Object Removal

Object Removal

Playground

WaveSpeedAI Object Removal removes mask-selected objects from input images and returns clean edited images with unwanted elements removed, making it useful for photo cleanup, product images, e-commerce assets, creative editing, and image restoration workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Object Removal removes mask-selected objects from an input image and returns a clean edited image. Upload an image and a matching mask to specify exactly which area should be removed.

Why Choose This?

• Mask-guided object removal
  Use a mask to precisely define the area that should be removed.

• Controlled image editing
  Preserve the unmasked parts of the image while removing the selected object.

• Simple two-input workflow
  Provide the source image and a matching mask to generate the edited result.

• Standard image output
  The edited image is returned as a URL in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Upload image — Provide the image you want to edit.
2. Upload mask — Provide a mask with the same dimensions as the input image. Mark the removal area in white.
3. Submit — Generate the edited image.
4. Review output — Retrieve the result from the returned image URL.

Pricing

Best Use Cases

• Product cleanup — Remove unwanted objects, props, or distractions from product images.
• Creative editing — Create a cleaner base image for further editing or compositing.
• Marketing assets — Remove visual distractions from campaign images, banners, and promotional visuals.
• Photo cleanup — Remove selected objects from everyday photos while preserving the surrounding context.
• Design workflows — Prepare cleaner source images for layouts, mockups, and visual production.

Pro Tips

• Make sure image and mask have identical dimensions.
• Use white pixels in the mask to mark the exact areas to remove.
• Keep the mask focused on the object or region that should be removed.
• Avoid masking too much surrounding context unless it also needs to be removed.
• Use a clear source image for more stable results.
• Ensure the input image and mask URLs are publicly accessible.

Notes

• After generating the mask, save the mask image locally first, then upload it as the mask input.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |