# LoRA for Style Training - Documentation

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown is available with `Accept: text/markdown` and `.md` URL variants.

Source: /docs/api-reference/model-apis-create-style-training

# LoRA for Style Training

You can train a LoRA model to generate images that emulate a specific artistic style.

##

[​](#create-style-training-task)

Create Style Training Task

`POST https://api.novita.ai/v3/training/style`
Use this API to start a style training task.

This is an asynchronous API; only the task_id is returned initially. Utilize this task_id to query the Task Result API at [Get Style Training Result API](#get-style-training-result) to retrieve the results of the image generation.

###

[​](#request-headers)

Request Headers

[​](#param-content-type)

Content-Type

string

required

Enum: `application/json`

[​](#param-authorization)

Authorization

string

required

Bearer authentication format, for example: Bearer {{API Key}}.

###

[​](#request-body)

Request Body

[​](#param-name)

name

string

required

Task name for this model training.

[​](#param-base-model)

base_model

string

required

Base models used for training.

Enum: `stable-diffusion-xl-base-1.0`, `dreamshaperXL09Alpha_alpha2Xl10_91562`, `protovisionXLHighFidelity3D_release0630Bakedvae_154359`, `v1-5-pruned-emaonly`, `epicrealism_naturalSin_121250`, `chilloutmix_NiPrunedFp32Fix`, `abyssorangemix3AOM3_aom3a3_10864`, `dreamshaper_8_93211`, `WFChild_v1.0`, `majichenmixrealistic_v10`, `realisticVisionV51_v51VAE_94301`, `sdxlUnstableDiffusers_v11_216694`, `realisticVisionV40_v40VAE_81510`, `epicrealismXL_v10_247189`, `somboy_v10_172675`, `yesmixXL_v10_283329`, `animagineXLV31_v31_325600`

[​](#param-width)

width

integer

required

Width of training images, must be > 0

[​](#param-height)

height

integer

required

Height of training images, must be > 0

[​](#param-image-dataset-items)

image_dataset_items

object[]

required

Image asset IDs and their captions.

Hide properties

[​](#param-assets-id)

assets_id

integer

required

Image asset ID; see [Upload Images For Training](#_1-upload-images-for-training) for reference.

[​](#param-caption)

caption

string

required

Image caption; refer to [Training Image Caption Guidance](/guides/model-apis-training-guidance) for more information.

[​](#param-expert-setting)

expert_setting

object

Show properties

[​](#param-train-batch-size)

train_batch_size

integer

batch size of training, Range [1, 4]

[​](#param-learning-rate)

learning_rate

number(float)

This parameter controls the extent of model parameter updates during each iteration. A higher learning rate results in larger updates, potentially speeding up the learning process but risking overshooting the optimal solution. Conversely, a lower learning rate ensures smaller, more precise adjustments, which may lead to a more stable convergence at the cost of slower training.

Enum: `1e-4, 1e-5, 1e-6, 2e-4, 5e-5`

[​](#param-max-train-steps)

max_train_steps

integer

This parameter specifies the maximum number of training steps to be executed before halting the training process. It sets a limit on the duration of training, ensuring that the model does not continue to train indefinitely. If the `max_train_steps` set to 2000 and images amount in parameter `image_dataset_items` is 10, the number of training steps per graph is 200. Minimum value is 1.

[​](#param-seed)

seed

integer

A seed is a number from which Stable Diffusion generates noise, which, makes training deterministic. Using the same seed and set of parameters will produce identical LoRA each time, Minimum 1.

[​](#param-lr-scheduler)

lr_scheduler

string

This parameter specifies the type of learning rate scheduler to be used during the training process. The scheduler dynamically adjusts the learning rate according to one of the specified strategies. `constant`: Maintains a fixed learning rate throughout training. `linear`: Gradually decreases the learning rate linearly from a higher to a lower value. `cosine`: Adjusts the learning rate following a cosine curve, decreasing it initially and then increasing towards the end. `cosine_with_restarts`: Similar to cosine, but resets the rate periodically to avoid local minima. `polynomial`: Decreases the learning rate according to a polynomial decay. `constant_with_warmup`: Starts with a lower learning rate and warms up to a constant rate after a specified number of steps.

