# Run the example

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/)
- [Introduction to neural graphics and Neural Super Sampling (NSS)](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/1-install-plugin/)
- [Setting up the emulation layers](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/2-emulation-layer/)
- [Create an example game](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/3-create-example/)
- [Run the example](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/3-run-example/)
- [Using RenderDoc for Debugging and Analysis](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/5-renderdoc/)
- [Wrapping up](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/6-wrapping-up/)
- [Next Steps](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/_next-steps/)

## Start the level and verify NSS

1. Enable NSS before starting the level. The plugin checkbox alone does not enable NSS, which defaults to `0`. Run this command in the Unreal Engine console:
   ```
   r.NSS.Enable 1
   ```
2. Press the green **Play** button to start the level.
3. In the running game’s console, verify NSS with:
   ```
   ShowFlag.VisualizeTemporalUpscaler 1
   ```
   Confirm that **ThirdParty TemporalUpscaler** reports **NSS** in the rendering summary.

<ads-card><ads-card-label>Tip</ads-card-label>
<ads-card-content>

To save the NSS setting for future sessions, select **Enable** under **NSS** in **Edit > Project Settings > Plugins > Neural Graphics 1.1.0**.

</ads-card-content></ads-card>

Run `ShowFlag.VisualizeTemporalUpscaler 0` to disable the overview. To visualize the NSS model output in real-time, run the following command:
```
r.NSS.Debug 1
```
This will add real-time views showing the model’s processed outputs, such as predicted filter coefficients and feedback, as below. In the [Wrapping up section](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/6-wrapping-up/), you will find links to learn more about what the debug outputs mean.

![Image Alt Text:Debug view of Neural Super Sampling model output in Unreal Engine](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/images/nss_debug.png)  
*Figure 6: Visualize NSS model debug output in real time.*

## NSS console variables

Use these Unreal Engine console variables to configure NSS behavior, debug views, and resource lifetime. Enter a variable and value in the Unreal Engine console, for example, `r.NSS.Enable 1`.

| Console variable                                | Default | Value range       | Details                                                      |
|-------------------------------------------------|---------|-------------------|--------------------------------------------------------------|
| `r.NSS.Enable`                                  | `0`     | `0`, `1`          | Enables NSS for Temporal Upscale.                           |
| `r.NSS.EnableInEditorViewport`                  | `0`     | `0`, `1`          | Enables NSS for Temporal Upscale in the editor viewport.    |
| `r.NSS.Debug` (UE 5.4 and UE 5.6)               | `0`     | `0`, `1`          | Displays 16 debug outputs in a 4x4 grid.                   |
| `r.NSS.Debug` (UE 4.27)                         | `0`     | `0`, `1`          | Displays 12 debug outputs in a 3x4 grid.                   |
| `r.NSS.AdjustMipBias`                           | `1`     | `0`, `1`          | Allows NSS to adjust the minimum global texture mip bias: `r.ViewTextureMipBias.Min` and `r.ViewTextureMipBias.Offset`. |
| `r.NSS.ShaderQualityMode`                       | `1`     | `0`, `1`, `2`     | Selects shader quality: `0` for quality (high), `1` for balanced (default), and `2` for performance (low). |
| `r.NSS.UseFragmentShader`                       | `1`     | `0`, `1`          | Uses a fragment job for NSS.                                 |
| `r.NG.DeferDelete`                              | `5`     | `> 0`             | Sets the number of frames to defer deletion.                |

## Troubleshooting tips

If the example does not behave as expected, check the following common issues before continuing.

### Plugin missing or build failed

If the plugin is missing, first check that `NG.uplugin` is directly inside your engine-specific plugin folder. If the build failed, first inspect the earliest error for your project’s editor target in Visual Studio’s **Output > Build**. Follow the [plugin setup and build checks](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/3-create-example/#enable-the-plugin).

### NSS absent from the rendering summary

- First query `r.NSS.Enable` without a value and confirm that it reports `1`.
- Verify that Vulkan is selected as the **Default RHI**.
- Confirm the **Arm Neural Graphics Plugin** is enabled and that Unreal Engine was restarted after enabling it.
- Check **Edit > Project Settings > Plugins > Neural Graphics 1.1.0** to confirm that NSS is enabled.

If the Arm Neural Graphics Plugin is enabled but NSS appears to have no effect:
- Confirm that you installed version 0.10.0 or later of the standalone [ML Emulation Layer for Vulkan](https://github.com/arm/ai-ml-emulation-layer-for-vulkan).
- Ensure Vulkan Configurator is running.
- Verify that the correct layer configuration is selected and active.
- Double-check that:
  - The emulation layer path points to the extracted release’s `bin` directory
  - The Graph layer is ordered above the Tensor layer

Refer back to the [emulation layer section](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/2-emulation-layer/) for the full Vulkan Configurator setup and validation steps.

### Debug view absent

First confirm that `ShowFlag.VisualizeTemporalUpscaler 1` reports NSS while the game is running. Then hide the overview and run `r.NSS.Debug 1` again. Use **Play** for this check; NSS is disabled in the non-playing editor viewport by default.

### Check the software and hardware setup

- Confirm that you’re using Arm Neural Graphics Plugin 1.1.0 with a supported Unreal Engine version.
- Verify that your GPU driver supports Vulkan.
- Verify that your Visual Studio version aligns with the Unreal Engine version you are using.
- Return to the Visual Studio build output and inspect the logs carefully to identify the first reported error.

Build or startup failures are often caused by version mismatches or missing dependencies.

## NSS model on Hugging Face

The model that powers NSS is published on Hugging Face in the [VGF format](https://github.com/arm/ai-ml-sdk-vgf-library). This format is optimized for inference via ML extensions for Vulkan.

Visit the [NSS model page on Hugging Face](https://huggingface.co/Arm/neural-super-sampling/)  
On this landing page, you can read more about the model, and learn how to run a test case - a *scenario* - using the ML SDK for Vulkan.

## Result

You now have Neural Super Sampling integrated and running inside Unreal Engine. This setup provides a real-time testbed for neural upscaling.

Proceed to the next section to debug your frames using RenderDoc, or move on to the final section to explore more resources on the technology behind NSS.