> For the complete documentation index, see [llms.txt](https://xalora-ai.gitbook.io/xalora-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xalora-ai.gitbook.io/xalora-ai-docs/image-generation-api.md).

# Image Generation API

#### Overview <a href="#overview" id="overview"></a>

Xalora provides a REST API that allows developers to invoke Stable Diffusion / Flux model inference to programmatically generate images based on text prompts. This document outlines how to use the API to submit image generation jobs and retrieve the generated images.

#### [​](https://docs.heurist.ai/dev-guide/image-generation/introduction#authentication)Authentication <a href="#authentication" id="authentication"></a>

To use the API, you must include a valid authentication token in the request header.

Copy

```
Authorization: Bearer YOUR_AUTH_KEY
```

#### [​](https://docs.heurist.ai/dev-guide/image-generation/introduction#request-format)Request Format <a href="#request-format" id="request-format"></a>

Submit a JSON payload with the following structure:

Copy

```
{
  "job_id": "Random Job Identifier (Must Be Unique)",
  "model_input": {
    "SD": {
      "prompt": "Textual description to generate the image",
      "neg_prompt": "Negative prompt to avoid certain elements in the image",
      "num_iterations": "Number of iterations for the image generation process",
      "width": "Width of the generated image in pixels",
      "height": "Height of the generated image in pixels",
      "guidance_scale": "Guidance scale to control the adherence to the prompt",
      "seed": "Seed for the random number generator to ensure reproducibility"
    }
  },
  "model_id": "Identifier for the image generation model"
  "deadline": 60,
  "priority": 1
}
```

[**​**](https://docs.heurist.ai/dev-guide/image-generation/introduction#parameters)**Parameters**

* `job_id` (String, required): A unique identifier for the job ensuring that every job you submit is tracked individually..
* `model_input` (Object, required): Contains the parameters for the image generation.
  * `SD` (Object): Specific settings for the Stable Diffusion model.
    * `prompt` (String, required): The main description that guides the image generation.
    * `neg_prompt` (String, optional): Descriptions of what to avoid in the generated image.
    * `num_iterations` (Integer, optional): The number of iteration steps. We recommend 20\~30. Cannot exceed 50.
    * `width` (Integer, optional): The width of the generated image in pixels. Default is 512.
    * `height` (Integer, optional): The height of the generated image in pixels. Default is 512.
    * `guidance_scale` (Float, optional): Influences the model’s adherence to the prompt.
    * `seed` (Integer, optional): Ensures reproducibility of the image generation. Default is -1 for pure randomness.
* `model_id` (String, required): The identifier of the image generation model to use. You can find all supported models in the [Xalora model list](https://github.com/XaloraAI/Xalora-models/blob/main/models.json). Meaning of model type parameter:`sd15` = Stable Diffusion 1.5 checkpoint.`sdxl10` = SDXL 1.0 checkpoint. `composite15` = Stable Diffusion 1.5 LoRA. `compositexl` = SDXL LoRA
* `priority` (Integer, required): Sets priority in a queue for the job. Default is 1.
* `deadline` (Integer, required): Sets the max duration of a job. Default is 60.

#### [​](https://docs.heurist.ai/dev-guide/image-generation/introduction#response-structure)Response Structure <a href="#response-structure" id="response-structure"></a>

When the job is successfully processed, the API returns a URL pointing to the generated image.

For API reference, Please visit the Image Generation Endpoint section.

#### [​](https://docs.heurist.ai/dev-guide/image-generation/introduction#cost-considerations)Cost Considerations <a href="#cost-considerations" id="cost-considerations"></a>

The cost of generating an image depends on the model type, resolution, and number of iteration steps:

* **1 Standard Unit of Credit** = 1 image generated at 1024x1024 resolution using SDXL model with 20 iterations.
* The cost of a job is proportional to the image’s resolution and the number of iterations used. For example:
* If you generate an image at **1024x512** resolution using **30 iterations** with SDXL model, the cost calculation is: `1024x512 / (1024x1024) * 30 / 20 = 0.75 credits`
* **SD 1.5** models are smaller and thus cost less than SDXL models.

#### [​](https://docs.heurist.ai/dev-guide/image-generation/introduction#api-integration-examples)API Integration Examples <a href="#api-integration-examples" id="api-integration-examples"></a>

Want to see the Image Generation API in action? Here are a few integration examples:

* [Stable Diffusion WebUI](https://github.com/XaloraAI/stable-diffusion-webui) is a simple demo project that integrates with Xalora’s image generation API, built with Gradio in Python. Here’s the relevant [POST API request](https://github.com/XaloraAI/stable-diffusion-webui/blob/main/main.py)
* [Xalora Node.js SDK](https://github.com/XaloraAI/Xalora-sdk/blob/main/packages/images/index.ts) integrates with the API. The SDK provides complete authentication and error handling features.