Enum: `constant, linear, cosine, cosine_with_restarts, polynomial, constant_with_warmup`

[​](#param-lr-warmup-steps)

lr_warmup_steps

integer

This parameter determines the number of initial training steps during which the learning rate increases gradually, effective only when the lr_scheduler is set to one of the following modes: linear, cosine, cosine_with_restarts, polynomial, or constant_with_warmup. The warmup phase helps in stabilizing the training process before the main learning rate schedule begins. The minimum value for this parameter is 0, indicating no warmup, Minimum 0.

[​](#param-components)

components

object[]

required

Common parameters configured for training.

Hide properties

[​](#param-name-1)

name

string

required

Type of components. When set to `face_crop_region`, args can be set to args: [name: ratio, value: 1.0], ratio > 1 means more non-facial area will be included. When set to `resize`, args can be set to args: [name: width, value: 512, name: height, value: 512], which mean all the images will be cropped to 512*512. When set to `face_restore`, args can be set to args: [name: method, value:gfpgan_1.4], which mean face restore will be open.

Enum: `face_crop_region`, `resize`, `face_restore`

[​](#param-args)

args

object[]

required

Component detail settings.

Hide properties

[​](#param-name-2)

name

string

required

Name of argument.

[​](#param-value)

value

string

required

Argument value.

###

[​](#response)

Response

[​](#param-task-id)

task_id

string

Utilize this `task_id` to query the Task Result API at [Get style training result](#get-style-training-result).

##

[​](#get-style-training-result)

Get style training result

`GET https://api.novita.ai/v3/training/style`
Use this API to get the style training result, including the model.

###

[​](#request-headers-2)

Request Headers

[​](#param-authorization-1)

Authorization

string

required

In Bearer {{API Key}} format.

###

[​](#request-body-2)

Request Body

[​](#param-task-id-1)

task_id

string

required

###

[​](#response-2)

Response

[​](#param-task-id-2)

task_id

string

The task id of training.

[​](#param-task-status)

task_status

string

Represents the current status of a task, particularly useful for monitoring and managing the progress of training tasks. Each status indicates a specific phase in the task’s lifecycle.

Enum: `UNKNOWN`, `QUEUING`, `TRAINING`, `SUCCESS`, `CANCELED`, `FAILED`

[​](#param-model-type)

model_type

string

Model trained type.

Enum: `lora`

[​](#param-models)

models

object[]

models info

Show properties

[​](#param-model-name)

model_name

string

model file name.

[​](#param-model-status)

model_status

string

model status.

Enum: `DEPLOYING`, `SERVING`

[​](#param-extra)

extra

object

extra info

Show properties

[​](#param-eta-relative)

eta_relative

number

Estimated time of arrival in seconds.

[​](#param-progress-percent)

progress_percent

number

The progress percent with a range of 0 to 100.

##

[​](#example)

Example

Generally, model training involves following steps.

- Upload the images for model training.

- Set training parameters and start the training.

- Get the training results and generate images with the trained model.

###

[​](#1-upload-images-for-training)

1. Upload images for training

- Currently we only supports uploading images in `png` / `jpeg` / `webp` format.

- Each task supports uploading up to 50 images. In order to make the final effect good, the images uploaded should meet some basic conditions, such as: “portrait in the center”, “no watermark”, “clear picture”, etc.

