Skip to content
Image Editing
/
/
Generative Fill

Generative Fill

Request

Try out this capability in Bria's sandbox

Description

The GenFill Route enables the generation of objects by prompt in a specific region of an image.

You can define the area for object generation by using a mask that outlines the region where the object will be created. Our model is optimized to work seamlessly with blob-shaped masks.

Masks can be created by allowing users to draw directly on the image with a brush, for example. To access the SDK that demonstrates how to implement a brush feature in your interface, please refer to the following link.

Output Characteristics

  • The modified image is returned at the original resolution, preserving full visual quality without any automatic resizing or downscaling.
  • All areas outside the provided mask remain completely unchanged, ensuring pixel-perfect preservation of unedited regions.
  • If the input includes an alpha channel and preserve_alpha=true, the original transparency values (both full and partial) are maintained in the output.

Content Moderation

This endpoint includes granular content moderation controls to ensure safe usage across all stages of processing:

  • Prompt Moderation – Validates the provided prompt and rejects requests containing unsafe or prohibited terms before processing starts.
  • Input Image Moderation – Scans the uploaded image and stops processing if inappropriate or restricted content is detected.
  • Output Image Moderation – Evaluates the generated image and blocks the response if it violates safety guidelines.
Headers
api_tokenstringrequired

API token associated with the organization.

Bodyapplication/json
imagestringrequired

The source image to be handled by the API.
Supported input types:

  • Base64-encoded string
  • URL pointing to an image file that is publicly accessible and available at the time of processing.

Accepted formats: JPEG, JPG, PNG, WEBP.

maskstringrequired

The binary mask image that defines the region where object generation will occur.

Mask Requirements

  • The region to generate content must have a pixel value of 255 (white).
  • All other areas must have a pixel value of 0 (black).
  • The mask must have the same aspect ratio as the input image.

Supported Input Types

  • Base64-encoded string – provide the mask data directly in the request.
  • URL – provide a publicly accessible URL to the mask image.

Accepted formats: JPEG, JPG, PNG, WEBP.

Ensure that any provided URL is publicly accessible at the time of the request.

promptstringrequired

The prompt you would like to use to generate the object within the masked region.

Prompt Length Limits: ~90-110 words

refine_promptboolean

Controls the automatic prompt refinement feature.

  • true (default): The provided prompt is automatically adjusted for optimal results. The adjusted prompt is then returned in the response payload as refined_prompt.
  • false: The original prompt is used as-is, without modification.
Default:true
prompt_content_moderationboolean

When enabled (default: true), the input prompt is moderated before processing.

Expected Behavior

  • The prompt is scanned for NSFW content and terms that violate Bria’s ethical guidelines.
  • If the prompt fails moderation, the request is blocked and the API responds with a 422 error.
Default:true
negative_promptstring

The prompt you would like to use to specify details or attributes to avoid in the object generated within the masked region.

preserve_alphaboolean

Controls whether the alpha channel values from the input image are retained in the output, if the input includes an alpha channel.

  • When true: The output image maintains the original transparency of fully and partially transparent pixels.
  • When false: The output image is fully opaque.
  • Has no effect if the input image does not include an alpha channel.
Default:true
syncboolean

Specifies the response mode.

  • When false (default), the request is processed asynchronously: the API immediately returns a status URL to track progress.
  • When true, the request is processed synchronously: the API hold the connection open until the proccess is complete and then returns the final image URL in the response.
Default:false
webhook_urlstring, (uri)

Optional URL for receiving the result via webhook when the async job completes. See Webhooks.

seedinteger

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

visual_input_content_moderationboolean

When enabled, applies content moderation to input visual.

Expected behavior:

  • Processing stops if the image fails moderation.
  • Returns a 422 error with details about which parameter failed.
Default:false
visual_output_content_moderationboolean

When enabled, applies content moderation to result visual.

Expected behavior:

  • If the modified image fails moderation, returns a 422 error.
Default:false
POST
/gen_fill
curl -i -X POST \
  https://engine.prod.bria-api.com/v2/image/edit/gen_fill \
  -H 'Content-Type: application/json' \
  -H 'api_token: string' \
  -d '{
    "image": "https://labs-assets.bria.ai/sandbox-example-inputs/genfill_image_example.jpg",
    "mask": "https://labs-assets.bria.ai/sandbox-example-inputs/genfill_mask_exmple.jpg",
    "prompt": "A red delicious cherry"
  }'

Responses

Successful operation (Synchronous Success)

Bodyapplication/json
resultobjectrequired
request_idstringrequired
Response
{
  "result": {
    "image_url": "string"
  },
  "request_id": "string"
}