is on its tool page: open its card above.
What can you do with Recraft V3 Image to Image in Muse Code?
Build website illustrations and campaign artwork from the project's visual requirements with Recraft V3. A coding agent can use the project's copy and palette to write concrete image briefs and review the results in context.
Event poster concepts
Develop a poster with an illustrated subject and an embedded event title. Start from a written brief or rework an existing poster image.
Editorial illustrations
Illustrate an article's central idea with a specific arrangement of objects. Create the scene from a description or reinterpret an existing visual.
Campaign graphics
Develop graphics around an established visual style and color palette. Use a written campaign brief or an existing campaign image as the starting point.
Website illustrations
Create an illustration for an onboarding screen or article header. Describe the intended scene or restyle an existing illustration to match the site's direction.
Photographic advertising concepts
Explore a photographic scene with specified subjects, colors, and object placement. Work from a written concept or reinterpret an existing photo.
Presentation artwork
Develop a visual metaphor for a presentation, such as three separate paths converging on one destination. Generate it from a brief or adapt an existing image.
Photo-to-illustration restyling
Turn a source photo into an illustration while asking to retain its composition. Compare a lower change strength with a higher one to choose the desired departure.
More on Recraft V3 Image to Image and Muse Code
Overview
Recraft V3 Image to Image in other agents
Questions about Recraft V3 Image to Image in Muse Code
Can Muse Code use Recraft V3 Image to Image?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Recraft V3 Image to Image like any built-in tool.
How much does Recraft V3 Image to Image cost in Muse Code?
$0.052 per image. 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 Recraft V3 Image to Image in Muse Code?
No. Spiral runs Recraft V3 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 Recraft V3 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 Recraft V3 Image to Image runs?
Recraft V3 Image to Image runs in the background. Muse Code starts the run, checks on it and gives you the image when it's ready.
What is Recraft V3 useful for?
Recraft V3 suits posters, editorial illustrations, photographic concepts, and designs with embedded lettering. Its scene following also makes it useful when a brief specifies object counts, colors, and placement.
Can Recraft V3 generate readable text inside an image?
Yes. Text rendering is a documented strength, including longer passages. Put the exact wording in quotation marks and check the result before using it.
How detailed should a Recraft V3 prompt be?
Keep it within 1,000 characters. Describe the subject, then specify the important counts, colors, and positions so the visual brief is concrete.
Can Recraft V3 keep a consistent visual style across several images?
Yes. Recraft V3 supports style consistency from example images without retraining. Reuse the same established style when producing a campaign or illustration series.
Is Recraft V3 only useful for illustrations?
No. Photorealism and text rendering are also documented strengths, so briefs can call for photographic scenes as well as illustrated designs.
Start using Recraft V3 Image to Image in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