####

[​](#1-1-get-image-upload-url)

1.1 Get image upload URL

- This interface returns the URL for single image to upload and can be called multiple times to upload images for training.

```
curl --location --request POST 'https://api.novita.ai/v3/assets/training_dataset' \
--header 'Authorization: Bearer {{API Key}}' \
--header 'Content-Type: application/json' \
--data-raw '{
"file_extension": "png"
}'
```

`Response:`

```
{
"assets_id": "34558688e2f42a0137ca2d5274a8cf43",
"upload_url": "https://faas-training-dataset.s3.ap-southeast-1.amazonaws.com/test/******",
"method": "PUT",
"headers": {
"Host": {
"values": [
"faas-training-dataset.s3.ap-southeast-1.amazonaws.com"
]
}
}
}
```

- `assets_id`: The unique identifier of the image, which will be used in the training task.

- `upload_url`: The URL for image upload.

- `method`: The HTTP method for image upload.

####

[​](#1-2-upload-images)

1.2 Upload images

After obtaining the `upload_url` at step `Get image upload URL`, please refer to the following document to complete the image upload: [https://docs.aws.amazon.com/zh_cn/AmazonS3/latest/userguide/PresignedUrlUploadObject.html.](https://docs.aws.amazon.com/zh_cn/AmazonS3/latest/userguide/PresignedUrlUploadObject.html)
`Put images:`

```
curl -X PUT -T "{{filepath}}" "{{upload_url}}"
```

`or`

```
curl --location --request PUT '{{upload_url}}' \
--header 'Content-Type: image/png' \
--data '{{filepath}}'
```

###

[​](#2-start-training-task-and-configure-parameters)

2. Start training task and configure parameters

In this step, we will begin the model training process, which is expected to take approximately 10 minutes, depending on the actual server’s availability.
There are four types of parameters for model traning: `Model info parameters`, `dataset parameters`, `components parameters`,`expert parameters`, you can set them according to our tables below.
Here are some tips to train a good model:

- At least 10 photos of faces that meet the requirements.

- For parameters `instance_prompt`, we suggests using “a close photo of ohwx <man|\woman>”

- For parameters `base_model`, value `v1-5-pruned-emaonly` has better generalization ability and can be used in combination with various Base models, such as `dreamshaper 2.5D`, value `epic-realism` has a strong sense of reality.

TypeParametersDescriptionModel info parametersnameName of your training modelModel info parametersbase_modelbase_model typeModel info parameterswidthTarget image widthModel info parametersheightTarget image heightdataset parametersimage_dataset_itemsArray: consist of `imageUrl` and image `caption`dataset parameters- image_dataset_items.assets_idimages assets_id, which can be found in step `Get image upload URL`components parameterscomponentsArray: consist of `name` and `args`, this is a common parameters configured for training.components parameters- components.nameType of components, Enum: `face_crop_region`, `resize`, `face_restore`components parameters- components.argsDetail values of components.nameexpert parametersexpert_settingexpert parameters.expert parameters- instance_promptCaptions for all the training images, here is a guidance of how to make a effective prompt : [Click Here](/docs/guides/model-apis-training-guidance)expert parameters- batch_sizebatch size of training.expert parameters- max_train_stepsMax train steps, 500 is enought for lora model training.expert parameters- …More expert parameters can be access at api reference.

Here is a example of how to start training:

```
curl --location --request POST 'https://api.novita.ai/v3/training/style' \
--header 'Accept: ' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {{API Key}}' \
--data-raw '{
"name": "test_style_01",
"base_model": "v1-5-pruned-emaonly",
"width": 512,
"height": 512,
"image_dataset_items": [
{
"assets_id": "34558688e2f42a0137ca2d5274a8cf43"
},
{
"assets_id": "1231231243f42a0137ca2d5274a8cf43"
}
],
"expert_setting": {
"instance_prompt": "Xstyle, of a young woman, profile shot, from side,sitting, looking at viewer, smiling, head tilt, eyes open,long black hair, glowing skin,light smile,cinematic lighting,dark environment",
"class_prompt": "person"
},
"components": [
{
"name": "face_crop_region",
"args": [
{
"name": "ratio",
"value": "1"
}
]
},
{
"name": "resize",
"args": [
{"name": "width", "value": "512"},
{"name": "height", "value": "512"}
]
},
{
"name": "face_restore",
"args": [
{"name": "method", "value": "gfpgan_1.4"},
{"name": "upscale", "value": "1.0"}
]
}
]
}'
```

Response:

```
{
"task_id": "d660cdd0-ab9b-4a55-8b78-4bc851051fb0"
}
```

The `task_id` is the unique identifier of the training task, which can be used to query the training status and results.

