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

opencode · Image

How to Use RunDiffusion Photo Flux in opencode

RunDiffusion Photo Flux makes photographic portraits, product concepts, and cinematic stills from text. Its photo enhancer emphasizes skin and surface texture, with a recommended weight of 0.65 to 0.80.

Prompts to try with RunDiffusion Photo Flux in opencode

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

Read the homepage copy in this project, then use RunDiffusion Photo Flux to create a photographic hero concept at 1536 × 1024. Describe a concrete subject, soft side lighting, and space on the left for the heading.

RunDiffusion Photo Fluxopencode
Try asking
  • Use RunDiffusion Photo Flux to generate a 1024 × 1024 concept for the fictional desk lamp described in the product brief. Show brushed aluminum, a linen shade, and soft studio reflections from a three-quarter camera angle.

  • Read the character brief and use RunDiffusion Photo Flux to make a fictional portrait at 1024 × 1536. Specify an 85 mm lens look, window light, visible skin texture, and a plain background.

  • Use RunDiffusion Photo Flux to create a 1536 × 1024 cinematic still based on the opening scene in this project's script. Translate the scene into subject placement, camera angle, materials, and lighting.

  • Use RunDiffusion Photo Flux to build a comparison of photo enhancer weights 0.65, 0.75, and 0.80 for a walnut chair with a woven seat. Keep the prompt, seed, and 1024 × 1024 size fixed, then make a contact sheet.

How to set up RunDiffusion Photo Flux 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 RunDiffusion Photo Flux

    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/rundiffusion-photo-flux",
        "input": {
          "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture…"
        }
      }'

Then paste one of the prompts above: opencode finds RunDiffusion Photo Flux on Spiral, shows the price and runs it.

RunDiffusion Photo Flux providers and prices

Spiral runs RunDiffusion Photo Flux through fal. Open a card for today's price, with every fee included.

falImage
Rundiffusion Photo Flux
rundiffusion-fal/rundiffusion-photo-flux

Settings you can ask for

RunDiffusion Photo Flux works from your prompt. Ask opencode for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Photo LoRA scalea number0.75

LoRA Scale of the photo lora model

Number of inference steps1 to 5028

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)0 to 353.5

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 pngjpeg

The format of the generated image.

Every API field of Rundiffusion Photo Flux is on its tool page: open its card above.

What can you do with RunDiffusion Photo Flux in opencode?

Turn project briefs into photographic assets for design review. A coding agent can read project copy and plan compositions around the intended placement.

Portrait concepts

Explore fictional character portraits with specific skin detail and lighting.

Product photography concepts

Plan studio compositions for imagined products, including surface finishes and reflections.

Material studies

Explore fabric, wood, plastic, and metal appearances under a defined light source.

Film mood boards

Turn scene descriptions into photographic stills for discussing framing and lighting.

Architectural concepts

Visualize imagined buildings with specified construction materials and camera viewpoints.

Fashion shoot planning

Explore clothing textures, locations, and photographic treatments before a shoot.

Questions about RunDiffusion Photo Flux in opencode

Can opencode use RunDiffusion Photo Flux?

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

How much does RunDiffusion Photo Flux cost in opencode?

$0.0585 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. 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 opencode plan is separate.

Do I need a fal account to use RunDiffusion Photo Flux in opencode?

No. Spiral runs RunDiffusion Photo Flux on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up RunDiffusion Photo Flux in opencode?

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

Does opencode wait while RunDiffusion Photo Flux runs?

RunDiffusion Photo Flux runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

What is RunDiffusion Photo Flux best at?

Photographic portraits, product concepts, material studies, and cinematic stills. Its emphasis is believable skin, surfaces, and lighting.

How should I prompt RunDiffusion Photo Flux?

Describe the subject, material, lighting, lens, and camera angle. For example, specify brushed steel under soft side lighting rather than asking only for a realistic object.

What is the maximum output resolution?

The documented maximum is 1536 × 1536 pixels.

What photo enhancer weight should I use?

Start within the recommended 0.65 to 0.80 range. Compare results with the same prompt and seed while changing only the weight.

Where does RunDiffusion Photo Flux struggle?

Painterly styles and exact pose or layout control are weaker fits. Low resolutions and overly aggressive settings can also introduce artifacts.

Get started

Start using RunDiffusion Photo Flux 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