Skip to main content

Avatar Generator Endpoint

Overview​

This endpoint allows you to generate image with the face image provided

Request​

--request POST 'https://modelslab.com/api/v6/image_editing/avatar_gen' \

Make a POST request to https://modelslab.com/api/v6/image_editing/avatar_gen endpoint and pass the required parameters as a request body to the endpoint.

Body Attributes​

ParameterDescription
keyYour API Key used for request authorization
promptText prompt with description of the things you want in the image to be generated.
init_imageLink or valid base64 data which follows data:image/jpeg;base64,{your_base64_string} to the image of the face you want your generations to resemble.
widthWidth of your generated image. Max dimension: 512 x 768
heightHeight of your generated image. Max dimension: 512 x 768
num_inference_stepsNumber of denoising steps. Value accepted are 21,31 or 41
guidance_scaleScale for classifier-free guidance.
s_scaleadjust the weight of the face structure [float][0.0 to 2.0] [default 1.0].
samplesNumber of images to be returned in response. The maximum value is 2.
safety_checkerWhether to run the safety checker to prevent NSFW image generation. One of true or false.
safety_checker_typeMust be one of black, blur, sensitive_content_text, pixelate
pose_image Image used for pose reference.
identitynet_strength_ratio Strength ratio for identity network. Values range between 0.0 and 1.0
adapter_strength_ratio Strength ratio for the adapter. Values range between 0.0 and 1.0. Default 1.0
pose_strength Strength of the pose reference.. Values range between 0.0 and 1.0. Default 0.4
canny_strength Strength of the canny edge detection. Values range between 0.0 and 1.0. Default 0.3
controlnet_selection Selection mode for control network. Default pose
base64If provided init_image is in base64 format or if you want your generated images as a base64 string, must be set to true. Default: false.
webhookSet an URL to get a POST API call once the image generation is complete.
track_idThis ID is returned in the response to the webhook API call. This will be used to identify the webhook request.

Example​

Body​

Body
{
  "key": "",
  "prompt": "pretty woman",
  "negative_prompt": "anime, cartoon, drawing, big nose, long nose, fat, ugly, big lips, big mouth, face proportion mismatch, unrealistic, monochrome, lowres, bad anatomy, worst quality, low quality, blurry",
  "init_image":"https://media.allure.com/photos/647f876463cd1ef47aab9c88/3:2/w_2465,h_1643,c_limit/angelina%20jolie%20blonde%20hair%20chloe.jpg",
  "width": "512",
  "height": "512",
  "samples": "1",
  "num_inference_steps": "21",
  "safety_checker": false,
  "base64": false,
  "seed": null,
  "guidance_scale": 7.5,
  "identitynet_strength_ratio": 1.0,
  "adapter_strength_ratio": 1.0,
  "pose_strength": 0.4,
  "canny_strength": 0.3,
  "controlnet_selection":"pose",
  "webhook": null,
  "track_id": null

}

Request​

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
     "key": "",
    "prompt": "pretty woman",
    "negative_prompt": "anime, cartoon, drawing, big nose, long nose, fat, ugly, big lips, big mouth, face proportion mismatch, unrealistic, monochrome, lowres, bad anatomy, worst quality, low quality, blurry",
    "init_image":"https://media.allure.com/photos/647f876463cd1ef47aab9c88/3:2/w_2465,h_1643,c_limit/angelina%20jolie%20blonde%20hair%20chloe.jpg",
    "width": "512",
    "height": "512",
    "samples": "1",
    "num_inference_steps": "21",
    "safety_checker": false,
    "base64": false,
    "seed": null,
    "guidance_scale": 7.5,
    "identitynet_strength_ratio": 1.0,
    "adapter_strength_ratio": 1.0,
    "pose_strength": 0.4,
    "canny_strength": 0.3,
    "controlnet_selection":"pose",
    "webhook": null,
    "track_id": null  
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

fetch("https://modelslab.com/api/v6/image_editing/avatar_gen", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

Response​

Example Response

{
    "status": "success",
    "generationTime": 7.358475685119629,
    "id": 32,
    "output": [
        "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/temp/35435593-31f4-4d50-80d8-8e91f1ad54b7-0.png"
    ],
    "proxy_links": [
        "https://cdn2.stablediffusionapi.com/temp/35435593-31f4-4d50-80d8-8e91f1ad54b7-0.pngg"
    ],
    "meta": {
        "base64": "no",
        "face_image": "https://media.allure.com/photos/647f876463cd1ef47aab9c88/3:2/w_2465,h_1643,c_limit/angelina%20jolie%20blonde%20hair%20chloe.jpg",
        "file_prefix": "8c3ef6ea-1c44-4d69-91cb-fc11971a65d1",
        "guidance_scale": 7.5,
        "height": 512,
        "negative_prompt": "anime, cartoon, drawing, big nose, long nose, fat, ugly, big lips, big mouth, face proportion mismatch, unrealistic, monochrome, lowres, bad anatomy, worst quality, low quality, blurry",
        "num_inference_steps": 21,
        "outdir": "out",
        "prompt": "pretty woman",
        "safety_checker": "no",
        "safety_checker_type": "blur",
        "samples": 1,
        "seed": 4029484891,
        "temp": "yes",
        "width": 512
    }
}