> For the complete documentation index, see [llms.txt](https://luw-ai.gitbook.io/luw.ai-app-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://luw-ai.gitbook.io/luw.ai-app-docs/3d-and-video/3dspace-ai.md).

# 3DSpace AI

Stage furniture in a 3D version of your room photo and render the result. A beta tool.

3DSpace AI turns a room photo into a 3D scene, lets you add furniture to it, and then renders the scene as a realistic photo. It's for trying real furniture pieces in a real room.

{% hint style="warning" %}
3DSpace is in beta. The app says: "This AI model is in beta - results may vary."
{% endhint %}

## What you need

* A photo of the room.
* Furniture as 3D models (GLB, GLTF or OBJ), or photos you turn into models with 3DGen AI.
* Credits for each render. See [Credits](#credits).

## Stage and render a room

3DSpace has three steps: **Upload an image**, **Select editing area** and **Customize and Generate**. The title reads **3DSpace BETA**.

<figure><img src="https://1930792265-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F4yESzclcaZeSiIDZ8eIa%2Fuploads%2Fgit-blob-737280a3ec3b56a1b226114f9fbcffc5ea21a79f%2F3dspace-upload.webp?alt=media" alt="3DSpace BETA screen with the three steps Upload an image, Select editing area and Customize and Generate at the top, the History and Change Persona bar, and an empty upload area with Upload your image and Generate Image with AI"><figcaption><p>3DSpace starts like the other tools, with a photo upload.</p></figcaption></figure>

1. Open **3DSpace** from the Dashboard, or pick **3DSpace AI** in **All Tools**.
2. Upload a photo of the room. See [Uploading images](/luw.ai-app-docs/working-with-images/uploading-images.md).
3. In the second step, press **Get started**. The app builds a 3D scene from your photo. Wait until it's done.
4. Add furniture from the **Add Furniture** panel:
   * **Generate 3D Model with AI** makes a model from a photo, using 3DGen AI.
   * **Upload 3D Model** adds your own GLB, GLTF or OBJ file.
   * **Import from Projects & Favorites** adds 3D models you've saved.
   * **Import from Gallery** adds a model from a library of examples.
5. When the scene looks right, press **Save & Continue**.
6. In **Customize and Generate**, choose a **Visual Strength** and press **Generate Image with AI**. The render is made from a snapshot of your 3D scene and appears in **Latest Designs**.

## Settings

| Setting                      | What it does                                                                                                               |
| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| **History & Change Persona** | Switches to another persona or starts a new one. See [Personas and history](/luw.ai-app-docs/getting-started/personas.md). |
| **Visual Strength**          | **Precise** keeps closer to the snapshot of your scene, **Creative** changes more. **Balanced** is the default.            |

3DSpace has no prompt, **Designs** or style settings.

## Credits

Each render uses 3 credits. Furniture you make with **Generate 3D Model with AI** is charged like [3DGen AI](/luw.ai-app-docs/3d-and-video/3dgen-ai.md). See [Credits and engines](/luw.ai-app-docs/getting-started/credits-and-engines.md).

## Tips

* Make your furniture models first with [3DGen AI](/luw.ai-app-docs/3d-and-video/3dgen-ai.md) and save them to a project or to your favorites. They then show up under **Import from Projects & Favorites**.
* The **Cancel** button at the top of the staging panel resets your whole design. Use it with care.
* The in-app info note suggests **Creative** when you want reflections and richer lighting in the render.
* Because it's a beta, results vary. If a render isn't right, adjust the scene and generate again.

## Related

* [3DGen AI](/luw.ai-app-docs/3d-and-video/3dgen-ai.md)
* [Interior AI](/luw.ai-app-docs/redesign-spaces/interior-ai.md)
* [Uploading images](/luw.ai-app-docs/working-with-images/uploading-images.md)
* [The result viewer](/luw.ai-app-docs/results/result-viewer.md)