Tailored Generation
/
Endpoints
/
Create Model

Overview

Tailored Generation provides capabilities to generate visuals (photos, illustrations, vectors) that preserve and faithfully reproduce specific IP elements or guidelines, ensuring consistency across all generated outputs.

The Tailored Generation APIs allow you to manage and train tailored models that maintain the integrity of your visual IP. You can train models through our Console or implement training directly via API. Explore the Console here.

Advanced Customization and Access:
As part of Bria’s Source Code & Weights product, developers seeking deeper customization can access Bria’s source-available GenAI models via Hugging Face.
This allows full control over fine-tuning, pipeline creation, and integration into proprietary workflows—empowering AI teams to develop and optimize their own generative AI solutions.

The Tailored Generation Training API provides a set of endpoints to manage the entire lifecycle of a tailored generation project:

  1. Project Management: Create and manage projects that define IP characteristics:
  • Create and Retrieve Projects: Use the /projects endpoints to create a new project or retrieve existing projects that belong to your organization.
  • Define IP Type: Specify the IP type (e.g., multi_object_set, defined_character, stylized_scene) and medium (currently illustration, with photography coming soon).
  • Manage Project Details: Use the /projects/{id} endpoints to update or delete specific projects.
  1. Dataset Management: Organize and refine datasets within your projects:
  • Create and Retrieve Datasets: Use the /datasets endpoints to create new datasets or retrieve existing ones.
  • Generate an Advanced Caption Prefix (For stylized_scene IP type)
    • If the IP type is stylized_scene, it is recommended to generate an advanced prefix before uploading images.
    • Use /tailored-gen/generate_prefix to generate a structured caption prefix using 1-6 sample images from the input images provided for training (preferably 6 if available).
    • Update the dataset with the generated prefix using /datasets/{dataset_id} before proceeding with image uploads.
  • Upload and Manage Images: Use the /datasets/{dataset_id}/images endpoints to upload images and manage their captions.
  • Clone Datasets: Create variations of existing datasets using the clone functionality.
  1. Model Management: Train and optimize tailored models based on your datasets:
  • Create and Retrieve Models: Use the /models endpoints to create new models or list existing ones.
  • Choose Training Version: Select between "light" (for fast generation and structure reference compatibility) or "max" (for superior prompt alignment and enhanced learning capabilities).
  • Monitor and Control: Manage the model lifecycle, including training start/stop and status monitoring.
Register and get API Access

Training Process

To train a tailored model:

  1. Create a Project: Use the /projects endpoint to define your IP type and medium.
  2. Create a Dataset: Use the /datasets endpoint to create a dataset within your project.
  3. Generate an Advanced Caption Prefix (For stylized_scene IP type only):
  • Before uploading images, call /tailored-gen/generate_prefix, sampling 1-6 images from the input images provided for training (preferably 6 if available).
  • Update the dataset with the generated prefix using /datasets/{dataset_id}.
  1. Upload Images: Upload images using the /datasets/{dataset_id}/images endpoint (minimum resolution: 1024x1024px).
  2. Prepare Dataset: Review auto-generated captions and update the dataset status to 'completed'.
  3. Create Model: Use the /models endpoint to create a model, selecting either the "light" or "max" training version.
  4. Start Training: Initiate training via the /models/{id}/start_training endpoint. Training typically takes 1-3 hours.
  5. Monitor Progress: Check the training status using the /models/{id} endpoint until training is 'Completed'.
  6. Generate Images: Once trained, your model can be used in multiple ways:
  • Use /text-to-image/tailored/{model_id} for text-to-image generation.
  • Use /text-to-vector/tailored/{model_id} for generating illustrative vector graphics.
  • Use /reimagine/tailored/{model_id} for structure-based generation.
  • Access through the Bria platform interface.

Alternatively, manage and train tailored models through Bria's user-friendly Console.
Get started here.

