# Seedream 4.5

> Upgraded Bytedance image model with stronger spatial understanding and world knowledge. Supports single/multi-reference image-to-image and sequential (multi-image) generation.

- **Provider**: replicate
- **Model ID**: bytedance/seedream-4.5
- **Category**: image_generation
- **Credits**: 90 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `image_input` (array, optional): Input image(s) for image-to-image generation. List of 1-14 images for single or multi-reference generation. (Default: `[]`)
- `width` (integer, optional): Custom image width (only used when size='custom'). Range: 1024-4096 pixels. (Default: `2048`; Range: min: 1024, max: 4096)
- `height` (integer, optional): Custom image height (only used when size='custom'). Range: 1024-4096 pixels. (Default: `2048`; Range: min: 1024, max: 4096)
- `sequential_image_generation` (string, optional): 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). (Default: `disabled`; Options: `disabled`, `auto`)
- `max_images` (integer, optional): Maximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15. (Default: `1`; Range: min: 1, max: 15)
- `prompt` (string, **required**): Text prompt for image generation. Maximum 4000 characters. BytePlus recommends keeping prompts under 600 English words for best results.
- `disable_safety_checker` (boolean, optional): Disable the safety checker for generated images. When enabled, input moderation is relaxed to only block illegal content (CSAM). Use responsibly. (Default: `False`)
- `aspect_ratio` (string, optional): Image aspect ratio. Only used when size is not 'custom'. Use 'match_input_image' to automatically match the input image's aspect ratio. (Default: `match_input_image`; Options: `match_input_image`, `1:1`, `4:3`, `3:4`, `4:5`, `5:4`, `16:9`, `9:16`, `3:2`, `2:3`, `21:9`, `9:21`)
- `size` (string, optional): Image resolution: 2K (2048px), 4K (4096px), or 'custom' for specific dimensions. Note: 1K resolution is not supported in Seedream 4.5. (Default: `2K`; Options: `2K`, `4K`, `custom`)

## Example Request

```json
{
  "model": "bytedance/seedream-4.5",
  "input": {
    "image_input": [],
    "aspect_ratio": "16:9",
    "size": "4K",
    "sequential_image_generation": "disabled",
    "width": 2048,
    "max_images": 1,
    "prompt": "A warm, nostalgic film-style interior of a cozy caf\u00e9, shot on 35mm-inspired digital photography with soft afternoon sunlight filtering through the front windows. Wooden shelves display neatly arranged ceramics, pastries, and coffee beans.",
    "height": 2048
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

bytedance, seedream, image-generation, text-to-image, image-editing, multi-reference, sequential-generation, popular

## Documentation

https://replicate.com/bytedance/seedream-4.5