# AI Creator

#### Requirements:

* Unity 2020.3 - 2022.2
* Anything World Account Credentials
* Anything World SDK
* Optional: Microphone

{% hint style="danger" %}
Please note: This package is not compatible out of the box with the previous (Classic) versions of Anything World. Contact us on discord or email if you have a project that needs migrating.
{% endhint %}

## Setting Up AI Creator

The AI Creator panel allows users to convert verbal or text input into real time Unity scene creation using our extensive repository of models and auto-rigging functionality.

AI Creator comes installed in our latest Anything World SDK package, see our [Unity Quickstart](https://anything-world.gitbook.io/anything-world/quickstart/unity-quickstart) guide to setup our Anything World SDK before using the AI Creator. 

After completing the Unity Quickstart guide, simply open the Anything World menu from the top tool bar and select the AI Creator option to access the AI Creator panel.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2Flz9mODzkddkKE7zWtt2E%2Fimage.png?alt=media&#x26;token=2fc6a3cb-c6ab-4984-bac4-eb7b9eaff191" alt=""><figcaption></figcaption></figure>

## Getting Start with AI Creator

Our AI Creator panel provides two methods for users to give input

* The microphone button activates the recording feature which converts verbal commands to text for ease of access in adding, removing, and moving models in the active scene during editor mode or at runtime.
* The text field provides the same functionality in enabling users to give written commands to add, remove, or move models from our extensive model database.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2F7bgLbryJwyFjgHLVIvnH%2Fimage.png?alt=media&#x26;token=46c4799e-b35c-40f0-bcb7-7872c76b51ff" alt=""><figcaption></figcaption></figure>

### Valid Commands:

Currently our AI Creator supports commands that will enable users to:

* Add one or several models to the active scene
* Move one model to a specified location
* Remove one or several models from the active scene

#### Examples:

Add commands:

* **Create** one cat
* **Add** five chickens&#x20;

Move commands:

* **Move** one chicken here&#x20;
* **Move** the cat to the left of the chicken

Remove commands:

* **Remove** the cat
* **Delete** five chickens

#### Valid Modifiers:

Quantity Modifier:

* Add **five** gorillas
* Remove **three** cats

Relative Location Modifier:

* Add one car **here**
* Move one gorilla **above** the car
* Create one cat to the **right** of the car
* Add one human to the **left** of the car
* Create a snake **below** the car

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FtkvQsbByTrszMTSqz6sv%2Fimage.png?alt=media&#x26;token=0adc9175-f7db-48ec-bc09-76127f1b8fbf" alt=""><figcaption></figcaption></figure>

#### Multiple actions can be requested in a single command

Example:

* Add one cat and one human
* Add a bumblebee and move the cat here
* Remove the human and move the bumblebee above the cat

## AI Creator Panel

The AI Creator panel features several buttons to make the creation process more streamlined.

#### Microphone Input:

The Microphone button enables the recording functionality which allows users to convert verbal commands to real-time scene creation and manipulation using our extensive 3D model database within a Unity scene. Select the microphone button once to enable the recording session and select the same button again to submit the verbal request.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FOAyOrA5qwBxucg6hXRDd%2Fimage.png?alt=media&#x26;token=2e13ac81-4186-4de6-86f6-90a19829e147" alt=""><figcaption><p>By default the five dots will be displayed beneath the microphone button.</p></figcaption></figure>

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2Fhc3ML7AXHRx4bA3Yx4Le%2Fimage.png?alt=media&#x26;token=f0fb6fc0-7bd1-4e95-819e-be9c2d2a1a1a" alt=""><figcaption><p>The five dots represents the volume of the verbal input received during recording.</p></figcaption></figure>

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FE8BG8zRAHnSeczLfBMq4%2Fimage.png?alt=media&#x26;token=26d5fbac-69a7-48f0-aa7b-4cc17770e37d" alt=""><figcaption><p>The five dots will move in a wave motion when processing the request. This animation will occur when providing verbal or written requests.</p></figcaption></figure>

#### Text Input and Submission:

The Text box provides an alternative method of providing input to our AI Creator for creation and manipulation our repository of 3D assets. To use the text box, type the request and select the submit button.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2F4MNWNbqAxwMXpjueBxkB%2Fimage.png?alt=media&#x26;token=5c484336-564f-43ac-9e12-e51f3b9a1730" alt=""><figcaption><p>Select the submit button or press the enter key to send the request to AI Creator</p></figcaption></figure>

The Results dropdown will display the input received and provide a list of actions that AI Creator will take to fulfill the desired request. Selecting the dropdown will display additional information regarding the action, the type of model, and the quantity of the models requested.&#x20;

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FPeaNiVrubjDBU3kzXCt1%2Fimage.png?alt=media&#x26;token=5a367c39-2f6b-4236-acb7-bafec5bdfe2e" alt=""><figcaption><p>Select the dropdown to see more information regarding the provided request.</p></figcaption></figure>

Once the request has been processed, the Make button will appear to the right of the requested model allowing the user to add one model at a time.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FI5XNtqVGmqcKHYvRoxSy%2Fimage.png?alt=media&#x26;token=1b74fe34-3224-4f68-81f3-6160c78bf4a2" alt=""><figcaption></figcaption></figure>

#### Make All Button and Auto Option:

When users provide multiple commands, they may select the Make All button to add, remove, or change the position of the desired model within the scene. Additionally, the Auto checkbox will automatically create, manipulate, or delete the models of the scene without requiring the user to verify the list of commands.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FNQKp5j7Pu9W7FNYx5IXT%2Fimage.png?alt=media&#x26;token=3079f23f-52df-4530-863c-241b069f34f2" alt=""><figcaption><p>Select the Auto option to skip the manual process of making each command.</p></figcaption></figure>

#### Grid Options:

Selecting the Gird Options button will open a secondary panel containing the same grid settings found in the Transform Settling panel. The Grid options can be used to specify the spacing between models inserted via the AI Creator. Make sure to select the Apply button to ensure the settings were saved before proceeding in adding more assets to your scene.

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2FWVamrhk0t5LhagJteA2o%2Fimage.png?alt=media&#x26;token=48a178b8-bf46-470e-95a5-837a273f1eef" alt=""><figcaption><p>Select the Grid Options button to open the Grid Settings Panel.</p></figcaption></figure>

<figure><img src="https://588284853-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_f9MEtTx5q1bKIGvl-%2Fuploads%2F4EyoCOwn3QwIYmjoDlDJ%2Fimage.png?alt=media&#x26;token=55c5832a-ca6c-4430-950d-ea27b50c0e4a" alt=""><figcaption><p>These settings are universally used when adding models through the Anything Browser or the AI Creator. </p></figcaption></figure>


---

# 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://anything-world.gitbook.io/anything-world/quickstart/unity-quickstart/ai-creator.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.