Skip to main content
POST
/
v3
/
async
/
image-eraser
Image Eraser
curl --request POST \
  --url https://api.novita.ai/v3/async/image-eraser \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "mask": "<string>",
  "image": "<string>",
  "prompt": "<string>",
  "output_format": "<string>"
}
'
{
  "task_id": "<string>"
}
AI-powered image erasing service. Supports object removal from images via mask and text prompts. Offers high-quality image processing: out-of-the-box REST inference API, top performance, no cold start, affordable pricing.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
mask
string
Mask image indicating the area to be erased. Areas to erase should be white; areas to keep should be black.
​
image
string
required
The original image to be processed.
​
prompt
string
Text prompt specifying the object or region to remove from the image, e.g., β€˜dog’ or β€˜hat’.
​
output_format
string
default:"jpeg"
Output image format.Optional values: jpeg, png, webp

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.
Last modified on December 10, 2025