# Seedream 4.0 - Core.Today AI API

> ByteDance's latest image generation model with exceptional prompt understanding and creative capabilities.

- **Provider**: ByteDance
- **Model ID**: bytedance/seedream-4
- **Category**: Image Generation
- **Credits**: 70 per image
- **Speed**: Medium
- **Quality**: High

## Features
- Advanced language understanding
- Creative composition
- Excellent text rendering
- Multiple style support
- High resolution output

## Use Cases
- Marketing creatives
- Social media content
- Text-integrated designs
- Brand materials
- Creative campaigns

## 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

### Optional
- **image_input**: array (default: []) - Input image(s) for image-to-image generation. List of 1-10 images for single or multi-reference generation.
- **size**: string (default: 2K) - Output dimensions
  Options: 1K, 2K, 4K, custom
- **aspect_ratio**: string (default: match_input_image) - Image aspect ratio. Only used when size is not 'custom'. Use 'match_input_image' to automatically match the input image's aspect ratio.
  Options: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9
- **width**: integer (default: 2048) - Custom image width (only used when size='custom'). Range: 1024-4096 pixels.
- **height**: integer (default: 2048) - Custom image height (only used when size='custom'). Range: 1024-4096 pixels.
- **sequential_image_generation**: string (default: disabled) - Group image generation mode. 'disabled' generates a single image. 'auto' lets the model decide whether to generate multiple related images (e.g., story scenes, character variations).
  Options: disabled, auto
- **max_images**: integer (default: 1) - Maximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15.
- **enhance_prompt**: boolean (default: true) - Enable prompt enhancement for higher quality results, this will take longer to generate.

## Examples

### Social Media Post
Create engaging social content
```json
{
  "model": "bytedance/seedream-4",
  "input": {
    "prompt": "Modern coffee shop interior with text 'OPEN NOW' in neon sign style, cozy atmosphere, Instagram aesthetic",
    "size": "1024x1024"
  }
}
```

## 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
- Great for designs that need text elements
- Excels at understanding complex compositions
- Try different style presets for variety