> ## Documentation Index
> Fetch the complete documentation index at: https://docs.eden.art/llms.txt
> Use this file to discover all available pages before exploring further.

# Seedream45

> ByteDance's advanced text-to-image model generation

## Overview

ByteDance's advanced text-to-image model generation

* **Output Type**: image
* **Estimated Cost**: 4 \* max\_images credits
* **Handler**: replicate

## Parameters

### Required Parameters

<ParamField body="prompt" type="string" required>
  Text prompt for image generation

  * Label: Prompt
</ParamField>

### Optional Parameters

<ParamField body="size" type="string" default="2K">
  Image resolution preset

  <Tip>
    1K: 1024px, 2K: 2048px, 4K: 4096px, custom: use width/height parameters
  </Tip>

  * Label: Size
  * Options: `1K`, `2K`, `4K`, `custom`
</ParamField>

<ParamField body="width" type="integer" default={2048}>
  Custom image width in pixels (only used when size is 'custom')

  * Label: Width
  * Minimum: 1024
  * Maximum: 4096
</ParamField>

<ParamField body="height" type="integer" default={2048}>
  Custom image height in pixels (only used when size is 'custom')

  * Label: Height
  * Minimum: 1024
  * Maximum: 4096
</ParamField>

<ParamField body="aspect_ratio" type="string" default="match_input_image">
  Aspect ratio for the generated image

  <Tip>
    Set aspect ratio manually (not "match\_input\_image") if you do not have any image inputs
  </Tip>

  * Label: Aspect ratio
  * Options: `match_input_image`, `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`, `21:9`
</ParamField>

<ParamField body="image_input" type="array<image>">
  Optional input image(s) to use as references

  <Tip>
    Optional input images for image-to-image transformation or object/style reference
  </Tip>

  * Label: Input images
</ParamField>

<ParamField body="max_images" type="integer" default={1}>
  Maximum number of images to generate when sequential generation is enabled

  * Label: Number of images
  * Minimum: 1
  * Maximum: 15
</ParamField>

<ParamField body="sequential_image_generation" type="string" default="disabled">
  Group image generation mode

  <Tip>
    When enabled, the model will generate a batch of up to max\_images images with consistency
  </Tip>

  * Label: Sequential generation
  * Options: `disabled`, `auto`
</ParamField>