> 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/image-generation/input-controls/keywords.md).

# Keywords

Keywords are structured visual modifiers that extend and refine what your prompt describes. Where a prompt sets the scene in natural language, keywords give you precise, reliable control over focus, lighting, shot composition, lens characteristics, and output quality — producing more consistent results across generations.

***

#### How Keywords Work

Keywords are selected from categorized sections in the input controls area and appended to your prompt as structured visual directives. They work alongside your prompt — not instead of it. A strong prompt combined with well-chosen keywords produces significantly more consistent and controlled output than either alone.

{% hint style="info" %}
Use your prompt to describe *what* is in the image. Use keywords to control *how* it looks — the lighting, depth, framing, and quality.
{% endhint %}

***

#### Focus & Depth Keywords

Control depth of field and subject sharpness.

| Keyword                    | Effect                                                                |
| -------------------------- | --------------------------------------------------------------------- |
| **Shallow Depth of Field** | Background blurred, subject sharp — isolates subject from environment |
| **Deep Focus**             | Full scene in sharp focus — everything is equally clear               |
| **Bokeh**                  | Soft, circular background blur — aesthetic and cinematic              |
| **Soft Focus**             | Gentle overall blur — dreamy, romantic quality                        |
| **Background Blur**        | Blurs the background while keeping foreground sharp                   |
| **Sharp Foreground**       | Ensures foreground elements are crisp and detailed                    |

***

#### Shot Size Keywords

Control how tightly the subject is framed within the image.

| Keyword         | Effect                                                 |
| --------------- | ------------------------------------------------------ |
| **Close-Up**    | Tight framing on subject detail — face, hands, product |
| **Medium Shot** | Subject from waist up — standard portrait framing      |
| **Wide Angle**  | Broad view with subject in environmental context       |
| **Overhead**    | Bird's-eye view looking straight down                  |
| **Low Angle**   | Camera positioned below subject — adds drama and scale |
| **Macro Shot**  | Extreme close-up — fine detail and texture             |

***

#### Lens Keywords

Simulate different camera lens types and their visual characteristics.

| Keyword                   | Effect                                                           |
| ------------------------- | ---------------------------------------------------------------- |
| **35mm Lens**             | Natural, true-to-life perspective — standard photographic look   |
| **85mm Portrait Lens**    | Flattering compression, shallow depth — classic portrait lens    |
| **Fisheye**               | Extreme wide-angle with barrel distortion — dramatic and surreal |
| **Tilt-Shift**            | Selective focus with a miniature-like effect                     |
| **Wide-Angle Distortion** | Exaggerated perspective at edges — dynamic and expansive         |

***

#### Lighting Keywords

Define how the scene is lit — affecting mood, contrast, and visual tone.

| Keyword                | Effect                                                           |
| ---------------------- | ---------------------------------------------------------------- |
| **Golden Hour**        | Warm, orange-tinted natural light — sunrise or sunset atmosphere |
| **Studio Lighting**    | Clean, controlled light — professional and even                  |
| **Cinematic Lighting** | Dramatic, high-contrast — filmic and atmospheric                 |
| **Soft Ambient**       | Diffused, gentle light — natural and flattering                  |
| **Neon Lighting**      | Vivid artificial colored light — urban and cyberpunk aesthetic   |
| **High Contrast**      | Strong highlights and deep shadows — bold and graphic            |
| **Dramatic Shadows**   | Hard shadows with defined edges — intense and moody              |
| **Flat Lighting**      | Minimal shadows — clean, even, product-photography style         |

***

#### Artistic Style Keywords

Define the visual medium, aesthetic, or rendering approach.

| Keyword            | Effect                                                |
| ------------------ | ----------------------------------------------------- |
| **Photorealistic** | Pushes output toward real-world visual accuracy       |
| **Oil Painting**   | Rich texture, visible brushstrokes, painterly quality |
| **Watercolor**     | Soft edges, translucent washes, textured paper feel   |
| **Anime**          | Japanese animation aesthetic — cel-shaded, expressive |
| **Cyberpunk**      | Neon-lit, futuristic urban dystopia aesthetic         |
| **Minimalist**     | Clean, simple composition — reduced to essentials     |
| **3D Render**      | Computer-generated three-dimensional aesthetic        |

***

#### Enhancement Keywords

Improve overall visual quality and production value.

| Keyword                 | Effect                                             |
| ----------------------- | -------------------------------------------------- |
| **Ultra-Detailed**      | Maximum surface texture and environmental detail   |
| **Hyper-Realistic**     | Extreme photographic accuracy and fine detail      |
| **8K Resolution**       | Signals highest fidelity and sharpness             |
| **High Texture Detail** | Emphasizes surface materials and tactile qualities |
| **Sharp Focus**         | Ensures crisp, clear subject edges and detail      |
| **4K**                  | High-resolution, detailed output                   |

***

#### 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.

Enter negative keywords in the dedicated **Negative Prompt** field — not in the main prompt.

**Common negative keywords:**

| Negative Keyword          | What It Removes                                      |
| ------------------------- | ---------------------------------------------------- |
| **No extra fingers**      | Reduces anatomical errors in hands                   |
| **No distorted face**     | Improves facial accuracy                             |
| **No background clutter** | Produces cleaner, more focused compositions          |
| **No text**               | Removes unintended text appearing in the image       |
| **No watermark**          | Removes visible watermarks                           |
| **No grain**              | Reduces noise and film grain                         |
| **No artifacts**          | Removes rendering glitches and compression artifacts |
| **No blur**               | Reduces unwanted soft focus or motion blur           |

{% hint style="info" %}
Always include negative keywords when generating human subjects — `no extra fingers`, `no distorted face`, and `no artifacts` significantly reduce the most common generation errors for portraits and figure images.
{% endhint %}

***

#### Combining Keywords Effectively

Keywords work best in coordinated sets. Here are recommended combinations by use case:

1. **Professional product photography:** `Studio Lighting` + `Sharp Focus` + `Flat Lighting` + `4K` + `No Background Clutter` + `No Artifacts`
2. **Cinematic portrait:** `85mm Portrait Lens` + `Shallow Depth of Field` + `Cinematic Lighting` + `Dramatic Shadows` + `Ultra-Detailed`
3. **Editorial lifestyle image:** `Golden Hour` + `35mm Lens` + `Soft Ambient` + `Wide Angle` + `Photorealistic` + `4K`
4. **Fantasy concept art:** `Cinematic Lighting` + `Deep Focus` + `Oil Painting` + `Ultra-Detailed` + `High Texture Detail` + `No Artifacts`
5. **Minimalist brand visual:** `Flat Lighting` + `Studio Lighting` + `Minimalist` + `Sharp Focus` + `4K` + `No Background Clutter` + `No Shadows`
6. **Urban night scene:** `Neon Lighting` + `Cinematic Lighting` + `35mm Lens` + `Shallow Depth of Field` + `Hyper-Realistic`


---

# 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/image-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.