> ## 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.

# Load Model V2

> This endpoint is updated V2 version of the load_model endpoint allows you to load models from Huggingface, Civitai, and custom trained models.

## Request

Send a `POST` request to below endpoint.

```
--request POST 'https://modelslab.com/api/v1/enterprise/pony/load_model_v2' \
```

## ControlNet Model url and model\_id table

| url                                       | model\_id |
| :---------------------------------------- | :-------- |
| lllyasviel/control\_v11p\_sd15\_inpaint   | inpaint   |
| lllyasviel/control\_v11e\_sd15\_ip2p      | ip2p      |
| lllyasviel/control\_v11f1e\_sd15\_tile    | tile      |
| lllyasviel/control\_v11e\_sd15\_shuffle   | shuffle   |
| lllyasviel/control\_v11p\_sd15\_softedge  | softedge  |
| lllyasviel/control\_v11p\_sd15\_scribble  | scribble  |
| lllyasviel/control\_v11p\_sd15\_lineart   | lineart   |
| lllyasviel/control\_v11p\_sd15\_normalbae | normalbae |
| lllyasviel/control\_v11f1p\_sd15\_depth   | depth     |
| lllyasviel/control\_v11p\_sd15\_mlsd      | mlsd      |
| lllyasviel/control\_v11p\_sd15\_canny     | canny     |

## Load a .ckpt or .safetensors Model from Civitai

```json json theme={null}
{  
    "key": "enterprise_api_key",  
    "url": "https://civitai.com/api/download/models/94640",  
    "model_id": "majicmix-realistic",  
    "model_category": "stable_diffusion",  
    "model_format": "safetensors",  
    "webhook": "https://modelslab.com",  
    "revision": "fp16"
}
```

## Load a Huggingface Model

```json json theme={null}
{  
    "key": "enterprise_api_key",  
    "url": "wavymulder/Analog-Diffusion",  
    "model_id": "analog-diffusion",  
    "model_type": "huggingface",  
    "from_safetensors": "no",  
    "webhook": "https://modelslab.com",  
    "revision": "fp32",  
    "upcast_attention": "no"
}
```

## Load a ControlNet Model

```json json theme={null}
{  
    "key": "enterprise_api_key",  
    "url": "lllyasviel/control_v11p_sd15_canny",  
    "model_id": "canny",  
    "model_type": "controlnet",  
    "webhook": "https://modelslab.com",  
    "revision": "fp32",  
    "upcast_attention": "no"
}
```

## BodyAttributes

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

<ParamField path="url" type="string" required>
  The URL of the Hugging Face model, a <code>.ckpt</code> download link, or a trained model from our Dreambooth API.
</ParamField>

<ParamField path="model_id" type="string" required>
  Unique name (ID) for your model. The model will be saved under this ID and can be referenced later when generating images.
</ParamField>

<ParamField path="model_category" type="string" enum="[&#x22;lora&#x22;,&#x22;stable_diffusion&#x22;,&#x22;stable_diffusion_xl&#x22;,&#x22;controlnet&#x22;]" required>
  The category of the model. Options: lora, stable\_diffusion, stable\_diffusion\_xl, controlnet.
</ParamField>

<ParamField path="model_format" type="string" enum="[&#x22;ckpt&#x22;,&#x22;safetensors&#x22;,&#x22;pt&#x22;,&#x22;diffusers&#x22;]" required>
  The format of the model. Options: ckpt, safetensors, pt, diffusers.
</ParamField>

<ParamField path="revision" type="string" enum="[&#x22;fp16&#x22;,&#x22;fp32&#x22;]" default="fp32">
  Precision revision of the model. Options: fp16 or fp32. Default: fp32.
</ParamField>

<ParamField path="webhook" type="string">
  A webhook URL to receive a POST callback when the model load event completes.
</ParamField>