> ## 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.

# Controlnet

> This endpoint is used to generate ControlNet images.

## Request

Send a `POST` request to below endpoint.

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

<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>

<Check>
  You can also use multi ControlNet. Just make sure to pass comma saparated controlnet models to the `controlnet_model` as "canny,depth" and `init_image` in the request body.
</Check>

<Check>
  You can also use this endpoint to inpaint images with ControlNet. Just make sure to pass the link to the `mask_image` in the request body. and use controlnet\_model as `inpaint`.
</Check>

## Body

```json json theme={null}
{  
  "key": "enterprise_api_key",  
  "controlnet_model": "canny",  
  "controlnet_type" :"canny",  
  "model_id": "midjourney",  
  "auto_hint": "yes",  
  "guess_mode" : "no",  
  "prompt": "a model doing photoshoot, ultra high resolution, 4K image",  
  "negative_prompt": null,  
  "init_image": "https://huggingface.co/datasets/diffusers/test-arrays/resolve/main/stable_diffusion_imgvar/input_image_vermeer.png",  
  "mask_image": null,  
  "width": "512",  
  "height": "512",  
  "samples": "1",  
  "scheduler": "UniPCMultistepScheduler",  
  "num_inference_steps": "30",  
  "safety_checker": "no",  
  "enhance_prompt": "yes",  
  "guidance_scale": 7.5,  
  "strength": 0.55,  
  "seed": null,  
  "webhook": null,  
  "track_id": null
}
```

## ControlNet Models

ControlNet API using Controlnet 1.1 as default: Suported controlnet\_model:

* canny
* depth
* hed
* mlsd
* normal
* openpose
* scribble
* segmentation
* inpaint
* softedge
* lineart
* shuffle
* tile
* face\_detector
* qrcode

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

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

<ParamField query="controlnet_model" type="string">
  ControlNet model ID. It can be from the <a href="#models">models</a> list or user trained.
</ParamField>

<ParamField query="controlnet_type" type="string">
  ControlNet model type. It can be from the <a href="#models">models</a> list.
</ParamField>

<ParamField query="auto_hint" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="no">
  Auto hint image. Options: yes/no.
</ParamField>

<ParamField query="guess_mode" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="no">
  If set to yes and no prompt is passed, the model will attempt to guess what's in the <code>init\_image</code> and create variations. Options: yes/no.
</ParamField>

<ParamField query="prompt" type="string">
  Text prompt describing required image modifications. Make it detailed for best results.
</ParamField>

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

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

<ParamField query="control_image" type="string">
  Link to the ControlNet image.
</ParamField>

<ParamField query="mask_image" type="string">
  Link to the mask image for inpainting.
</ParamField>

<ParamField query="width" type="integer" max="1024" default="512">
  Width of the image. Maximum: 1024.
</ParamField>

<ParamField query="height" type="integer" max="1024" default="512">
  Height of the image. Maximum: 1024.
</ParamField>

<ParamField query="samples" type="integer" min="1" max="4" default="1">
  Number of images to return in the response. Maximum: 4.
</ParamField>

<ParamField query="scheduler" type="string">
  The scheduler to use. See <a href="#schedulers">Schedulers</a>.
</ParamField>

<ParamField query="tomesd" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="yes">
  Enable ToMeSD for faster results. Default: yes.
</ParamField>

<ParamField query="use_karras_sigmas" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="yes">
  Use Karras sigmas for improved results. Default: yes.
</ParamField>

<ParamField query="algorithm_type" type="string" enum="[&#x22;none&#x22;,&#x22;dpmsolver+++&#x22;]" default="none">
  Used in DPMSolverMultistepScheduler. Default: none.
</ParamField>

<ParamField query="vae" type="string">
  Custom VAE to use. Default: null.
</ParamField>

<ParamField query="lora_strength" type="string">
  Strength values for LoRa models (comma-separated). Range: 0.1-1.
</ParamField>

<ParamField query="lora_model" type="string">
  LoRa models to use (comma-separated). Example: contrast-fix,yae-miko-genshin
</ParamField>

<ParamField query="num_inference_steps" type="integer" enum="[21,31]" default="21">
  Number of denoising steps. Allowed values: 21 or 31.
</ParamField>

<ParamField query="safety_checker" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="yes">
  NSFW checker. If detected, replaces image with blank. Default: yes.
</ParamField>

<ParamField query="enhance_prompt" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="yes">
  Enhance prompts for better results. Default: yes.
</ParamField>

<ParamField query="multi_lingual" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="yes">
  Enable multilingual input. Default: yes.
</ParamField>

<ParamField query="guidance_scale" type="number" min="1" max="20" default="7.5">
  Scale for classifier-free guidance.
</ParamField>

<ParamField query="controlnet_conditioning_scale" type="number" min="1" max="20" default="1">
  Scale for ControlNet guidance.
</ParamField>

<ParamField query="strength" type="number" min="0" max="1" default="0.7">
  Prompt strength when using <code>init\_image</code>. 1.0 fully overrides the init image.
</ParamField>

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

<ParamField query="webhook" type="string" format="url">
  URL to receive a POST callback when image generation is complete.
</ParamField>

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

<ParamField query="upscale" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="no">
  Set to yes to upscale the generated image 2x.
</ParamField>

<ParamField query="clip_skip" type="integer" min="1" max="8">
  Clip skip value. Range: 1-8.
</ParamField>

<ParamField query="base64" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="no">
  Return response as base64. You can also pass init\_image, mask\_image, and control\_image as base64. Default: no.
</ParamField>

<ParamField query="temp" type="string" enum="[&#x22;yes&#x22;,&#x22;no&#x22;]" default="no">
  Generate a temporary image link valid for 24 hours. Default: no.
</ParamField>