Boogu Image Edit API Documentation

Boogu Image Edit API Documentation

Playground

Boogu Image Edit transforms input images using English or Chinese edit instructions, supporting prompt-based image editing for visual changes, style adjustments, and image refinements. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Boogu Image Edit transforms an input image using a text instruction. Upload an image, describe the edit you want, and generate an edited image through the standard WaveSpeed prediction response. English and Chinese edit prompts are both supported.

Why Choose This?

• Instruction-based image editing
  Upload an image and describe the transformation you want in natural language.

• Bilingual edit prompts
  Use English or Chinese instructions to guide the image edit.

• Original-ratio default
  When no explicit size is provided, the edited image follows the input image aspect ratio.

• Simple public interface
  The public form focuses on prompt, input image, and output format.

• Standard image output
  Edited images are returned as URLs in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Upload your image — Provide the input image you want to edit.
2. Write your edit prompt — Describe what should change and what should stay the same.
3. Choose output format — Use jpeg for general-purpose output or png when PNG output is needed.
4. Submit — Generate the edited image and retrieve the output URL.

Pricing

Best Use Cases

• Photo transformation — Change backgrounds, style, mood, color, or visual details in an input image.
• Product and marketing edits — Refine uploaded or generated assets for campaigns, product visuals, and content production.
• Creative iteration — Try different edit prompts on the same source image.
• Bilingual workflows — Use English or Chinese instructions in the same API workflow.
• Format-specific outputs — Generate edited images in jpeg or png depending on the downstream use case.

Pro Tips

• Use clear edit instructions that describe both what should change and what should remain unchanged.
• Upload a sharp image with the main subject clearly visible.
• Keep the prompt focused on one main edit when possible.
• Use png when you need a higher-quality image for further editing.
• Use jpeg for smaller, general-purpose edited images.
• Ensure the input image URL is publicly accessible.

## 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 |