Skip to main content
Generate a series of architectural concept images by extracting a single variable (like material) from a prompt and driving it from a separate node. Once the pattern is set up you can swap concrete for rammed earth or translucent glass without touching the rest of the prompt. Time: 8 minutes You’ll need: A Runchat account (free Starter plan is fine)

Open the example workflow

Make a copy of this workflow in your account to follow along.

​
1. Add an image model

Open a new workflow. Double-click the canvas and type Flux 2 Klein to add a Flux 2 Klein node. Flux 2 Klein is fast and cheap, so it’s the right model for this kind of exploration. You’ll swap it for something higher-quality once you find a direction you like.

​
2. Write a baseline prompt

Architectural prompts work best when they mention three things:
  1. Subject: what’s in the image
  2. Lighting: golden hour, raking light, overcast, dawn
  3. Rendering style: naming “architectural photography” or a photographer pushes the model toward grounded imagery instead of generic AI aesthetic
Avoid generic adjectives like “cinematic” or “beautiful”. Specific words and named references give the model something to latch onto. For this example, paste in:
Click Run in the node header. You’ll get a single image.

​
3. Generate variations

One image is rarely enough when you’re feeling out a concept. Select the node and set the variations control on its toolbar to 4 images, then click Run again. Page through the results with the strip under the image (1 of 4), or drag a thumbnail onto the canvas to keep it as its own node.

​
4. Extract a variable into its own node

Right now the prompt is one lump of text. Swapping “concrete” for “rammed earth” means rewriting the prompt every time. Instead, pull that word out into its own node:
  1. Click + next to the agent composer and choose Text to add a text input. Type concrete
  2. Double-click the input’s title and rename it to material (so it’s clear what it does later)
  3. Click into the Flux 2 Klein prompt field
  4. Type @ to open the reference picker
  5. Pick material. It drops into your prompt as a chip
  6. Edit the prompt so the chip replaces the word concrete
Now changing the text input from concrete to rammed earth to translucent glass updates the image prompt automatically. Each value gives you a fresh set of variations without rewriting the prompt. For more on inline references, see Data Referencing and Connecting Nodes.

​
5. Drive the variable from an agent

A text input is one source. You could swap it for any other node that produces text, including an Agent node that generates a list of materials for you.
  1. Add an Agent node
  2. Open More (…) on its toolbar and set Output format to List
  3. Prompt it: Generate 5 architectural materials for a pavilion. Return a single word or short phrase per item.
  4. Click Run on the Agent node
  5. In the image prompt, reference the agent’s list output with @ instead of the text input
Because the agent’s output is a list, each item becomes a separate run of the image model. With variations set to 2, a list of 5 items gives you 10 images out of one run.
Drop variations down to 2 when driving from an agent list. Otherwise a list of 5 items at 4 variations each blows out into 20 images per run. See Credits for cost details.

​
6. Swap models for the final pass

Once you spot a direction you like, swap the Flux 2 Klein model for Muse Image or Flux 2 Pro for higher-quality output. Keep your prompt and the rest of the workflow, just select the image node and click Swap model on its toolbar. This is the iterate-cheap-then-finalise pattern, covered in more detail in the media node reference.

​
Next steps