# Overview

Bria’s Image Generation API provides builders with a flexible and controllable way to generate high-quality visuals from textual prompts or reference images.  
It supports various resolutions, aspect ratios, and generation speeds, enabling scalable and efficient production of photos, illustrations, and vector graphics for commercial use.

**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](https://huggingface.co/briaai).   
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.

### **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/base`  
- `/text-to-image/fast`  
- `/text-to-vector/base`  
- `/text-to-vector/fast`  

**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.

<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"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/canny_map.png"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/canny_output.png"></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"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/depth_map.webp"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/depth_output.png"></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"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/recoloring_map.webp"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/recoloring_output.png"></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"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/colorgrid_map.png"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.amazonaws.com/api_doc/cns/colorgrid_output.png"></td>
  </tr>
</table>  

**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.

<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>Image Prompt 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"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.us-east-1.amazonaws.com/temp_exp_or/image.png"></td>
  </tr>
  <tr>
    <td>Image Prompt 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"></td>
    <td style="width: 150px;"><img src="https://bria-datasets.s3.us-east-1.amazonaws.com/temp_exp_or/seed_627499055.png"></td>
  </tr>
</table>  

### **IP-related prompts**
Our models are trained exclusively on fully licensed, safe-for-commercial-use data.  
Prompts that reference public figures, brands, or other protected content may result in generic or altered outputs.  
These prompts are not blocked, but results may differ from what you expect.   
If an IP-related signal is detected in the prompt, the following warning will appear in the API response:
```text
  This prompt may contain intellectual property (IP)-protected content.
  To ensure compliance and safety, certain elements may be omitted or altered.
  As a result, the output may not fully meet your request.
  ```



## Servers

```
https://engine.prod.bria-api.com/v1
```

## Download OpenAPI description

[Overview](https://docs.bria.ai/_spec/image-generation.yaml)

## Endpoints

### Generate Image - Base

 - [POST /text-to-image/base/{model_version}](https://docs.bria.ai/image-generation/endpoints/text-to-image-base.md): 


This Image Generation pipeline enables builders to integrate the generation of high-quality, photorealistic or artistic images into their products. It harnesses the power of Bria’s proprietary text-to-image foundation models, enhanced with additional capabilities that optimize output quality and provide greater control. The pipeline supports native generation at 1MP resolution and accommodates a wide range of aspect ratios to fit diverse needs.



: A professional headshot of a CEO


           

: A surreal and whimsical food concept photo of a sunny-side-up egg clipped to a rope with a wooden clothespin, against a bright turquoise background. The yolk is glossy and slightly runny, dripping downward, creating a playful and unexpected visual. The composition is clean, colorful, and minimalistic, with a creative twist that evokes humor and imagination. On the bottom text "Just hanging out... Sunny side up!"

 

This API endpoint supports content moderation via an optional parameter that can prevent generation if input images contain inappropriate content, and filters out unsafe generated images - the first blocked input image will fail the entire request.

### Generate Image - Fast

 - [POST /text-to-image/fast/{model_version}](https://docs.bria.ai/image-generation/endpoints/text-to-image-fast.md): 



This Image Generation pipeline is optimized for speed, enabling builders to rapidly generate high-quality, photorealistic or artistic images without compromising visual fidelity. It leverages Bria’s proprietary text-to-image foundation models, combined with performance-oriented enhancements that ensure faster generation while maintaining control and flexibility. The pipeline supports native generation at 1MP resolution and accommodates a wide range of aspect ratios, making it ideal for applications that require quick turnaround with consistent output control.




: 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



       
This API endpoint supports content moderation via an optional parameter that can prevent generation if input images contain inappropriate content, and filters out unsafe generated images - the first blocked input image will fail the entire request.

### Generate Image - HD

 - [POST /text-to-image/hd/{model_version}](https://docs.bria.ai/image-generation/endpoints/text-to-image-hd.md): 



This Image Generation pipeline is designed for builders working on projects that demand maximum image detail and clarity. It leverages Bria’s proprietary text-to-image foundation models, enhanced to deliver high-resolution outputs while preserving control and flexibility. The pipeline supports native generation at 1920×1080 resolution (or 1536×1536 for square aspect ratios) and accommodates a wide range of aspect ratios, making it ideal for use cases where visual precision and output quality are critical.



: A photo of detailed short female blond hair viewed from behind, with rich texture and clearly visible individual strands that give depth and realism, and featuring subtle waves reflect light



 

: 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



 
This API endpoint supports content moderation via an optional parameter that filters out unsafe generated images.       

