v1

latestOpenAPI 3.0.02026-07-13650400.5 KB

Image Generation

Generate Image - fast model

Description

The /text-to-image/fast Route is optimized for speed, enabling rapid image creation without compromising quality. This model allows for generating high-quality, photorealistic and artistic, images with a resolution of up to 1024x1024 pixels, supporting a variety of aspect ratios natively to accommodate diverse creative needs. Ideal for applications requiring quick turnaround without sacrificing image fidelity.

Advanced Customization and Access:

Beyond the API, developers interested in deeper customization can access BRIA's models directly through Hugging Face. This alternative provides access to the underlying model source code, offering additional features such as ControlNets: <a href="https://huggingface.co/briaai/BRIA-2.3-ControlNet-Canny" target="_blank">Canny</a> , <a href="https://huggingface.co/briaai/BRIA-2.3-ControlNet-Depth" target="_blank">Depth</a>, and <a href="https://huggingface.co/briaai/BRIA-2.3-ControlNet-Recoloring" target="_blank">ReColoring</a>. This option is ideal for developers seeking advanced control over the image generation process and those who wish to integrate cutting-edge AI directly into their workflows.

An example:

prompt: A portrait of a Beautiful and playful ethereal singer, art deco, fantasy, intricate art deco golden designs, elegant, highly detailed, sharp focus, blurry background, teal and orange shades

BRIA FAST model 2.3:

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/fast/{model_version}

Path parameters

model_version'2.3' required

The model version 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. How many images you would like to generate. 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.

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.

medium'photography' | 'art'

Which medium should be included in your generated images. This parameter is optional.

prompt_enhancementboolean

When set to true, enhances the provided prompt by generating additional, more descriptive variations, resulting in more diverse and creative output images. Note that turning this flag on may result in a few additional seconds to the inference time.

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.

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.

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.