# Grok Imagine Image - Core.Today AI API

> Generate images using xAI's Grok Imagine model. Sibling to Grok Imagine Video, sharing the same underlying Grok Imagine architecture for fast text-to-image generation.

- **Provider**: xAI
- **Model ID**: xai/grok-imagine-image
- **Category**: Image Generation
- **Credits**: 47 per image
- **Speed**: Fast
- **Quality**: Standard

## Features
- Text-to-image generation built on the Grok Imagine architecture
- Image editing mode — pass an existing image plus a prompt to edit it
- 14 aspect ratio presets plus an auto option
- Shares its underlying architecture with Grok Imagine Video

## Use Cases
- Rapidly iterating on image concepts from text prompts
- Editing an existing image by passing it in as input alongside a prompt
- Generating images across varied aspect ratios for social posts, wide banners, and mobile screens

## 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 for image generation or editing

### Optional
- **image**: string - Input image for editing. When provided, the model edits this image based on the prompt. Supports jpg, jpeg, png, webp.
- **aspect_ratio**: string (default: 1:1) - Aspect ratio of the generated image. Ignored when editing an image.
  Options: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, 9:19.5, 20:9, 9:20, auto

## Examples

### Text-to-image generation
Generates a new image from a text prompt at a 16:9 aspect ratio.
```json
{
  "model": "xai/grok-imagine-image",
  "input": {
    "prompt": "A futuristic city skyline at sunset, flying vehicles, neon reflections on glass towers",
    "aspect_ratio": "16:9"
  }
}
```

### Edit an existing image
Edits an uploaded image based on the prompt; aspect_ratio is ignored.
```json
{
  "model": "xai/grok-imagine-image",
  "input": {
    "prompt": "Change the background to a snowy mountain landscape",
    "image": "https://example.com/input-photo.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
- Pass an image to switch into edit mode — the model edits that image based on your prompt instead of generating from scratch
- aspect_ratio is ignored when editing an image since the output follows the input image's dimensions
- Use aspect_ratio=auto to let the model choose a sensible ratio for the prompt

## Documentation
https://replicate.com/xai/grok-imagine-image