### Generate Vector Graphics - Base (Beta)

 - [POST /text-to-vector/base/{model_version}](https://docs.bria.ai/image-generation/endpoints/text-to-vector-base.md): 



This Vector Generation pipeline enables builders to integrate the generation of high-quality, editable vector graphic assets into their products or workflows. It leverages Bria’s proprietary text-to-image foundation models, enhanced to produce vector-compatible outputs while maintaining control and flexibility. The pipeline supports generation of scalable assets such as icons, logos, and illustrations, making it ideal for use cases requiring vector graphics.




: A sticker of a cute kitten

   

: A beautiful butterfly


 


 On the left, a generated vector illustration. On the right, the same illustration after being re-colored in a vector editor

 This API endpoint supports content moderation via an optional parameter that can prevent generation if input images contain inappropriate content, and filters out unsafe generated images - the first blocked input image will fail the entire request.

### Generate Vector Graphics - Fast (Beta)

 - [POST /text-to-vector/fast/{model_version}](https://docs.bria.ai/image-generation/endpoints/text-to-vector-fast.md): 



This Vector Generation pipeline is optimized for speed, enabling builders to quickly integrate the generation of high-quality, editable vector graphic assets into their products or workflows. It leverages Bria’s proprietary text-to-image foundation models, enhanced to accelerate output while maintaining control and flexibility. The pipeline supports generation of scalable assets such as icons, logos, and illustrations, making it ideal for use cases that require rapid delivery of vector graphics.



: An icon of a bird with a blue head and yellow beak against a solid background

   
This API endpoint supports content moderation via an optional parameter that can prevent generation if input images contain inappropriate content, and filters out unsafe generated images - the first blocked input image will fail the entire request.

### Reimagine - Structure Reference

 - [POST /reimagine](https://docs.bria.ai/image-generation/endpoints/reimagine-structure-reference.md): 

The  endpoint in Bria’s API allows guiding image generation not just with prompts but also by using an input image. This feature retains the original structure and depth of the input while incorporating new materials, colors, and textures to create fresh visuals.
### Key Benefits
- : Use a reference image to replicate its outline and depth, reducing the need for complex prompts and minimizing trial and error.

- :
    - Convert illustrations, sketches, or photos into new illustrative outputs.
    - Transform photos into variations that maintain the original layout.
    
- : Control how much the input image's structure impacts the output on a scale from 0 to 1, allowing for diverse creative results.

- : Ensures the output maintains the reference image's aspect ratio for layout consistency. The output resolution is approximately 1 megapixel.

- : Combine structural references with tailored models to include unique IP characteristics in the generated outputs. 
### Potential Use Cases


Empower creative platforms and editing tools with advanced levels of control and flexibility for generating visual content.
- 
  
  Structure reference image
  
  
  
  
  Generated Visual (combined into a gif)
  
  
- 
  
  Structure reference image
  
  
  
  prompt: A watercolor painting of a lively urban street featuring a red vintage car parked in front of multi-story buildings, where soft, fluid brushstrokes capture the subtle gradients in the building facades, with warm earth tones blending into cool blues and grays for the shadows, giving the scene a nostalgic and dreamy atmosphere.
  
  structure_ref_influence: 0.75
  
  Generated Visual
  
  
- 
  
  Structure reference image
  
  
  
  prompt: A ginger kitten sits on a textured beige surface, surrounded by soft balls of yarn.
  
  structure_ref_influence: 0.75
  
  Generated Visual
  
  
- 
  
  Structure reference image
  
  
  
  prompt: curled orange peel.
  
  structure_ref_influence: 0.1
  
  Generated Visual
  
  


- : Maintain the structure and detail of assets while updating textures and colors for fresh looks without altering the original shape or layout.

- : Simplifies design iteration for gaming assets, enabling rapid exploration and refinement.

- : Transform marketing visuals while preserving their composition, adding new styles and elements with structural guidance.

- : Repurpose user-generated content for marketing campaigns, making it fit seamlessly with brand aesthetics.


This API endpoint supports content moderation via an optional parameter that can prevent generation if input images contain inappropriate content, and filters out unsafe generated images - the first blocked input image will fail the entire request.

### Prompt enhancement

 - [POST /prompt_enhancer](https://docs.bria.ai/image-generation/endpoints/prompt-enhancer.md): 



The /prompt_enhancer route is designed to boost users' creativity by transforming simple prompts into more detailed and vivid descriptions. This helps generate richer, more diverse images. (It is also available as a built-in flag in all of our /text-to-image routes, excluding tailored generation.)

We recommend using this feature by offering users a range of prompts to choose from before generating an image, enabling them to explore creative ideas.

*Works best with short to medium prompts of up to approximately 50 words.



: A cat

 

: A black and white photograph of a sophisticated Siamese cat, sitting in a chair next to a large window, with the urban cityscape visible in the background