# Muse Image 1.0 Edit - Core.Today AI API

> Edit an existing image with Meta's Muse Image model - pass a source image URL and a prompt describing the change. Up to 10 variants per request, webp/png/jpeg output.

- **Provider**: Meta
- **Model ID**: meta/muse-image-1.0/edit
- **Category**: Image Generation
- **Credits**: 24 per image
- **Speed**: Medium
- **Quality**: High

## Features
- Prompt-driven edits of a source image (png/jpeg/webp)
- Up to 10 edited variants per request (billed per image)
- Optional aspect ratio change via WxH size presets
- Same per-image price as generation - no separate input fee

## Use Cases
- Product photo retouching - swap backgrounds, lighting or props
- Adding or removing objects from an existing shot
- Restyling a photo while keeping its composition

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt describing the edit to apply.
- **image**: string - Source image URL to edit (png/jpeg/webp).

### Optional
- **n**: integer (default: 1) - Number of edited variants to generate (1-10). Billed per image.
- **size**: string - Output aspect ratio as WxH (ratio only, native resolution). Omit to keep the source image's ratio.
  Options: 1024x1024, 1792x1024, 1024x1792, 1536x1024, 1024x1536, 1280x720, 720x1280
- **output_format**: string (default: webp) - Output image format.
  Options: webp, png, jpeg

## Examples

### Edit an existing image
Changes the lighting and adds an object to a source photo.
```json
{
  "model": "meta/muse-image-1.0/edit",
  "input": {
    "prompt": "Make it golden hour and add a small red bicycle leaning on the wall",
    "image": "https://files.core.today/aiapi/6f8aed9a74674cd1/public/SlzMWjEAXHIdNTyTRKe6jV2keHjUXZ2k/0.jpg"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Describe only the change you want; the model keeps everything else from the source image
- Use n to get several candidate edits in one request
- For a brand-new image from text only, use meta/muse-image-1.0

## Documentation
https://dev.meta.ai/docs/image-generation