# Image Models

## Overview

Our API offers advanced image generation capabilities, supporting a diverse range of models to meet various creative and technical needs. This includes both open-source solutions and proprietary models, ensuring flexibility and high-quality outputs for your projects.

### Select Model

Start by selecting the model that best suits your needs. Each model is designed for specific tasks, such as generating highly realistic images, producing higher resolutions, or supporting advanced features like negative prompts.

#### Crafting a Prompt

Begin by envisioning the image you want to create. Construct a detailed prompt that includes specific keywords to guide the image generation process. These keywords can define elements such as:

* **Setting or place** (e.g., a bustling cityscape, a serene forest)
* **Objects or subjects** (e.g., a futuristic car, a glowing crystal)
* **Quality or resolution** (e.g., ultra-high detail, 4K)
* **Artistic style** (e.g., photorealistic, watercolor painting)
* **Additional elements** (e.g., lighting, mood, or specific textures)

The prompt is a critical component of the image generation process, as it directly influences the content, style, and overall outcome of the generated image. Take time to refine your prompt to achieve the desired results.

#### Configure Metaparameters

Once your prompt is ready, adjust the metaparameters to fine-tune the image generation process:

1. **Steps**:\
   Controls the number of iterations for refining the image. Higher steps yield more detail, while fewer steps speed up generation. Default: `50`.
2. **Aspect Ratio**:\
   Defines the dimensions of the output image (e.g., `16:9`, `1:1`). Ensure it matches your model's supported resolutions.
3. **Seed**:\
   A random value to ensure reproducibility. If not provided, a random seed is generated.
4. **Style**:\
   Specifies the artistic style of the image (e.g., `photorealistic`, `watercolor`). Some models require a default style if not specified.
5. **Image Strength**:\
   Determines how closely the output adheres to the input prompt or reference image.
6. **Guidance Scale**:\
   Balances creativity and adherence to the prompt. Higher values make the output more aligned with the prompt.
7. **Safety Checker**:\
   Enables or disables content moderation. Default: `true`.
8. **Provider-Specific Parameters**:
   * **Flux**: Supports `sync_mode`, `safety_tolerance`, `output_format`, and `quality` (e.g., `hd` for 2752x1536 resolution).
   * **Ideogram**: Allows `expand_prompt` for richer interpretations.
   * **Recraft**: Supports `image_size`, `colors`, and `style_id` for advanced customization.

With your prompt and metaparameters configured, you’re all set to start generating images. Experiment, iterate, and refine to bring your vision to life!


---

# 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://kidjig.gitbook.io/kidjig-docs/api-provider/image-models.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.