Video > Object Removal By Prompt
Object Removal By Prompt
Remove an object from a video by prompt text.
Examples
curl -X POST https://api.medux.io/api/app/v1/process/video/object_removal_by_prompt \
-H 'Authorization: Bearer $MEDUX_API_KEY' \
-H 'Content-Type: application/json' \
-d '{"input_file_id":"FILE_ID","model_id":"remove-video-object-by-prompt-default","prompt_text":"Hello from Medux"}'Auth Requirements
Authentication is required via Authorization header.
Preconditions
Upload the source file and create a file reference before calling this endpoint.
Successful requests return a Medux task record immediately. Use the task query or sync endpoints to track completion.
All file inputs must be uploaded and persisted as file references before submission.
Request
Body
application/jsonAuthorizationstringrequiredBearer token or API key.
Location: HEADER
input_file_idstringrequiredInput video file_id.
Location: BODY
prompt_textstringrequiredtext prompt used to initialize object segmentation before removal.
Location: BODY
model_idstringoptionalVideo object removal by prompt model id. Default: remove-video-object-by-prompt-default.
Location: BODY
titlestringoptionalOptional task title.
Location: BODY
Response
Response
application/jsonMCP Tool
This endpoint is also available through the Medux-hosted remote MCP service.
Object Removal By Prompt
Remove an object from a video by prompt text.
Invocation Example
Remove an object from a video by prompt text.
On this page