# Muse Image 1.0 - Core.Today AI API

> Meta's Muse Image model over the Meta developer API - text-to-image with built-in web and image search grounding, up to 10 images per request, webp/png/jpeg output. To edit an existing image use meta/muse-image-1.0/edit.

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

## Features
- Built-in web and image search grounding at no extra charge
- Up to 10 images per request (billed per image)
- Aspect ratio control via WxH size presets
- webp (default), png or jpeg output
- Synchronous API - the result is ready when the job completes

## Use Cases
- Product and lifestyle imagery grounded in real-world references
- Marketing visuals across landscape, portrait and square ratios
- Batch concept exploration with the n parameter

## 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 image to generate.

### Optional
- **n**: integer (default: 1) - Number of images to generate (1-10). Billed per image.
- **size**: string - Aspect ratio as WxH. Sets the ratio only - the image is rendered at the model's native resolution. Omit to let the model choose.
  Options: 1024x1024, 1792x1024, 1024x1792, 1536x1024, 1024x1536, 1280x720, 720x1280
- **output_format**: string (default: webp) - Output image format.
  Options: webp, png, jpeg

## Examples

### Text-to-image generation
Generates a wide cinematic image from a text prompt.
```json
{
  "model": "meta/muse-image-1.0",
  "input": {
    "prompt": "A cozy Seoul street cafe at dusk, warm window light, rain-slick pavement, cinematic photo",
    "size": "1792x1024"
  }
}
```

### Batch variations
Generate 4 png variations of the same prompt in one request.
```json
{
  "model": "meta/muse-image-1.0",
  "input": {
    "prompt": "A minimalist logo concept for a coffee brand, flat design",
    "n": 4,
    "size": "1024x1024",
    "output_format": "png"
  }
}
```

## 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
- To edit an existing image, use meta/muse-image-1.0/edit - this model has no image input
- The size preset fixes the aspect ratio, not the pixel dimensions
- Prompts that reference real products or places benefit from the built-in search grounding
- The default output is webp; choose png when you need lossless output

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