Restyle Portraits

The Restyle Portrait feature enables you to change the style of portrait images while preserving the identity of the subject. It utilizes a reference image of the person alongside a trained tailored model, ensuring consistent representation of facial features and identity across different visual styles.

Restyle Portrait is specifically optimized for portraits captured from the torso upward, with an ideal face resolution of at least 500×500 pixels. Using images below these recommended dimensions may lead to inconsistent or unsatisfactory results.

To use Restyle Portrait:

  • Reference Image: Provide a clear portrait image that meets the recommended guidelines.

  • Tailored Model: Select a tailored model trained specifically to reflect your desired style or visual IP.

Use the /tailored-gen/restyle_portrait endpoint to access this capability directly, allowing seamless integration of personalized style transformations into your workflow.

Guidance Methods

Some of the APIs below support various guidance methods to provide greater control over generation. These methods enable to guide the generation using not only a textual prompt, but also visuals.

The following APIs support guidance methods:

  • /text-to-image/tailored
  • /text-to-vector/tailored

ControlNets:
A set of methods that allow conditioning the model on additional inputs, providing detailed control over image generation.

  • controlnet_canny: Uses edge information from the input image to guide generation based on structural outlines.
  • controlnet_depth: Derives depth information to influence spatial arrangement in the generated image.
  • controlnet_recoloring: Uses a grayscale version of the input image to guide recoloring while preserving geometry.
  • controlnet_color_grid: Extracts a 16x16 color grid from the input image to guide the color scheme of the generated image.

You can specify up to two ControlNet guidance methods in a single request. Each method requires an accompanying image and a scale parameter to determine its impact on the generation inference.

When using multiple ControlNets, all input images must have the same aspect ratio, which will determine the aspect ratio of the generated results.

To use ControlNets, include the following parameters in your request:

  • guidance_method_X: Specify the guidance method (where X is 1, 2). If the parameter guidance_method_2 is used, guidance_method_1 must also be used. If you want to use only one method, use guidance_method_1.
  • guidance_method_X_scale: Set the impact of the guidance (0.0 to 1.0).
  • guidance_method_X_image_file: Provide the base64-encoded input image.
Guidance MethodPromptScaleInput ImageGuidance ImageOutput Image
ControlNet CannyAn exotic colorful shell on the beach1.0
ControlNet DepthA dog, exploring an alien planet0.8
ControlNet RecoloringA vibrant photo of a woman1.00
ControlNet Color GridA dynamic fantasy illustration of an erupting volcano0.7

Image Prompt Adapter:

This method offers two modes:

  • regular: Uses the image’s content, style elements, and color palette to guide generation.
  • style_only: Uses the image’s high-level style elements and color palette to influence the generated output.

To use Image Prompt Adapter as guidance, include the following parameters in your request:

  • image_prompt_mode: Specify how the input image influences the generation.
  • image_prompt_scale: Set the impact of the provided image on the generated result (0.0 to 1.0).
  • image_prompt_file: Provide the base64-encoded image file to be used as guidance.

or

  • image_prompt_urls: Provide a list of URLs pointing to publicly accessible images to be used as guidance.
Guidance MethodPromptModeScaleGuidance ImageOutput Image
Image Prompt AdapterA drawing of a lion laid on a table.regular0.85
Image Prompt AdapterA drawing of a bird.style1
Download OpenAPI description
tailored-generation.json
tailored-generation.yaml
Languages
Servers
https://engine.prod.bria-api.com/v1/

Endpoints

Operations

Delete Image

Request

Permanently remove an image from a dataset. This will also delete the image files and associated thumbnails.

Constraints:

  • Cannot delete images from completed datasets
Path
dataset_idstringrequired

Dataset ID

image_idintegerrequired

Image ID

Headers
api_tokenstringrequired
curl -i -X DELETE \
  'https://engine.prod.bria-api.com/v1/tailored-gen/datasets/{dataset_id}/images/{image_id}' \
  -H 'api_token: string'

Responses

Image successfully deleted

Response
No content

Create Model

Request

Create new model. A dataset can be used to train multiple models with different training versions (e.g., one light and one max). The model will belong to the same project as its dataset.

