# canny

> <p>更适合东方宝宝的canny</p><p>实验型模型</p><p>flux引导：20</p><p><strong>模型用途声明</strong></p><p>1. 你不得将此模型及其衍生版本（如融合模型版本）托管于计划赚取收入或捐赠的网站/应用程序。如果您需要将此模型及其衍生版本用于商业目的（如生成式服务、售卖图片、将图片用于公开发表到短视频平台的文章或出版物等等），请通过站内联系本人</p><p>2. 您不得直接售卖由此模型生成的图片，除非您对该图片进行了足够程度的人工修改，使其在法律意义上可以被完全判定为您的个人作品。如果您违反本条，所造成的一切法律后果由您个人承担，请恕本人概不负责。</p><p>3. 您不能使用该模型故意制作或共享非法或有害的内容传播和输出，请您遵守公序良德，将此模型用于积极正面的用途。</p><p>4. 为了避免不必要的误会，请勿将本模型上传到其他任何模型网站，请勿使用本模型产出的图片训练新模型，并禁止一切形式的融合模型，谢谢！</p>

## Overview

- **Model ID**: `canny`
- **Category**: stable diffusion
- **Provider**: modelslab
- **Status**: model_ready
- **Screenshot**: `https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/03063a83-7292-47a6-aefa-3475285a90d8/width=1800/62864563.jpeg`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v5/controlnet`
- **Method**: POST

### Parameters

- **`init_image`** (required): 
  - Type: file
  - Example: Please upload image 

- **`prompt`** (required): 
  - Type: textarea
  - Example: Enter Prompt

- **`controlnet_model`** (required): controlnet model and conttrolnet type must be same
  - Type: select (options: lineart, canny, depth, scribble, mlsd, openpose, softedge, qrcode)

- **`controlnet_type`** (required): controlnet model and conttrolnet type must be same
  - Type: select (options: lineart, canny, depth, scribble, mlsd, openpose, softedge, qrcode)

- **`model_id`** (required): Some controlNet models are not supported by FLUX
  - Type: select (options: sdxl, sd15, fluxdev)

- **`controlnet_conditioning_scale`** (required): 0.1 (Creative) takes min refrance from init image and 1.0 takes max refrance from init image
  - Type: number (range: 0.1-1)

- **`negative_prompt`** (optional): 
  - Type: textarea
  - Example: Enter Negative prompt that you do not want to see in image

- **`samples`** (optional): 
  - Type: number (range: 1-4)

- **`guidance_scale`** (optional): 
  - Type: number (range: 1-10)

- **`num_inference_steps`** (optional): 
  - Type: number (range: 21-31)

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v5/controlnet \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "canny",
    "init_image": "https://assets.modelslab.com/generations/a8572240-3040-4fd8-b9f4-aeaaf4fe287d",
    "prompt": "a girl, wearing red bikini, looking at camera, ocean in background",
    "controlnet_model": "lineart",
    "controlnet_type": "lineart",
    "controlnet_conditioning_scale": "0.5",
    "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
    "samples": "1",
    "guidance_scale": "7.5",
    "num_inference_steps": "31"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v5/controlnet",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "canny",
        "init_image": "https://assets.modelslab.com/generations/a8572240-3040-4fd8-b9f4-aeaaf4fe287d",
        "prompt": "a girl, wearing red bikini, looking at camera, ocean in background",
        "controlnet_model": "lineart",
        "controlnet_type": "lineart",
        "controlnet_conditioning_scale": "0.5",
        "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
        "samples": "1",
        "guidance_scale": "7.5",
        "num_inference_steps": "31"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v5/controlnet", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "canny",
    "init_image": "https://assets.modelslab.com/generations/a8572240-3040-4fd8-b9f4-aeaaf4fe287d",
    "prompt": "a girl, wearing red bikini, looking at camera, ocean in background",
    "controlnet_model": "lineart",
    "controlnet_type": "lineart",
    "controlnet_conditioning_scale": "0.5",
    "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
    "samples": "1",
    "guidance_scale": "7.5",
    "num_inference_steps": "31"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Links

- [Model Playground](https://modelslab.com/models/controlnet/canny)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)