###

[​](#3-get-training-status)

3. Get training status

####

[​](#3-1-get-model-training-and-deployment-status)

3.1 Get model training and deployment status

In this step, we will obtain the progress of model training and the status of model deployment after training

```
curl --location --request GET 'https://api.novita.ai/v3/training/style?task_id=d660cdd0-ab9b-4a55-8b78-4bc851051fb0' \
--header 'Authorization: Bearer {{API Key}}'
```

`Response:`

```
{
"task_id": "d660cdd0-ab9b-4a55-8b78-4bc851051fb0",
"task_status": "SUCCESS",
"model_type": "",
"models": [
{
"model_name": "model_1698904832_F2BB461625.safetensors",
"model_status": "DEPLOYING"
}
]
}
```

- `task_status`: The status of the training task, Enum: `UNKNOWN`, `QUEUING`, `TRAINING`, `SUCCESS`, `CANCELED`, `FAILED`.

- `model_status`: The status of the model, Enum: `DEPLOYING`, `SERVING`.

- `model_name`: The name of the model, which can be used to generate images in next step.

When the `task_status` is `SUCCESS`, the `model_status` is `SERVING` we can starting to use the lora model.

####

[​](#3-2-start-using-the-trained-model)

3.2 Start using the trained model

After model deployed successfully, we can download the model files or generate images directly.

##### 3.2.1 Use the generated models to create images

In order to use the trained lora models, We need to add `model_name` into the `request` of endpoint `/v3/async/txt2img` or `/v3/async/img2img`. Currently trained lora model can not be used in /v3 endpoint.
Below is a example of how to generate images with trained model:
Please set the `Content-Type` header to `application/json` in your HTTP request to indicate that you are sending JSON data. Currently, only JSON format is supported.
`Request:`

```
curl --location 'https://api.novita.ai/v3/async/txt2img' \
--header 'Authorization: Bearer {{API Key}};' \
--header 'Content-Type;' \
--data '{
"extra": {
"response_image_type": "jpeg"
},
"request": {
"model_name": "realisticVisionV51_v51VAE_94301.safetensors",
"prompt": "a young woman",
"negative_prompt": "bottle, bad face",
"sd_vae": "",
"loras": [
{
"model_name": "model_1698904832_F2BB461625.safetensors",
"strength": 0.7
}
],
"embeddings": [
{
"model_name": ""
}
],
"hires_fix": {
"target_width": 1024,
"target_height": 768,
"strength": 0.5
},
"refiner": {
"switch_at": null
},
"width": 512,
"height": 384,
"image_num": 2,
"steps": 20,
"seed": 123,
"clip_skip": 1,
"guidance_scale": 7.5,
"sampler_name": "Euler a"
}
}'
```

`Response:`

```
{
"code": 0,
"msg": "",
"data": {
"task_id": "bec2bcfe-47c6-4536-af34-f26cfe6fd457"
}
}
```

Use `task_id` to get images
HTTP status codes in the 2xx range indicate that the request has been successfully accepted, while status codes in the 5xx range indicate internal server errors.
You can get images url in `imgs` of response.
`Request:`

```
curl --location 'https://api.novita.ai/v3/async/task-result?task_id=bec2bcfe-47c6-4536-af34-f26cfe6fd457' \
--header 'Authorization: Bearer {{API Key}}'
```

