# FLUX Kontext Pro - Core.Today AI API

> State-of-the-art text-based image editing model that transforms images through natural language. Excellent for style transfer, object modification, text replacement, background changes, and character consistency.

- **Provider**: Black Forest Labs
- **Model ID**: black-forest-labs/flux-kontext-pro
- **Category**: Image Generation
- **Credits**: 93 per image
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Text-driven image editing with high fidelity
- Style transfer and transformation
- Object and text replacement
- Background editing
- Character consistency across edits

## Use Cases
- Photo retouching and stylization
- Marketing creative variations
- Product image background swaps
- Character-consistent illustrations

## 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 - Editing instruction or generation prompt

### Optional
- **input_image**: string - URL of the source image to edit (jpeg, png, gif, or webp)
- **aspect_ratio**: string (default: match_input_image) - Output aspect ratio. Use match_input_image to preserve the input ratio
  Options: match_input_image, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
- **output_format**: string (default: png) - Output image format
  Options: jpg, png
- **safety_tolerance**: integer (default: 2) - Safety tolerance: 0 strictest, 6 most permissive. Max 2 when input_image is provided
- **prompt_upsampling**: boolean (default: false) - Auto-improve prompt before generation
- **seed**: integer - Random seed for reproducibility

## Examples

### Style Transfer
Convert a photo into a 90s cartoon style
```json
{
  "model": "black-forest-labs/flux-kontext-pro",
  "input": {
    "prompt": "Make this a 90s cartoon",
    "input_image": "https://replicate.delivery/pbxt/N55l5TWGh8mSlNzW8usReoaNhGbFwvLeZR3TX1NL4pd2Wtfv/replicate-prediction-f2d25rg6gnrma0cq257vdw2n4c.png",
    "aspect_ratio": "match_input_image",
    "output_format": "jpg",
    "safety_tolerance": 2
  }
}
```

## 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
- Provide input_image to use editing mode — without one it generates from scratch
- Use match_input_image when you want to preserve the original aspect ratio
- Lower safety_tolerance values reject more outputs — start at 2
- Use a fixed seed when iterating on a single edit