# Create Videos

<figure><img src="/files/q22IYhzntMOWyLWFXyms" alt=""><figcaption></figcaption></figure>

## **What is Text to Video?**

**Text to Video** is a tool designed to generate high-quality videos from textual descriptions. Simply describe a scene, action, or environment, and the AI model will generate a video that matches your vision. From dramatic action sequences to peaceful nature scenes, this feature allows creators to quickly generate engaging visual content based on nothing more than a few sentences.

{% hint style="info" %}
ImagineArt features the latest AI models alongside our proprietary options. See the model comparison at the end of this page for more details.
{% endhint %}

## **Make your first Video**

{% stepper %}
{% step %}
**Select** [**Video Mode:**](https://imagine.art/video) to begin creating your video. This will open up the video creation interface where you can input your prompt and customize the settings.
{% endstep %}

{% step %}
**Enter Your Prompt:** In the prompt field, type a detailed description of the video you want to create. The more specific you are, the better the AI will understand your needs and generate a video closer to your vision. Describe actions, scenes, and visual elements clearly.

<figure><img src="/files/DIen8atzcnWMTwpRoxAS" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}
Select the AI Video model you want to use from the available options, including WAN, **Kling**, and **Hailuo AI**, based on the video style you need (e.g., cinematic, realistic, etc.). Then, choose the **aspect ratio** and other generation settings such as video length and resolution.&#x20;

{% hint style="info" %}
Each video model has unique generation settings in terms of ratio and duration settings, please see the table below to find out model supported settings.
{% endhint %}

<figure><img src="/files/zN48DzjYoNsAhPAjoLoL" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}
**Click Create:** After finalizing your settings and prompt, click the **Generate** button. The AI will process your request and create a video based on the input you've provided.
{% endstep %}
{% endstepper %}

### Support

**Text to Video** is supported by the following models:

| **Seedance Lite**     | 4:3, 16:9, 1:1                      | 3, 4, 5, 6, 7, 8, 9, 10, 12, 13             |
| --------------------- | ----------------------------------- | ------------------------------------------- |
| **Imagine V3**        | 9:16, 16:9, 1:1                     | 5                                           |
| **Kling 1.6 SD**      | 9:16, 16:9, 1:1                     | 5, 10                                       |
| **Kling 1.6 Pro**     | 9:16, 16:9, 1:1                     | 5, 10                                       |
| **Kling 2.1 Pro**     | 9:16, 16:9, 1:1                     | 5, 10                                       |
| **Kling 2.1 SD**      | 9:16, 16:9, 1:1                     | 5, 10                                       |
| **Hailuo AI**         | 16:9                                | 6, 10                                       |
| **Hailuo O2 SD**      | 9:16, 16:9, 1:1, 2:3, 3:2, 3:4, 4:3 | 6, 10                                       |
| **Hailuo O2 Pro**     | 9:16, 16:9, 1:1, 2:3, 3:2, 3:4, 4:3 | 6, 10                                       |
| **LUMA RAY2**         | 9:16, 16:9, 3:4, 4:3                | 5                                           |
| **PixVerse 3.5**      | 9:16, 16:9, 1:1, 3:4, 4:3           | 5, 8                                        |
| **PixVerse 4**        | 9:16, 16:9, 1:1, 3:4, 4:3           | 5, 8                                        |
| **PixVerse 4.5**      | 9:16, 16:9, 1:1, 3:4, 4:3           | 5, 8                                        |
| **Google Veo 2**      | 9:16, 16:9                          | 5                                           |
| **Google Veo 3**      | 9:16, 16:9, 1:1                     | 5                                           |
| **Google Veo 3 Fast** | 9:16, 16:9, 1:1                     | 5                                           |
| **Seedance Pro**      | 1:1, 4:3, 16:9, 3:4, 9:16           | 5                                           |
| **Wan 2.2**           | 9:16, 16:9, 1:1                     | 5                                           |
| **Wan 2.5**           | 9:16, 16:9, 1:1                     | 5                                           |
| **Sora 2**            | 9:16, 16:9                          | 5, 10                                       |
| **Lucy**              | 9:16, 16:9                          | 5                                           |
| **PixVerse v5**       | 9:16, 16:9, 1:1, 3:4, 4:3           | 5, 8                                        |
| **Kling 3.0 Pro**     | 16:9, 9:16, 1:1                     | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 |
| **Runway 4.5**        | 16:9, 9:16, 1:1, 4:3, 3:4           | 5, 8, 10                                    |
| **Seedance 1.5 Pro**  | 6:9, 9:16, 3:4, 4:3, 1:1            | 4, 5, 6, 7, 8, 9, 10, 11, 12                |

Select the **aspect ratio** that fits your project’s needs.

<table><thead><tr><th width="126.64654541015625">Aspect Ratio</th><th>Usage</th></tr></thead><tbody><tr><td><strong>9:16</strong></td><td>Best for mobile-first content, Instagram Stories, and TikTok</td></tr><tr><td><strong>16:9</strong></td><td>Traditional video format, ideal for YouTube and presentations</td></tr><tr><td><strong>5:4</strong></td><td>Common for photography prints and framed artwork</td></tr><tr><td><strong>4:5</strong></td><td>Optimized for Instagram posts with more vertical space</td></tr><tr><td><strong>2:3</strong></td><td>Standard for photography, especially portraits</td></tr><tr><td><strong>3:2</strong></td><td>Classic for DSLRs and digital photography</td></tr><tr><td><strong>1:1</strong></td><td>Perfect for Instagram posts, profile pictures, and social media feeds</td></tr><tr><td><strong>3:4</strong></td><td>Frequently used for posters, digital flyers, and tablets</td></tr><tr><td><strong>4:3</strong></td><td>Traditional TV and PowerPoint presentations, used in older monitors</td></tr></tbody></table>


---

# 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://help.imagine.art/creative-suite/video-tools/create-videos.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.