`Response:`

```
{
"task": {
"task_id": "bec2bcfe-47c6-4536-af34-f26cfe6fd457",
"status": "TASK_STATUS_SUCCEED",
"reason": ""
},
"images": [
{
"image_url": "https://faas-output-image.s3.ap-southeast-1.amazonaws.com/dev/replace_object_a910c8f7-76ce-40bd-b805-f00f3ddd7dc1_0.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASVPYCN6LRCW3SOUV%2F20231019%2Fap-southeast-1%2Fs3%2Faws4_request&X-Amz-Date=20231019T084537Z&X-Amz-Expires=3600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=b9ad40a5cb3aecf89602c15fe72d28be5d8a33e0bfe3656ce968295fde1aab31",
"image_url_ttl": 3600,
"image_type": "png"
}
],
"videos": [
{
"video_url": "https://faas-output-image.s3.ap-southeast-1.amazonaws.com/dev/replace_object_a910c8f7-76ce-40bd-b805-f00f3ddd7dc1_0.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASVPYCN6LRCW3SOUV%2F20231019%2Fap-southeast-1%2Fs3%2Faws4_request&X-Amz-Date=20231019T084537Z&X-Amz-Expires=3600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=b9ad40a5cb3aecf89602c15fe72d28be5d8a33e0bfe3656ce968295fde1aab31",
"video_url_ttl": "3600",
"video_type": "png"
}
]
}
```

####

[​](#3-3-list-training-tasks)

3.3 List training tasks

In this step, we can obtain all the info of trained models.

```
curl --location --request GET 'https://api.novita.ai/v3/training?pagination.limit=10&pagination.cursor=c_0' \
--header 'Authorization: Bearer {{API Key}}'
```

`Response:`

```
{
"tasks": [
{
"task_name": "test_01",
"task_id": "a0c4cc90-0296-4972-a1d8-e6e227daf094",
"task_type": "style",
"task_status": "SUCCESS",
"created_at": 1699325415,
"models": [
{
"model_name": "model_1699325939_E83A88DAC5.safetensors",
"model_status": "SERVING"
}
]
},
{
"task_name": "test_02",
"task_id": "51e9bf41-8f7a-464d-b5ad-2fa217a1ec93",
"task_type": "style",
"task_status": "SUCCESS",
"created_at": 1699267268,
"models": [
{
"model_name": "model_1699267603_27F0D9C81C.safetensors",
"model_status": "SERVING"
}
]
},
{
"task_name": "test_03",
"task_id": "7bd205ab-63e9-452b-9a66-39c597000eaa",
"task_type": "style",
"task_status": "FAILED",
"created_at": 1699264338,
"models": []
}
],
"pagination": {
"next_cursor": "c_10"
}
}
```

- `task_name` : The name of the training task.

- `task_id` : The unique identifier of the training task, which can be used to query the training status and results.

- `task_type` : The type of the training task.

- `task_status`: The status of the training task, Enum: `UNKNOWN`, `QUEUING`, `TRAINING`, `SUCCESS`, `CANCELED`, `FAILED`.

- `created_at`: The time when the training task was created.

- `model`: The trained model.

- `model_name`: The sd name of the model.

- `model_status`: The status of the model, Enum: `DEPLOYING`, `SERVING`.

###

[​](#4-training-playground)

4. Training playground

You can also use our training playground to train models in a user-friendly way at: [Click Here](https://huggingface.co/spaces/novita-ai/Face-Stylization-Playground)

####

[​](#4-1-input-novita-ai-api-key-images-and-select-training-type)

4.1 Input Novita AI API Key, images and select training type

![](https://next-app-static.s3.ap-southeast-1.amazonaws.com/get-started/training_playground01.png)

####

[​](#4-2-switch-to-the-inferencing-tab-and-add-more-detail)

4.2 Switch to the inferencing tab and add more detail

![](https://next-app-static.s3.ap-southeast-1.amazonaws.com/get-started/training_playground02.png)

![](https://next-app-static.s3.ap-southeast-1.amazonaws.com/get-started/training_playground03.png)

####

[​](#review-the-training-results)

Review the training results

![](https://next-app-static.s3.ap-southeast-1.amazonaws.com/get-started/training_playground04.png)

Last modified on March 27, 2025