Sign in
v2 endpoints

Add Object by Text

Try out this capability in Bria's sandbox

Description

Insert new objects into an image using natural language to describe the object and its position.

Example: Instruction: "Place a red vase with flowers on the table"

<table> <tr> <th style="text-align: center;">Input Image</th> <th style="text-align: center;">Output Image</th> </tr> <tr> <td align="center" style="vertical-align: middle;"> <img src="https://bria-datasets.s3.us-east-1.amazonaws.com/Liza/an_empty_table_in_living_room.png" width="300" style="border-radius: 8px;"> </td> <td align="center" style="vertical-align: middle;"> <img src="https://bria-datasets.s3.us-east-1.amazonaws.com/Liza/bria_result+(1).png" width="300" style="border-radius: 8px;"> </td> </tr> </table>
post/add_object_by_text

Headers

api_tokenstring required

Request body

imagestring required

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.

instructionstring required

Natural language command.

webhook_urlstring uri

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

Response

Successful operation (Synchronous Success)

request_idstring required
warningstring

Returned only when ip_signal = true and the instruction field included IP content.

Changes