Spiral gives your agent every tool with one account. Browse the tools →

opencode · Image

How to Use Juggernaut Flux Pro Image to Image in opencode

Juggernaut Flux Pro Image to Image creates a new photographic interpretation of an existing image. Unlike Juggernaut Flux Pro, it uses a reference image alongside your written description.

Prompts to try with Juggernaut Flux Pro Image to Image in opencode

Copy an example into opencode, or ask in your own words.

Use Juggernaut Flux Pro Image to Image with the interior reference in this project's assets. Create a photographic cafe concept with oak furniture, woven upholstery, and overcast window light; compare strength 0.8 and 0.95.

Juggernaut Flux Pro Image to Imageopencode
Try asking
  • Use Juggernaut Flux Pro Image to Image with the product reference in this project's assets. Interpret it as a studio photograph on pale stone with side lighting; compare guidance 2.5 and 3.5 and inspect the reflections.

  • Generate a product photo with Juggernaut Flux Pro 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 Juggernaut Flux Pro Image to Image.

  • Create a 16:9 hero image of a quiet mountain cabin at dusk with Juggernaut Flux Pro Image to Image.

How to set up Juggernaut Flux Pro Image to Image in opencode

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

Use Spiral's MCP server

  1. Add the server

    Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

    opencode mcp add spiral --global --url https://api.spiral.ai/mcp
  2. Sign in

    Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.

    opencode mcp auth spiral
  3. Check it

    Spiral shows as connected.

    opencode mcp list

Use the Spiral skill

  1. Send opencode 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.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Juggernaut Flux Pro 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": "rundiffusion-fal/juggernaut-flux/pro/image-to-image",
        "input": {
          "image_url": "https://fal.media/files/koala/Chls9L2ZnvuipUTEwlnJC.png",
          "prompt": "a cat dressed as a wizard with a background of a mystic forest."
        }
      }'

Then paste one of the prompts above: opencode finds Juggernaut Flux Pro Image to Image on Spiral, shows the price and runs it.

Juggernaut Flux Pro Image to Image providers and prices

Spiral runs Juggernaut Flux Pro Image to Image through fal. Open a card for today's price, with every fee included.

falImage
Juggernaut Flux Pro · Image to Image
rundiffusion-fal/juggernaut-flux/pro/image-to-image

Settings you can ask for

Juggernaut Flux Pro Image to Image works from your image URL and prompt. Ask opencode for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Strength0.01 to 10.95

The strength of the initial image. Higher strength values are better for this model.

Number of inference steps10 to 5040

The number of inference steps to perform.

Seeda whole number

The same seed and the same prompt given to the same version of the model

will output the same image every time.

Guidance scale (CFG)1 to 203.5

The CFG (Classifier Free Guidance) scale is a measure of how close you want

the model to stick to your prompt when looking for a related image to show you.

Number of images1 to 41

The number of images to generate.

Output formatjpeg or pngpng

The format of the generated image.

Every API field of Juggernaut Flux Pro · Image to Image is on its tool page: open its card above.

What can you do with Juggernaut Flux Pro Image to Image in opencode?

Create photographic image assets for landing pages, demos, and editorial layouts while working in your project. Turn the design brief into concrete directions for materials, lighting, and composition.

Product photography concepts

Explore a ceramic mug, perfume bottle, or other product in a photographic setting. Specify the surface, reflections, camera angle, and lighting.

Editorial portrait concepts

Develop portrait ideas around skin texture, wardrobe, expression, and directional light. Compare a studio treatment with a natural-light setting.

Fashion and fabric studies

Preview garment concepts with specific fabrics, folds, and lighting. Use the images to discuss how linen, wool, or silk should read in an editorial shoot.

Interior mood boards

Explore room concepts through furniture, wood grain, stone, upholstery, and window light. Keep each image focused on one material palette.

Architectural concept images

Visualize a building's materials and atmosphere for an early design discussion. Describe the facade, surrounding landscape, viewing angle, and time of day.

Cinematic still concepts

Develop a photographic frame for a storyboard or pitch. Direct the scene through a specific location, subject, light source, and camera position.

Reference image reinterpretation

Start with an existing image and describe a new photographic treatment. Compare different strength settings before choosing how much reinterpretation suits the brief.

Questions about Juggernaut Flux Pro Image to Image in opencode

Can opencode use Juggernaut Flux Pro Image to Image?

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Juggernaut Flux Pro Image to Image like any built-in tool.

How much does Juggernaut Flux Pro Image to Image cost in opencode?

Up to $0.0715 per run at the default inputs. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

Do I need a fal account to use Juggernaut Flux Pro Image to Image in opencode?

No. Spiral runs Juggernaut Flux Pro 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 Juggernaut Flux Pro Image to Image in opencode?

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

Does opencode wait while Juggernaut Flux Pro Image to Image runs?

Juggernaut Flux Pro Image to Image runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

What is Juggernaut Flux Pro good at?

Photographic portraits, product concepts, fashion imagery, and realistic environments. Skin, fabric, lighting, and material texture are useful reasons to choose it.

How should I write a Juggernaut Flux Pro prompt?

Describe the subject, setting, materials, lighting, and camera viewpoint. Use concrete photographic directions, such as a 50mm lens or shallow depth of field, and avoid stacking conflicting styles.

How many generation steps should I test?

Runware recommends 25 to 35 steps for Juggernaut Flux Pro. Treat that range as a starting point and compare fine textures and lighting before increasing the count.

Should I increase guidance when a detail is missing?

Try a clearer description first. Higher guidance can improve adherence, but it can also make the result look less natural.

Is Juggernaut Flux Pro useful for fashion concepts?

Yes. RunDiffusion highlights garment previews, fashion portraits, and material visualization, particularly where fabric texture and lighting matter.

Get started

Start using Juggernaut Flux Pro Image to Image in opencode

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into opencode:

Set up opencode

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options