> 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.md).

# Input Controls

Input Controls are where you define everything that goes into a generation — your prompt, reference images, and keywords. Together these inputs determine the subject, style, composition, and visual direction of your generated image.

***

#### What's in the Input Controls

<table><thead><tr><th width="314.6484375">Control</th><th>What It Does</th></tr></thead><tbody><tr><td><a href="/pages/pU6XiOPedazuZiDbLsl5"><strong>Prompt</strong></a></td><td>Describes the subject, environment, style, and mood in natural language</td></tr><tr><td><a href="/pages/qKotnsEwubG5P5i8H84p"><strong>Magic Prompt</strong></a></td><td>AI-enhanced version of your prompt for richer, more detailed generation</td></tr><tr><td><a href="/pages/qHVcNpXPTuqRG5SE4NBt"><strong>Reference Images</strong></a></td><td>Uploaded images that guide composition, style, or subject in generation</td></tr><tr><td><a href="/pages/Tk3lUKKGeazMMbPTEqnG"><strong>Keywords</strong></a></td><td>Structured visual modifiers for focus, lighting, shot type, lens, and style</td></tr><tr><td><a href="/pages/Tk3lUKKGeazMMbPTEqnG"><strong>Negative Keywords</strong></a></td><td>Explicit exclusions — objects, colors, styles, or artifacts to remove from output</td></tr></tbody></table>

***

#### How Inputs Work Together

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

For best results, combine all three:

* A **clear, specific prompt** for subject, environment, and mood
* **Relevant keywords** for lighting, focus, shot type, and quality enhancement
* **Reference images** when visual consistency with existing assets matters

***

#### What's in This Section

1. [**Prompt & Magic Prompt →**](/image-generation/input-controls/prompt-and-magic-prompt.md) How to write effective image prompts, use Magic Prompt for automatic enhancement, and structure inputs for consistent, high-quality outputs.
2. [**Reference Image Uploads →**](/image-generation/input-controls/reference-images.md) How to upload reference images for image-to-image generation, per-model upload limits, supported formats, and tips for effective reference use.
3. [**Keywords →**](/image-generation/input-controls/keywords.md) A complete breakdown of all keyword categories — lighting, focus, shot size, lens, enhancement, and negative keywords — with combination examples by use case.
