> ## Documentation Index
> Fetch the complete documentation index at: https://docs.modelslab.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Image to Image

> This endpoint generates an image from an image using trained or public models.

## Request

Make a `POST` request to below endpoint and pass the required parameters as a request body.

```curl curl theme={null}
--request POST 'https://modelslab.com/api/v1/enterprise/pony/img2img' \
```

<Info>
  To use the **load balancer**, you need to have **more than 1 server**. Pass the first server's API key, and it will handle the load balancing with the other servers.
</Info>

## Body

```json json theme={null}
{  
  "key": "enterprise_api_key",  
  "model_id": "realistic-vision-51",  
  "prompt": "women playing tennis",  
  "negative_prompt": null,  
  "init_image": "https://i.pinimg.com/736x/20/ab/3d/20ab3df5c180e1cae812020bcfeb3093.jpg",  
  "samples": "1",  
  "num_inference_steps": "31",  
  "safety_checker": "yes",  
  "enhance_prompt": "yes",  
  "guidance_scale": 7.5,  
  "strength": 0.7,  
  "scheduler": "UniPCMultistepScheduler",  
  "seed": null,  
  "lora_model": null,  
  "tomesd": "yes",  
  "use_karras_sigmas": "yes",  
  "vae": null,  
  "lora_strength": null,  
  "webhook": null,  
  "track_id": null
}
```

## Schedulers

This endpoint also supports schedulers. Use the "scheduler" parameter in the request body to pass a specific scheduler from the list below:

* EulerDiscreteScheduler
* EulerAncestralDiscreteScheduler
* LMSDiscreteScheduler
* HeunDiscreteScheduler
* KDPM2DiscreteScheduler
* KDPM2AncestralDiscreteScheduler
* DPMSolverMultistepScheduler
* DPMSolverSinglestepScheduler
* DDIMScheduler
* DDPMScheduler
* PNDMScheduler
* UniPCMultistepScheduler
* DEISMultistepScheduler
* LCMScheduler
* IPNDMScheduler

## Body Attributes

<ParamField path="key" type="string" required>
  Your enterprise API Key used for request authorization.
</ParamField>

<ParamField path="model_id" type="string" required>
  The ID of the model to be used. It can be public or your trained model.
</ParamField>

<ParamField path="prompt" type="string" required>
  Text prompt with description of the things you want in the image to be generated.
</ParamField>

<ParamField path="negative_prompt" type="string">
  Items you don't want in the image.
</ParamField>

<ParamField path="init_image" type="string">
  Link to the initial image.
</ParamField>

<ParamField path="width" type="number" default="512">
  Width of the image. Maximum: 1024.
</ParamField>

<ParamField path="height" type="number" default="512">
  Height of the image. Maximum: 1024.
</ParamField>

<ParamField path="samples" type="number" default="1">
  Number of images to return. Maximum: 4.
</ParamField>

<ParamField path="num_inference_steps" type="number" default="21">
  Number of denoising steps. Allowed values: 21, 31, or 41.
</ParamField>

<ParamField path="safety_checker" type="string" default="yes">
  NSFW image checker. If detected, replaces the image with blank. Options: yes/no.
</ParamField>

<ParamField path="safety_checker_type" type="string" default="sensitive_content_text">
  Action to apply if NSFW content is detected. Options: blur, sensitive\_content\_text, pixelate, black.
</ParamField>

<ParamField path="guidance_scale" type="number" default="7.5">
  Scale for classifier-free guidance (range: 1-20).
</ParamField>

<ParamField path="strength" type="number" default="0.7">
  Prompt strength when using init\_image. 1.0 fully overrides the init image.
</ParamField>

<ParamField path="clip_skip" type="number">
  Clip Skip value. Range: 1-8.
</ParamField>

<ParamField path="seed" type="number">
  Seed for reproducibility. Pass null for random generation.
</ParamField>

<ParamField path="webhook" type="string">
  URL to receive a POST callback once the image generation is complete.
</ParamField>

<ParamField path="track_id" type="string">
  ID returned in webhook callback to identify the request.
</ParamField>