Sign in

v1

latestOpenAPI 3.0.02026-07-13650400.5 KB
Tailored Generation

Generate Image - Tailored model

Description This route allows you to generate images using a Tailored Model. Tailored models are trained on a visual IP (illustrations, photos, vectors) to faithfully reproduce specific IP elements or guidelines. You can train an engine through our Console or implement training on your platform via API.

Overview of Tailored Generation Training API 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 which define the 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.

  2. Dataset Management: Create and manage datasets within your projects. You can:

    • Create and Retrieve Datasets: Use the /datasets endpoints to create new datasets or retrieve existing ones.
    • 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.

  3. Model Management: Create and train 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.

Training Process Overview

To train a tailored model:

  1. Create a Project: Use the /projects endpoint to create a project and define your IP type and medium.

  2. Create a Dataset: Use the /datasets endpoint to create a dataset within your project.

  3. Upload Images: Upload images to your dataset using the /datasets/{dataset_id}/images endpoint. Images must be 1024x1024px minimum.

  4. Prepare Dataset: Review auto-generated captions and use the /datasets/{id} endpoint to set status to 'completed'.

  5. Create Model: Use the /models endpoint to create a model, selecting light or max training version.

  6. Start Training: Initiate training using the /models/{id}/start_training endpoint. Training takes 1-3 hours.

  7. Monitor Progress: Check training status using the /models/{id} endpoint until status shows 'Completed'.

  8. Generate Images: Once trained, your model can be used in multiple ways:

  • Use the /text-to-image/tailored/{model_id} endpoint for text-to-image generation
  • Use the /text-to-vector/tailored/{model_id} endpoint for generating illustrative vector graphics
  • Use the /reimagine/tailored/{model_id} endpoint for generating using a structure reference images
  • Access through the Bria platform interface

Alternatively, you can use the Bria platform to manage and train your tailored models through a user-friendly interface. Access the Bria platform here.

Guidance Methods

This API supports various guidance methods to provide greater control over text-to-image generation. These methods condition the model on additional inputs derived from user-provided images.

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.

Using ControlNets
You can specify up to four 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. The table below provides detailed information about each guidance method, with an example os use:

<table> <tr> <th>Guidance Method</th> <th>Prompt</th> <th>Scale</th> <th style="width: 150px;">Input Image</th> <th style="width: 150px;">Guidance Image</th> <th style="width: 150px;">Output Image</th> </tr> <tr> <td>ControlNet Canny</td> <td>An exotic colorful shell on the beach</td> <td>1.0</td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/canny_input.jpg" alt="Input Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/canny_map.png" alt="Guidance Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/canny_output.png" alt="Output Image" style="width: 150px; height: 150px; object-fit: contain;"></td> </tr> <tr> <td>ControlNet Depth</td> <td>A dog, exploring an alien planet</td> <td>0.8</td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/depth_input.jpg" alt="Input Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/depth_map.webp" alt="Guidance Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/depth_output.png" alt="Output Image" style="width: 150px; height: 150px; object-fit: contain;"></td> </tr> <tr> <td>ControlNet Recoloring</td> <td>A vibrant photo of a woman</td> <td>1.00</td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/recoloring_input.png" alt="Input Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/recoloring_map.webp" alt="Guidance Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/recoloring_output.png" alt="Output Image" style="width: 150px; height: 150px; object-fit: contain;"></td> </tr> <tr> <td>ControlNet Color Grid</td> <td>A dynamic fantasy illustration of an erupting volcano</td> <td>0.7</td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/colorgrid_input.png" alt="Input Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/colorgrid_map.png" alt="Guidance Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/colorgrid_output.png" alt="Output Image" style="width: 150px; height: 150px; object-fit: contain;"></td> </tr> </table>

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

  • guidance_method_X: Specify the guidance method (where X is 1, 2). If the paramter guidance_method_2 is used, so does guidance_method_1 has to be used, and so on. If you would like to use only one method, use the paratmer 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 IP_adapter:

    Guides the model based on the input image and its associated style. This method offers two modes:

    • regular: Uses the full input image to condition the model, influencing both content and style.
    • style_only: Focuses only on the style of the input image, allowing the model to generate images based on the provided aesthetic without altering the content.

