> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runchat.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Create masks by Rhino material

> Capture a black-and-white mask of one material in Rhino and use it to edit only that material in a render

Your Rhino model already knows where every material is. Capture a flat mask of one material from the same view as your render, then use it in a masked edit to change only that surface.

![A render, a mask of the wall cladding from Rhino, and the render with only the cladding replaced](https://mintcdn.com/runchat/ExzxwftWKPCOoCF3/images/examples/masks-by-rhino-material.webp?fit=max\&auto=format\&n=ExzxwftWKPCOoCF3\&q=85\&s=1c04e81312ae54dae604d7454da7ab54)

> [card] [Open the example workflow](https://runchat.com/editor?id=d230ba31-8ae2-4685-b366-ae86cbe17d54)
>
> Make a copy of this workflow in your account to try it with your own images.

## How it works

1. **Render (Nano Banana Pro)** turns the linework view into a photograph.
2. **Mask of one material** is a flat capture from Rhino: the matching material in one colour, everything else in another. The Rhino node finds the material by keyword (here *cladding*).
3. **Fit mask to render** resizes the mask to the render and makes the area to edit black.
4. **Masked edit: swap cladding (Ideogram 4.5)** changes only the masked area: *replace the blackened timber cladding with natural silver-grey weathered cedar shiplap boards*.

## Tips

* Capture the mask from the exact same view and aspect ratio as the render, or it won't line up.
* Ideogram treats black as the area to edit. Other inpainting models may expect white: check the model's description.

## Use your own model

The image input holds a capture from our demo Rhino model, so the workflow runs as it is. To use your own model, open Rhino with the [Runchat plugin](https://docs.runchat.com/plugins/rhino.md) signed in, set up your view, and run the node marked **(optional) Rhino**. Then drag its screenshot into the image input. The scripts use only the standard display modes and match layers or materials by the keywords in their inputs, so they work on any model.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.