# Input Controls

The Input Controls panel sits on the left side of the Video Generation workspace. This is where you define everything that goes *into* a generation — your prompt, reference media, and keywords. Together these inputs determine the scene, motion, style, and visual direction of your generated video.

***

#### What's in the Input Controls Panel

| Control              | What It Does                                                                                |
| -------------------- | ------------------------------------------------------------------------------------------- |
| **Prompt**           | Describes the scene, subject, motion, and environment in natural language                   |
| **Magic Prompt**     | AI-enhanced version of your prompt for better generation results                            |
| **Initial Image**    | Sets the first frame of the video                                                           |
| **Last Frame Image** | Sets the final frame — model generates the motion between both frames                       |
| **Reference Files**  | Uploads image, video, or audio as a creative reference (model dependent)                    |
| **Keywords**         | Structured controls for motion, focus, lens, lighting, enhancement, and negative exclusions |

***

#### How Inputs Work Together

Your prompt is the foundation of every generation. Keywords refine and extend what the prompt describes — adding precise cinematic, motion, and stylistic direction that natural language alone cannot reliably produce. Reference media anchors the generation visually, giving the model a concrete starting point, ending point, or stylistic reference to work from.

For best results, combine all three:

* A **clear, descriptive prompt** for scene and narrative direction
* **Relevant keywords** for motion style, lens type, and visual quality
* **Reference media** when visual consistency with existing assets matters

***

#### What's in This Section

* [Prompt & Magic Prompt →](/video-generation/input-controls/prompt-and-magic-prompt.md)
* [Reference Media Uploads →](/video-generation/input-controls/reference-media-uploads.md)
* [Keywords →](/video-generation/input-controls/keywords.md)


---

# 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://docs.qolaba.ai/video-generation/input-controls.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.