# Background Removal AI

{% @arcade/embed flowId="CkY0Ze9Thd9cqcWGthAG" url="<https://app.arcade.software/share/CkY0Ze9Thd9cqcWGthAG>" %}

*\*If the tool is not available, you may need to use the **Upgrade** option*

Automatically remove the background behind one or multiple subjects in your photo. The neural network in Background RemovalAI can detect the main subject and up to nine types of other elements in your photo, and you can select which ones to keep. Plus, use a refinement brush to fix any imperfections. Here’s a step-by-step guide on using Background RemovalAI in Luminar Neo:

1. **Select an image:** click the Edit tab
2. **Layer Properties:** select the Masking tab and choose Background RemovalAI
3. **Selection:** Select the chosen main object or choose from additional elements found in the image.
4. **Remove the background:** Click “Remove” to initiate the Background Removal process. Luminar Neo will remove the image’s background, revealing a transparent checkbox background.
5. **Click Refinement Brush for additional finetuning:** A Transition Mask will appear, highlighting Transition in a white checkerboard pattern, Object in orange, and Background in blue. Select a brush and apply it to refine each section.

The final image will appear with a transparent background. Use Layers to add a new background and move the layer to the bottom of the Layers palette. This will reveal the image on a new background.

***

Location in Neo: Edit view -> Layer Properties -> Masking&#x20;

Discover more efficient workflow tips:

{% embed url="<https://skylum.com/blog/improve-photo-backgrounds?utm_campaign=content&utm_medium=organic&utm_source=support>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://support.skylum.com/editing-tools/layers/background-removal-ai.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.