Skip to content

Overview

The Bria Attribution Service enables developers to integrate Bria’s patented attribution technology, ensuring transparent compensation to content owners for their contributions to AI-generated outputs.

This service can be integrated by one of two integration architectures to fit different business and technical needs:

Attribution with No Compute Cost, where images are sent directly to Bria for processing.

Attribution with Full Data Privacy, where the Attribution Model is hosted within your environment and only irreversible vectors are shared with Bria.

Both approaches guarantee fair revenue sharing, royalties distribution, and legal protection for the commercial use of generated content.

Languages
Servers
Production

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

Attribution via Images API (model hosted by Bria)

Request

Bodyapplication/jsonrequired
imagestringrequired

Base64-encoded image

model_versionstringrequired

Version of the model to use

Enum"2.3""3.0""3.2"
curl -i -X POST \
  https://engine.prod.bria-api.com/v2/image/attribution/by_image \
  -H 'Content-Type: application/json' \
  -d '{
    "image": "iVBORw0KGgoAAAANSUhEUgAA... (truncated)",
    "model_version": "2.3"
  }'

Responses

Accepted

Bodyapplication/json
request_idstringrequired
status_urlstringrequired
Response
application/json
{ "request_id": "string", "status_url": "string" }

Attribution By Embedding (irreversible vectors - self-hosted)

Request

This API integration should take place after completing the installation of the attribution model, according to this reposetory: Bria Attribution GitHub.

Bodyapplication/jsonrequired
embeddings_base64Array of stringsrequired

List of base64-encoded embeddings

model_versionstringrequired

Version of the model to use

Enum"2.3""3.0""3.2"
embeddings_uidstring

Optional unique identifier for embeddings

model_namestring

Optional model name

curl -i -X POST \
  https://engine.prod.bria-api.com/v2/image/attribution/by_embedding \
  -H 'Content-Type: application/json' \
  -d '{
    "embeddings_base64": [
      "AAABAC8vLwAA... (truncated)"
    ],
    "model_version": "3.2"
  }'

Responses

Accepted

Bodyapplication/json
request_idstringrequired
status_urlstringrequired
Response
application/json
{ "request_id": "string", "status_url": "string" }