# Generate Ads

Bria's Ads Generation API enables builders to create multiple ads (scenes) in various sizes and resolutions, all unified by the same branding, style, and messaging. You can start exploring immediately with our public templates and brands.
For creating your own private templates and brands, please Contact Us.
Getting Started with Public Assets
You can start exploring the API immediately using our public templates and brands, with no setup required. You can also explore them in our Playground Demo.
* Public Template IDs: 
    * 1062: A template that requires a brand ID.
    * 1061: A brand-independent template (does not require a brand ID).
 Public Brand IDs: 167, 166, 122, 121, 120. These can be used for testing with compatible templates like 1062.  Important: Public templates and brands can only be used with each other and cannot be mixed with private assets.

    


Template  
Templates enable to repurpose and reuse well-design ads that share the same style, content and branded elements.It consists of multiple ads (“scenes”) and includes configurations for customizing the content at scale.

Smart Image Feature  
A standout feature of BRIA's Ads Generation API is its ability to seamlessly embed objects, products, and presenter images into another image (a "smart image"). This AI-powered capability allows for generating diverse backgrounds for the embedded image or extending the background to fit the ad's design perfectly.

How It Works  
The Ads Generation API works by sending a template ID along with inputs such as text, images, the main object with its background definition, and a brand ID (including logos, colors, and fonts). In response, the API generates a set of ad images.

In thie endpoint, responses are asynchronous, immediately providing URLs for ads that are generated in the background. Use polling for the URLs to retrieve ads once ready.

Templates can be easily created using BRIA’s Ads Editor. Once a template is ready, it can be used to produce multiple ad versions with varying messaging, branding, and images.

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.

Endpoint: POST /ads/generate

## Header parameters:

  - `api_token` (string, required)
    API token associated with the organization.

## Request fields (application/json):

  - `content_moderation` (boolean)
    When enabled, applies content moderation to both input visuals and generated outputs.

For input images:
- Processing stops at the first image that fails moderation
- Returns a 422 error with details about which parameter failed

For generated ads:
- Failed ads are replaced with zero-byte files at their placeholder URLs
- Successful ads are stored at their original placeholder URLs

  - `template_id` (string)
    The ID of the template to be used for generating the ads scenes.

  - `brand_id` (string)
    The ID of the brand to be used across all generated ads. A required field, unless the template is non brand related template and in that case even if brand if is provided, it isn't used.

  - `smart_image` (object)
    Smart image object for generating an image based on the embedded image, including the main object and its background definition (expand or generate_by_text).

  - `smart_image.input_image_url` (string)
    URL of the input image that will be embedded within the smart image.

  - `smart_image.scene` (object)

  - `smart_image.scene.operation` (string)
    Enum: "expand_image", "lifestyle_shot_by_text"

  - `smart_image.scene.input` (string)
    Background prompt or hex color for the image’s background. If the operation chosen is "expand" this parameter is ignored.

  - `elements` (array)
    List of text/images objects

  - `elements.layer_type` (string)
    The element type, either "text" or "image".
    Enum: "text", "image"

  - `elements.content_type` (string)
    The heading level configuration for the text. This allows the same text to be inserted into multiple elements across scenes.
Value should be in the format - Heading , Body , Image  when  can be replaced with any value between #1-#5 (for example Heading #1, Image #1 and etc.)

  - `elements.content` (string)
    Content of the text or image, if content_type is set to text it should be a string, and if content_type is image it should be an image URL.
To ignore this element, set this parameter to an empty string.

  - `elements.id` (string)
    Unique identifier for the element.

## Response 200 fields (application/json):

  - `result` (array)
    A list of objects, where each object contains an image URL corresponding to a scene in the template, the scene's name, and its resolution.

  - `result.id` (string)
    The unique ID for the generated scene.

  - `result.name` (string)
    The name of the scene from the template used to generate the image.
    Example: "scene_name"

  - `result.url` (string)
    The URL to download the generated scene result as a .png image.
    Example: "IMAGE_URL"

  - `result.resolution` (object)
    An object containing the width and height of the generated image. Can be an empty object if resolution is not available.
    Example: {"width":1920,"height":1080}

  - `result.resolution.width` (integer)
    Example: 1920

  - `result.resolution.height` (integer)
    Example: 1080


## Response 400 fields

## Response 401 fields

## Response 500 fields