Headers
api_tokenstringrequired
Bodyapplication/jsonrequired
namestring

Name of the model (required)

dataset_idinteger

ID of the dataset to use (required)

training_versionstring

Training version (required):

  • Light: Choose this version when you need fast generation times and compatibility with our structure reference feature.
  • Max: Best for complex IPs requiring high fidelity and precise prompt alignment. Choose this version when accurate replication of specific attributes is your top priority. This version is currently not available when ip_medium=photography.
Enum"light""max"
descriptionstring

Description of the model (optional)

curl -i -X POST \
  https://engine.prod.bria-api.com/v1/tailored-gen/models \
  -H 'Content-Type: application/json' \
  -H 'api_token: string' \
  -d '{
    "name": "Lora Character Model",
    "dataset_id": 456,
    "training_version": "max",
    "description": "A model trained on Lora character illustrations"
  }'

Responses

Model successfully created

Bodyapplication/json
idinteger

Unique identifier for the model

namestring

Name of the model

descriptionstring

Description of the model

statusstring

Status of the model

Value"created"
training_versionstring

Training version

Enum"light""max"
generation_prefixstring

Text drawn from the dataset's caption_prefix that is automatically prepended to generation prompts to maintain consistency. It matches the dataset's caption_prefix. It can be bypassed during generation by setting include_generation_prefix=false. This field is empty upon model creation, and filled after the training starts.

project_idinteger

ID of the project this model belongs to

dataset_idinteger

ID of the dataset used for training

created_atstring(date-time)

Timestamp when the model was created

Response
application/json
{
  "id": 789,
  "name": "Lora Character Model",
  "description": "A model trained on Lora character illustrations",
  "status": "created",
  "training_version": "max",
  "generation_prefix": "An illustration of a character named Lora, a female character with purple hair,",
  "project_id": 123,
  "dataset_id": 456,
  "created_at": "2024-05-26T12:00:00Z"
}

Get Models

Request

Retrieve a list of models. If there are no models, an empty array is returned.

Headers
api_tokenstringrequired
curl -i -X GET \
  https://engine.prod.bria-api.com/v1/tailored-gen/models \
  -H 'api_token: string'

Responses

Successfully retrieved models

Bodyapplication/jsonArray [
idinteger

Unique identifier for the model

namestring

Name of the model

descriptionstring

Description of the model

statusstring

Status of the model

Enum"Created""InProgress""Completed""Failed""Stopping""Stopped"
training_versionstring

Training version

Enum"light""max"
generation_prefixstring

Text drawn from the dataset's caption_prefix that is automatically prepended to generation prompts to maintain consistency. It matches the dataset's caption_prefix. It can be bypassed during generation by setting include_generation_prefix=false.

project_idinteger

ID of the project this model belongs to

dataset_idinteger

ID of the dataset used for training

created_atstring(date-time)

Timestamp when the model was created

]
Response
application/json
[
  {
    "id": 789,
    "name": "Lora Character Model",
    "description": "A model trained on Lora character illustrations",
    "status": "Completed",
    "training_version": "max",
    "generation_prefix": "An illustration of a character named Lora, a female character with purple hair,",
    "project_id": 123,
    "dataset_id": 456,
    "created_at": "2024-05-26T12:00:00Z"
  },
  {
    "id": 790,
    "name": "Max Character Model",
    "description": "A model trained for faster generation",
    "status": "InProgress",
    "training_version": "max",
    "generation_prefix": "An illustration of a character named Max, a male character with spiky black hair,",
    "project_id": 123,
    "dataset_id": 457,
    "created_at": "2024-05-27T09:00:00Z"
  }
]