Train a Lora Model with Custom Images

Overview

Using this endpoint you can train a Lora model with your own images. You can train a model on any object or person.

Request

--request POST 'https://modelslab.com/api/v3/lora_fine_tune' \

Make a POST request to https://modelslab.com/api/v3/lora_fine_tune endpoint and pass the required parameters as a request body.

For now, you can only train a model on normal lora models and sdxl and get its style.

Body Attributes

Parameter	Description	Values
key	Your API Key used for request authorization.	key
instance_prompt	Text prompt with how you want to call your trained person/object.	string
wandb_key	Key to the wandb platform to monitor your training process.	string
class_prompt	Classification of the trained person/object.	person/object
base_model_type	The type of LoRA base model you want to train on.	"normal" or "sdxl"
negative_prompt	Items you don't want in the image.	string
images	Accessible direct links to images, cropped to 512x512 pixels. A good number is about 7-8 images.	URL(s)
training_type	The type of the object you are training on.	"men", "women", "couple", "null"
lora_type	Type of LoRA model.	"lora" or "lycoris"
max_train_steps	Set at 2 times the number of images (Ni*2); minimum value is 10 and maximum value is 50.	integer
webhook	Set a URL to receive a POST call when training is complete.	URL

Training Types

The table below lists all the possible values for the training_type parameter.

Value	Description
men	Train on faces of men.
female	Train on faces of females.
couple	Train on couples of male and female; in images array pass images of couples, instead of images of a single person.
null	Train on object or anything.

Webhook Post JSON

This is an example webhook post call in JSON format.

{
 "status": "success",
 "training_status": "deploying_gpu",
 "logs": "it will take upto 25 minutes",
 "model_id": "F5jvdzGnYi",
}

Training Status Values

The table below describes all possible training statuses.

Status	Description
deploying_gpu	Deploying GPU
training_started	Training started
training_success	Training completed successfully
trained_model_compressing	Compressing the trained model
trained_model_uploading	Uploading the trained model
trained_model_uploaded	Trained model uploaded
deploying_model	Deploying the trained model
model_ready	The trained model is ready for use

Example

Body

Body
{
    "key":"",
    "instance_prompt": "photo of ambika0 man",
    "class_prompt": "photo of a man",
    "base_model_type": "sdxl",
    "negative_prompt":" lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
    "images": [
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/1.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/2.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/3.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/4.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/5.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/6.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/7.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/8.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/9.png"
  ],
    "seed": "0",
    "training_type": "men",
    "max_train_steps": "18",
    "lora_type":"lora",
    "webhook": null
}

Request

JS
PHP
NODE
PYTHON
JAVA

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

var raw = JSON.stringify({
    "key":"",
    "instance_prompt": "photo of ambika0 man",
    "class_prompt": "photo of a man",
    "base_model_type": "sdxl",
    "negative_prompt":" lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
    "images": [
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/1.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/2.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/3.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/4.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/5.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/6.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/7.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/8.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/9.png"
  ],
    "seed": "0",
    "training_type": "men",
    "max_train_steps": "18",
    "lora_type":"lora",
    "webhook": null
});

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

fetch("https://modelslab.com/api/v3/lora_fine_tune", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

<?php

$payload = [
  "key" => "", 
  "instance_prompt" => "photo of ambika0 man", 
  "class_prompt" => "photo of person", 
  "base_model_type" => "sdxl",
  "negative_prompt" => " lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
  "images" => [
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/1.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/2.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/3.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/4.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/5.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/6.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/7.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/8.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/9.png"
  ], 
  "seed" => "0", 
  "training_type" => "men", 
  "lora_type":"lora",
  "max_train_steps" => "18", 
  "webhook" => "" 
];

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://modelslab.com/api/v3/lora_fine_tune',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 0,
  CURLOPT_FOLLOWLOCATION => true,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_POSTFIELDS => json_encode($payload),
  CURLOPT_HTTPHEADER => array(
    'Content-Type: application/json'
  ),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;

var request = require('request');
var options = {
  'method': 'POST',
  'url': 'https://modelslab.com/api/v3/lora_fine_tune',
  'headers': {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    "key":"",
    "instance_prompt": "photo of ambika0 man",
    "class_prompt": "photo of a man",
    "base_model_type": "sdxl",
    "negative_prompt":" lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
    "images": [
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/1.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/2.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/3.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/4.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/5.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/6.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/7.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/8.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/9.png"
  ],
    "seed": "0",
    "training_type": "men",
    "max_train_steps": "18",
    "lora_type":"lora",
    "webhook": null
  })
};

request(options, function (error, response) {
  if (error) throw new Error(error);
  console.log(response.body);
});

import requests
import json

url = "https://modelslab.com/api/v3/lora_fine_tune"

payload = json.dumps({
    "key":"",
    "instance_prompt": "photo of ambika0 man",
    "class_prompt": "photo of a man",
    "base_model_type": "sdxl",
    "negative_prompt":" lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
    "images": [
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/1.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/2.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/3.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/4.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/5.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/6.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/7.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/8.png",
    "https://raw.githubusercontent.com/pnavitha/sampleImages/master/9.png"  
  ],
    "seed": "0",
    "training_type": "men",
    "max_train_steps": "18",
    "lora_type":"lora",
    "webhook": "",
})

headers = {
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\n    \"key\":\"\",\n    \"instance_prompt\": \"photo of ambika0 man\",\n    \"class_prompt\": \"photo of a man\",\n    \"base_model_type\": \"normal\",\n    \"negative_prompt\":\" lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry\",\n    \"images\": [\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/1.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/2.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/3.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/4.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/5.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/6.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/7.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/8.png\",\n    \"https://raw.githubusercontent.com/pnavitha/sampleImages/master/9.png\"\n  ],\n    \"seed\": \"0\",\n    \"training_type\": \"men\",\n    \"max_train_steps\": \"18\",\n    \"lora_type\":\"lora\",\n    \"webhook\": null\n}");
Request request = new Request.Builder()
  .url("https://modelslab.com/api/v3/lora_fine_tune")
  .method("POST", body)
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();

Response

{
  "status": "success",
  "messege": "deploying_gpu",
  "data": "it will take upto 30 minutes.",
  "training_id": "F5jvdzGnYi"
}

Overview​

Request​

Body Attributes​

Training Types​

Webhook Post JSON​

Training Status Values​

Example​

Body​

Request​

Response​

Overview

Request

Body Attributes

Training Types

Webhook Post JSON

Training Status Values

Example

Body

Request

Response