> For the complete documentation index, see [llms.txt](https://xfigura.gitbook.io/xfigura-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xfigura.gitbook.io/xfigura-docs/generate/image-node/inpaint-to-image.md).

# Inpaint to Image

Inpaint to Image is where your compositing work becomes a generation input. Set up your scene inside the Inpaint node — masking, layering, prompting — and pass it directly into an image generation node to produce a refined, fully generated output.

<figure><img src="https://1105741269-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FezPs4sBq27l9GhXqMswu%2Fuploads%2FeODXdAyT4OWh4T7Etptw%2FUntitled%20(15).gif?alt=media&amp;token=62fdd673-670f-476d-b807-d2c25d1bfa18" alt=""><figcaption></figcaption></figure>

**Building Your Composition** Bring in multiple images as separate layers and arrange them in the layers panel on the left.&#x20;

**Masking** Use the masking brush to define exactly which areas you want the next node to regenerate. Choose from three brush types and customize the brush size and color to build precise, controlled masks around the regions you want transformed.

**Adding a Prompt** Add text directly onto the composition to act as a generative prompt or attach a text node to the input port. Describe the change you want — a material, a lighting condition, a new element — and the image generation node will apply it to the masked area while keeping the rest of the composition intact.

**Shapes** Use the shapes tool to block out areas or add structural elements to your composition before it gets passed downstream.

**Generating the Output** Once your composition is set, connect the Inpaint node to an image generation node. The model reads your layers, masks, and prompt together and produces the final generated result.