> 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/output-settings-and-controls/dimensions-and-aspect-ratio.md).

# Dimensions and Aspect Ratio

Dimensions control the shape and pixel proportions of your generated image. Selecting the right dimensions before generating ensures your output fits its intended platform or format without cropping, stretching, or requiring post-generation resizing.

***

#### How Dimensions Work

Dimensions define the **aspect ratio** and **pixel size** of the generated output. Qolaba provides a range of preset dimensions — including standard orientations and platform-specific sizes — so you can match your output to its intended destination without manual calculation.

Dimensions do not affect credit cost. You can change them freely without impacting your generation budget.

***

#### Available Dimension Presets

**Standard Orientations**

| Orientation    | Aspect Ratio | Best For                                                 |
| -------------- | ------------ | -------------------------------------------------------- |
| **Square**     | 1:1          | Instagram feed, LinkedIn posts, profile images           |
| **Portrait**   | 3:4 or 4:5   | Instagram feed portrait, Pinterest, mobile-first content |
| **Landscape**  | 16:9         | YouTube thumbnails, presentations, desktop wallpapers    |
| **Ultra-wide** | 21:9         | Cinematic banners, website headers, widescreen displays  |

**Platform-Specific Presets**

| Platform              | Recommended Preset | Use Case                                  |
| --------------------- | ------------------ | ----------------------------------------- |
| **Instagram Feed**    | 1:1 or 4:5         | Standard posts and portrait feed images   |
| **Instagram Story**   | 9:16               | Full-screen vertical story and reel cover |
| **Twitter / X**       | 16:9               | In-feed image posts                       |
| **Pinterest**         | 2:3                | Standard pin format                       |
| **YouTube Thumbnail** | 16:9               | Video thumbnail at 1280 × 720px           |
| **Facebook Cover**    | \~2.7:1            | Page header banner                        |

***

#### Choosing the Right Dimensions

1. **Match dimensions to your delivery format before generating** — resizing after generation degrades quality and introduces cropping or letterboxing. Select the dimension preset that matches where the image will be used.
2. **For multi-platform content:** Generate separate versions at the required dimensions for each platform. Because dimensions do not affect credit cost, producing a square and a portrait version of the same image costs the same as generating one — only the generation count changes.
3. **For reference-guided generation:** Match your output dimensions to the natural aspect ratio of your reference image. A portrait reference used with a landscape output dimension will be cropped or distorted in the generated output.

***

#### Dimensions and Reference Images

When uploading reference images, the aspect ratio of your reference influences how the model frames the generated output. Mismatched dimensions between your reference and output setting can result in:

* **Cropping** — parts of the reference are cut off and excluded from the generation
* **Distortion** — the reference is stretched to fill the output frame unnaturally
* **Recomposition** — the model adds padding or repositions elements to fill the frame

To avoid this, always check the aspect ratio of your reference images before selecting output dimensions. See [Reference Image Uploads →](/image-generation/input-controls/reference-images.md) for more guidance on using references effectively.


---

# 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/output-settings-and-controls/dimensions-and-aspect-ratio.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.