> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/video-generation/input-controls/keywords.md).

# Keywords

Keywords are structured input controls that extend and refine what your prompt describes. Where a prompt sets the scene in natural language, keywords give you precise, reliable control over motion style, camera behavior, visual quality, lighting, and focus — with consistent results across generations.

***

#### How Keywords Work

Keywords are selected from categorized panels in the Input Controls area. When added to a generation, they are appended to your prompt as structured directives that influence how the model interprets and generates the video. Multiple keywords from different categories can be combined in a single generation.

{% hint style="warning" icon="lightbulb" %}
Think of keywords as precision tools. Your prompt sets the creative direction — keywords fine-tune the technical and stylistic execution.
{% endhint %}

***

#### Motion Keywords

Motion keywords control how subjects and the camera move within the scene.

| Keyword        | Effect                                   |
| -------------- | ---------------------------------------- |
| **Static**     | No camera movement — fixed, stable shot  |
| **Move Left**  | Camera or subject moves left             |
| **Move Right** | Camera or subject moves right            |
| **Move Up**    | Camera or subject moves upward           |
| **Move Down**  | Camera or subject moves downward         |
| **Zoom In**    | Camera closes in on the subject          |
| **Zoom Out**   | Camera pulls back from the subject       |
| **Pan Right**  | Camera rotates horizontally to the right |
| **Pan Left**   | Camera rotates horizontally to the left  |

{% hint style="warning" icon="lightbulb" %}
Combine motion keywords with camera movement descriptors in your prompt for the most controlled output — e.g., **Zoom In** keyword + *"slow dolly forward"* in the prompt.
{% endhint %}

***

#### Focus Keywords

Focus keywords control depth of field and shot framing.

| Keyword                    | Effect                                                       |
| -------------------------- | ------------------------------------------------------------ |
| **Shallow Depth of Field** | Background blurred, subject sharp — isolates the subject     |
| **Bokeh**                  | Soft, circular background blur — cinematic and aesthetic     |
| **Close-Up Shot**          | Tight framing on subject detail                              |
| **Short Shot**             | Slightly wider than close-up — head and shoulders framing    |
| **Medium Wide Shot**       | Subject visible from waist up with environment context       |
| **Extreme Wide Shot**      | Subject small within a large environment — establishes scale |

***

#### Lens Keywords

Lens keywords simulate different camera lens types and their visual characteristics.

| Keyword           | Effect                                                         |
| ----------------- | -------------------------------------------------------------- |
| **Macro Lens**    | Extreme close-up detail — ideal for small subjects or textures |
| **Zoom Lens**     | Optical zoom effect with perspective compression               |
| **Infrared Lens** | Infrared color effect — surreal, high-contrast aesthetic       |

***

#### Enhancement Keywords

Enhancement keywords improve overall visual quality and add cinematic polish to the output.

| Keyword             | Effect                                                    |
| ------------------- | --------------------------------------------------------- |
| **Cinematic**       | Adds filmic quality, widescreen feel, and dramatic pacing |
| **4K**              | Signals high-resolution, highly detailed output           |
| **Sharp Focus**     | Ensures subject clarity and crisp edges                   |
| **Photorealistic**  | Pushes the model toward real-world visual accuracy        |
| **Highly Detailed** | Increases surface texture and environmental detail        |
| **Photo Shoot**     | Clean, well-lit, professionally framed aesthetic          |

***

#### Lighting Keywords

Lighting keywords define how the scene is lit — affecting mood, contrast, and visual tone.

| Keyword           | Effect                                                         |
| ----------------- | -------------------------------------------------------------- |
| **Hard Lighting** | High contrast, defined shadows — dramatic and intense          |
| **Soft Lighting** | Diffused, gentle light — flattering and natural                |
| **Key Lighting**  | Single dominant light source — studio or portrait look         |
| **Golden Hour**   | Warm, orange-tinted natural light — sunrise or sunset feel     |
| **Neon Lighting** | Vivid artificial colored light — urban and cyberpunk aesthetic |
| **Backlit**       | Light source behind the subject — silhouette or halo effect    |

***

#### Landscape & Environment Keywords

Environment keywords set the broader atmospheric and geographical context of the scene.

| Keyword               | Effect                                      |
| --------------------- | ------------------------------------------- |
| **Sunrise**           | Early morning warm light and atmosphere     |
| **Stream Landscape**  | Flowing water in a natural setting          |
| **Urban Environment** | City streets, buildings, and infrastructure |
| **Forest**            | Dense natural tree cover and foliage        |
| **Desert**            | Arid, sandy or rocky open landscape         |
| **Ocean**             | Open water, waves, coastal setting          |

***

#### Negative Keywords

Negative keywords tell the model what to **exclude** from the generation. They are as important as positive keywords for controlling output quality and eliminating unwanted elements.

**Common negative keywords to use:**

| Negative Keyword       | What It Removes                              |
| ---------------------- | -------------------------------------------- |
| **Blur**               | Reduces unwanted motion blur or soft focus   |
| **Low quality**        | Discourages pixelated or low-fidelity output |
| **Distortion**         | Reduces warping or unnatural deformation     |
| **Watermark**          | Removes visible watermarks or text overlays  |
| **Extra limbs**        | Reduces anatomical errors in human subjects  |
| **Duplicate subjects** | Prevents unwanted subject repetition         |
| **Text**               | Removes generated text from the video        |

{% hint style="info" %}
Always include negative keywords when generating human subjects — `extra limbs`, `distortion`, and `duplicate subjects` significantly reduce common anatomical errors in AI video.
{% endhint %}

***

#### Combining Keywords Effectively

Keywords are most powerful when used in coordinated combinations. Here are recommended sets by use case:

1. **Cinematic product showcase:** `Cinematic` + `Shallow Depth of Field` + `Key Lighting` + `Sharp Focus` + `4K`
2. **Social media lifestyle clip:** `Move Right` + `Golden Hour` + `Bokeh` + `Highly Detailed` + `Photorealistic`
3. **Dramatic landscape reveal:** `Zoom Out` + `Extreme Wide Shot` + `Cinematic` + `Hard Lighting` + `4K`
4. **Close-up texture or detail shot:** `Macro Lens` + `Sharp Focus` + `Soft Lighting` + `Highly Detailed` + `Static`
5. **Urban night scene:** `Neon Lighting` + `Cinematic` + `Pan Right` + `Shallow Depth of Field` + `Highly Detailed`


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.qolaba.ai/video-generation/input-controls/keywords.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.