Skip to content
Tailored Generation
/
/
Get Projects

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.

Fully Automated Training Mode Bria supports users in training high-quality finetuned models without the guesswork. Based on the selected IP type & dataset, Bria automatically selects the right training parameters. This means that the user only needs to spend time curating their dataset.

Advanced Customization and Access: Bria offers 2 types of advanced training customization: Expert training mode and source-code & weights.

  • Expert training mode is for LoRa Finetune experts and provides the ability to finetune training parameters and upload larger training datasets.
  • Source-code & Weights is for developers seeking deeper customization and access to Bria’s source-available GenAI models via Hugging Face.

All methods allow 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.
  • 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 a Visual Schema (FIBO Models)
    • Required for fibo training versions
    • Use /tailored-gen/generate_visual_schema to create a structured visual schema using 5-10 sample images.
  • Generate Caption Prefix (Legacy Models)
    • Use /tailored-gen/generate_prefix to create a text-based prefix for legacy training versions.
  • Refine Structured Data
    • Use /tailored-gen/refine_structured_prompt to iterate on your Visual Schema or Image Captions using natural language instructions.
    • Example: You can send your generated schema with the instruction "Character's name is Lucy" to improve the training metadata programmatically.
  • Upload and Manage Images:
    • Basic upload: Use /datasets/{dataset_id}/images to upload up to 200 images individually.
    • Bulk upload: Use /datasets/{dataset_id}/images/bulk to upload zip files with >200 high-quality images (Advanced).
  • 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 mode: Select between Fully automated mode (automatic training based on Bria's recipes) and Expert mode (for training parameter tweaking).
  • Choose Training version: Select "Fibo" for best results.
  • Monitor and Control: Manage the model lifecycle, including training start/stop, status monitoring, and version control over the training parameters.
  1. Generation Capabilities:
  • Image Generation: Use v2/image/generate/tailored (FIBO) or v1/text-to-image/tailored (Legacy).
  • Structured Prompting: Use v2/structured_prompt/generate/tailored to create structured prompts via VLM before generation.
  • Video Generation: Use /video/generate/tailored/image-to-video to animate tailored images.
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. Define Visual Identity:
    • Step A (Generate): Call /tailored-gen/generate_visual_schema, sampling 5-10 images from your input set.
    • Step B (Refine - Optional): Call /tailored-gen/refine_structured_prompt with the generated schema and instructions to tweak the definitions (e.g., "Remove references to blue background").
    • Step C (Apply): Update the dataset with the final schema using /datasets/{dataset_id}.
  4. Upload Images: Upload images using the /datasets/{dataset_id}/images or /datasets/{dataset_id}/images/bulk endpoints (minimum resolution: 1024x1024px).
  5. Prepare Dataset: Review auto-generated captions (you can also use refine_structured_prompt to fix specific image captions) and update the dataset status to 'completed'.
  6. Create Model: Use the /models endpoint to create a model, which requires a training mode and version.
  7. Start Training: Initiate training via the /models/{id}/start_training endpoint. Training typically takes 4-6 hours.
  8. Monitor Progress: Check the training status using the /models/{id} endpoint until training is 'Completed'.
  9. Generate Images:
  • Use v2/image/generate/tailored for text-to-image generation.

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

Download OpenAPI description
tailored-generation.json
tailored-generation.yaml
Languages
Servers
https://engine.prod.bria-api.com/v2
https://engine.prod.bria-api.com/v1

Project

Manage your projects

Operations

Create Project

Request

Create a new project within the organization.

Project Locking & Training Version: Projects can be dedicated to a specific training version family (FIBO or Legacy).

  • If training_version is provided: The project is locked to that family immediately.
  • If training_version is omitted (null): The project remains unlocked until the first dataset is created. Upon creating the first dataset, the project automatically inherits the dataset's training_version and becomes locked to that family.

Families:

  • FIBO: fibo
  • Legacy: max, light, 3.2, 2.3 (Legacy versions are interchangeable within a project).

The following IP types are supported:

Defined Character A specific character that maintains consistent identity and unique traits while being reproduced in different poses, situations, and actions.

Medium: Photography

Example of defined character in different poses, photography medium

Medium: Illustration

Example of defined character in different poses, illustrative medium

Stylized Scene Complete environments or scenes created with a consistent visual style, look, and feel.

Medium: Photography

Example of stylized scene showing cohesive environment, photography medium

Medium: Illustration

Example of stylized scene showing cohesive environment, illustrative medium

Multi-Object Set A collection of different objects sharing a common style, design language, or color scheme. Objects are typically isolated on solid backgrounds. Example of multi-object set showing different objects with consistent style

Object Variants Multiple variations of the same object type, maintaining consistent style and structure while showing different interpretations. Objects are typically isolated on solid backgrounds. Example of object variants showing different versions of the same object

Icons A collection of cohesive, small-scale illustrations or symbols designed to represent concepts, actions, or objects in interfaces and applications. Maintains consistent visual style across the set. Example of icon set with consistent design language

Character Variants Multiple characters sharing the same fundamental structure, style, and color palette, allowing creation of new characters that fit within the established design system. Example of character variants showing different characters with consistent style

Headers
api_tokenstringrequired
Bodyapplication/jsonrequired
project_namestring

Name of the project (required)

project_descriptionstring

Description of the project (optional)

ip_namestring

Required only for defined_character IP type. The name of the character (1-3 words, e.g., "Lora", "Captain Smith"). This name will be incorporated into the automatically created caption prefix and generation prefix, used consistently during training and generation.