Using IP-Adapter <table>

<tr> <th>Guidance Method</th> <th>Prompt</th> <th>Mode</th> <th>Scale</th> <th style="width: 150px;">Guidance Image</th> <th style="width: 150px;">Output Image</th> </tr> <tr> <td>IP-adapter</td> <td>A drawing of a lion laid on a table.</td> <td>regular</td> <td>0.85</td> <td style="width: 150px;"><img src="https://images.pexels.com/photos/3246665/pexels-photo-3246665.png?auto=compress&cs=tinysrgb&w=1260&h=750&dpr=2" alt="Input Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.us-east-1.amazonaws.com/temp_exp_or/image.png" alt="Output Image" style="width: 150px; height: 150px; object-fit: contain;"></td> </tr> <tr> <td>IP-adapter</td> <td>A drawing of a bird.</td> <td>style</td> <td>1</td> <td style="width: 150px;"><img src="https://bria-datasets.s3.us-east-1.amazonaws.com/temp_exp_or/photo-1575995872537-3793d29d972c.avif" alt="Input Image" style="width: 150px; height: 150px; object-fit: contain;"></td> <td style="width: 150px;"><img src="https://bria-datasets.s3.us-east-1.amazonaws.com/temp_exp_or/seed_627499055.png" alt="Output Image" style="width: 150px; height: 150px; object-fit: contain;"></td> </tr> </table>
post/text-to-image/tailored/{model_id}

Path parameters

model_idstring required

The model id of the tailored model you would like to use in the request.

Headers

api_tokenstring required

Request body

promptstring

The prompt you would like to use to generate images. Bria currently supports prompts in English only, excluding special characters.

num_resultsinteger

How many images you would like to generate. This parameter is optional. When fast=false, only num_results 1, 2 are supported. and when using any guidance method, please use the value 1.

aspect_ratio'1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '4:5' | '5:4' | '9:16' | '16:9'

The aspect ratio of the image.

syncboolean

Determines the response mode. When true, responses are synchronous. With false, responses are asynchronous, immediately providing URLs for images that are generated in the background. Use polling for the URLs to retrieve images once ready.

fastboolean

Determines the generation mode. When true, the generation will utilize the fast mode which provides the best balance between speed and quality. When false, the regular mode will be utilized. At the moment, tailored models trained using the 'Max' training version, do not support fast generation.

seedinteger

You can choose whether you want your generated result to be random or predictable. You can recreate the same result in the future by using the seed value of a result from the response with the prompt, model type and model version. You can exclude this parameter if you are not interested in recreating your results. This parameter is optional.

steps_numinteger

The number of iterations the model goes through to refine the generated image. This parameter is optional. When fast=false, the default value is 30, the minimum is 20 and the maximum is 50.

model_influencenumber float

The influence of the structure reference on the generated image. This parameter is optional. Higher value means more adherence to the reference structure.

include_generation_prefixboolean

When true, the model's generation prefix is automatically prepended to your prompt to maintain consistency with the training data, while false allows you to override the training prefix and write the complete prompt yourself, including any preferred prefix text.

guidance_method_1'controlnet_canny' | 'controlnet_depth' | 'controlnet_recoloring' | 'controlnet_color_grid'

Which guidance type you would like to include in the generation. Up to 4 guidance methods can be combined during a single inference. This parameter is optional. At the moment, tailored models trained using the 'Max' training version, do not support generation with guidance methods.

guidance_method_1_scalenumber float

The impact of the guidance.

guidance_method_1_image_filestring

The image that should be used as guidance, in base64 format, with the method defined in guidance_method_1. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB. If more then one guidance method is used, all guidance images must be of the same aspect ratio, and this will be the aspect ratio of the generated results. If guidance_method_1 is selected, an image must be provided.

guidance_method_2'controlnet_canny' | 'controlnet_depth' | 'controlnet_recoloring' | 'controlnet_color_grid'

Which guidance type you would like to include in the generation. Up to 4 guidance methods can be combined during a single inference. This parameter is optional. At the moment, tailored models trained using the 'Max' training version, do not support generation with guidance methods.

guidance_method_2_scalenumber float

The impact of the guidance.

guidance_method_2_image_filestring

The image that should be used as guidance, in base64 format, with the method defined in guidance_method_2. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB. If more then one guidance method is used, all guidance images must be of the same aspect ratio, and this will be the aspect ratio of the generated results. If guidance_method_1 is selected, an image must be provided.

image_prompt_mode'regular' | 'style_only'

The mode to apply to the image guidance.

  • regular: Uses both content and style from the provided image for the generation.
  • style_only: Uses only the style from the provided image.
image_prompt_filestring

The image file to be used as guidance for the IP-Adapter, in base64 format. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB.

image_prompt_urlsstring[]

A list of URLs of images that should be used as guidance for the IP-Adapter. Accepted formats are jpeg, jpg, png, webp. The URLs should point to accessible, publicly available images.

image_prompt_scalenumber float

The impact of the provided image on the generated results. A value between 0.0 (no impact) and 1.0 (full impact).

Response

Successful operation.