# FLUX 2 Flex - Core.Today AI API

> Maximum-quality FLUX model supporting up to 10 reference images and advanced typography. The most capable model for complex, multi-reference creative projects.

- **Provider**: Black Forest Labs
- **Model ID**: black-forest-labs/flux-2-flex
- **Category**: Image Generation
- **Credits**: 280 per image
- **Speed**: Slow
- **Quality**: Ultra

## Features
- Up to 10 reference images supported
- Advanced typography rendering
- Ultra-quality output
- Complex multi-reference composition
- Best-in-class creative control

## Use Cases
- Complex brand identity projects
- Multi-reference style composition
- Advanced typography designs
- High-end creative campaigns
- Professional design asset creation

## 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 description of the image to generate

### Optional
- **input_images**: array (default: []) - Input images for style and content guidance (max 10)
- **aspect_ratio**: string (default: 1:1) - Aspect ratio for the generated image (use 'match_input_image' to match input)
  Options: match_input_image, custom, 1:1, 16:9, 3:2, 2:3, 4:5, 5:4, 9:16, 3:4, 4:3
- **resolution**: string (default: 1 MP) - Resolution in megapixels (up to 4 MP, 2 MP or below recommended)
  Options: match_input_image, 0.5 MP, 1 MP, 2 MP, 4 MP
- **width**: integer - Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16 (if it's not, it will be rounded to nearest multiple of 16).
- **height**: integer - Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16 (if it's not, it will be rounded to nearest multiple of 16).
- **safety_tolerance**: integer (default: 2) - Safety tolerance, 1 is most strict and 5 is most permissive
- **seed**: integer - Random seed for reproducibility
- **prompt_upsampling**: boolean (default: true) - Automatically modify the prompt for more creative generation
- **steps**: integer (default: 30) - Number of inference steps
- **guidance**: number (default: 4.5) - Guidance scale - controls how closely output follows the prompt
- **output_format**: string (default: webp) - Format of the output images
  Options: webp, jpg, png
- **output_quality**: integer (default: 80) - Quality of output images (0-100)

## Examples

### Multi-Reference Brand Design
Create a brand visual using multiple reference images
```json
{
  "model": "black-forest-labs/flux-2-flex",
  "input": {
    "prompt": "Premium brand campaign visual combining modern architecture with natural elements, luxury lifestyle aesthetic, professional advertising quality, 8k",
    "image_size": "landscape_16_9",
    "num_inference_steps": 50,
    "guidance_scale": 3.5
  }
}
```

## 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 multiple reference images for more precise style control
- Use higher inference steps (40-50) for maximum quality
- Ideal for projects requiring complex composition from multiple sources
- Leverage the advanced typography for text-heavy designs