ip_descriptionstring

Required only for defined_character and object_variants IP types. A short phrase (up to 6 words) describing only the most crucial distinguishing features of your character (e.g., "a female character with purple hair"). Keep it brief as the model will learn additional details from the training images. This description will be incorporated into the automatically created caption prefix and generation prefix, used during training and generation.

ip_mediumstring

Medium of the IP (required)

  • photography
  • illustration
Enum"photography""illustration"
ip_typestring

Type of the IP (required):

  • defined_character: A specific predefined character or person that can be reproduced consistently in different situations, poses, or actions, preserving their identity and unique traits.
  • stylized_scene: A complete scene or environment, such as a gaming background or a series of photos with a shared color palette, created with a cohesive style, look, and feel.
  • other: For IP types that don't fit into any of the types

The Types below are currently avilable only when ip_medium = illustration:

  • object_variants: Variations of the same object type, designed with consistent style, structure, and coloring, showcasing different interpretations. These objects are often isolated on a solid background.
  • multi_object_set: Multiple distinct objects that share a mutual style, design language, or color scheme. These objects are often isolated on a solid background.
  • icons: A collection of small, visually distinct illustrations, such as symbols or graphical elements, designed with a cohesive style and used to represent concepts, actions, or objects in interfaces, applications, or visual communication materials.
  • character_variants: Multiple characters sharing the same structure, style, and color palette, with the ability to create new characters that adhere to these shared characteristics while introducing unique elements.
Enum"multi_object_set""object_variants""icons""defined_character""character_variants""stylized_scene""other"
curl -i -X POST \
  https://engine.prod.bria-api.com/v1/tailored-gen/projects \
  -H 'Content-Type: application/json' \
  -H 'api_token: string' \
  -d '{
    "project_name": "Branded Character",
    "ip_name": "Adventure Series Characters",
    "ip_description": "A set of adventure game characters with unique personalities",
    "ip_medium": "illustration",
    "ip_type": "defined_character"
  }'

Responses

Project successfully created

Bodyapplication/json
idinteger

Unique identifier for the project

project_namestring

Name of the project

project_descriptionstring

Description of the project

ip_namestring

Name of the IP

ip_descriptionstring

Description of the IP

ip_mediumstring

Medium of the IP

ip_typestring

Type of the IP

training_versionstring or null

The training version family this project is locked to (e.g., 'fibo', 'max', or null if unlocked).

statusstring

Status of the project

Value"active"
created_atstring(date-time)

Timestamp when the project was created

Response
application/json
{
  "id": 123,
  "project_name": "Branded Character",
  "project_description": "",
  "ip_name": "Lora",
  "ip_description": "A female character with purple hair",
  "ip_medium": "illustration",
  "ip_type": "defined_character",
  "training_version": "fibo",
  "status": "active",
  "created_at": "2024-05-26T12:00:00Z"
}

Get Projects

Request

Retrieve all projects within the organization. If there are no projects, returns an empty array.

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

Responses

Successfully retrieved projects

Bodyapplication/jsonArray [
idinteger

Unique identifier for the project

project_namestring

Name of the project

project_descriptionstring

Description of the project

ip_namestring

Name of the IP

ip_descriptionstring

Description of the IP

ip_mediumstring

Medium of the IP

Enum"photography""illustration"
ip_typestring

Type of the IP

Enum"multi_object_set""object_variants""defined_object""icons""defined_character""character_variants""stylized_scene""other"
training_versionstring or null

The training version family this project is locked to.

statusstring

Status of the project

Value"active"
created_atstring(date-time)

Timestamp when the project was created

updated_atstring(date-time)

Timestamp when the project was last updated

]
Response
application/json
[
  {
    "id": 123,
    "project_name": "Branded Character",
    "project_description": "",
    "ip_name": "Lora",
    "ip_description": "A female character with purple hair",
    "ip_medium": "illustration",
    "ip_type": "defined_character",
    "status": "active",
    "created_at": "2024-05-26T12:00:00Z",
    "updated_at": "2024-05-26T14:30:00Z"
  },
  {
    "id": 124,
    "project_name": "Branded icons",
    "project_description": "",
    "ip_name": "",
    "ip_description": "",
    "ip_medium": "illustration",
    "ip_type": "icons",
    "status": "active",
    "created_at": "2024-05-27T09:00:00Z",
    "updated_at": "2024-05-27T10:15:00Z"
  }
]

Get Project by ID

Request

Retrieve full project information including project name and description, IP name and description, IP medium (photography/illustration), IP type, status, and timestamps.

Path
project_idstringrequired

Project ID

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

Responses

Successfully retrieved project

Bodyapplication/json
idinteger

Unique identifier for the project

project_namestring

Name of the project

project_descriptionstring

Description of the project

ip_namestring

Name of the IP

ip_descriptionstring

Description of the IP

ip_mediumstring

Medium of the IP

Enum"photography""illustration"
ip_typestring

Type of the IP

Enum"multi_object_set""object_variants""defined_object""icons""defined_character""character_variants""stylized_scene""other"
training_versionstring or null

The training version family this project is locked to.

statusstring

Status of the project

Value"active"
created_atstring(date-time)

Timestamp when the project was created

Response
application/json
{
  "id": 123,
  "project_name": "Branded Character",
  "project_description": "",
  "ip_name": "Lora",
  "ip_description": "A female character with purple hair",
  "ip_medium": "illustration",
  "ip_type": "defined_character",
  "training_version": "fibo",
  "status": "active",
  "created_at": "2024-05-26T12:00:00Z"
}

Dataset

Manage training datasets

Operations

Model

Manage and train models

Operations

Image Generation V2

Generation using FIBO models

Operations

Image Generation (Legacy)

Generation using Legacy models

Operations

Video Generation

Image-to-Video capabilities

Operations