Seedream 4.5

Seedream 4.5 is ByteDance’s image generation model for text prompts and reference-image workflows. Use model ID doubao-seedream-4-5-251128.

For specific content requests, select the Special-Ns resource group.

Key capabilities

Text to image — Generate images from text prompts
Image to image — Generate images from one or more references and a text prompt
Sequential generation — Generate multiple related images in one request
Output control — Configure size, seed, watermark, and logo settings

Text to image
Image to image

Quick example

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-5-251128",
    "prompt": "A serene mountain landscape at sunrise with misty valleys",
    "size": "1024x1024",
    "watermark": false
  }'

import requests

response = requests.post(
    "https://www.anyfast.ai/v1/images/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "doubao-seedream-4-5-251128",
        "prompt": "A serene mountain landscape at sunrise with misty valleys",
        "size": "1024x1024",
        "watermark": False,
    },
)
print(response.json())

Parameter	Type	Required	Description
`model`	string	Yes	Must be `doubao-seedream-4-5-251128`
`prompt`	string	Yes	Image generation prompt
`size`	string	No	Output size such as `1024x1024` or `2K`
`watermark`	boolean	No	Whether to add a watermark; default `false`
`seed`	integer	No	Random seed
`logo_info`	object	No	Logo settings: `add_logo`, `position`, `language`, and `opacity`

Quick example

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-5-251128",
    "prompt": "A girl and a cow doll riding a roller coaster in the morning, at noon, and at night",
    "image": ["https://example.com/ref1.png", "https://example.com/ref2.png"],
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": {"max_images": 3},
    "size": "2K",
    "watermark": false
  }'

import requests

response = requests.post(
    "https://www.anyfast.ai/v1/images/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "doubao-seedream-4-5-251128",
        "prompt": "A girl and a cow doll riding a roller coaster in the morning, at noon, and at night",
        "image": ["https://example.com/ref1.png", "https://example.com/ref2.png"],
        "sequential_image_generation": "auto",
        "sequential_image_generation_options": {"max_images": 3},
        "size": "2K",
        "watermark": False,
    },
)
print(response.json())

Parameter	Type	Required	Description
`model`	string	Yes	Must be `doubao-seedream-4-5-251128`
`prompt`	string	Yes	Image generation or editing prompt
`image`	string[]	Yes	Reference image URLs
`sequential_image_generation`	string	No	Set to `auto` to generate an image batch
`sequential_image_generation_options.max_images`	integer	No	Maximum number of generated images
`size`	string	No	Output size such as `1024x1024` or `2K`
`watermark`	boolean	No	Whether to add a watermark; default `false`
`seed`	integer	No	Random seed
`logo_info`	object	No	Logo settings: `add_logo`, `position`, `language`, and `opacity`

API Reference

View both Seedream 4.5 workflows.

Getting started

Model Introduction

Resources

Key capabilities

Quick example

Quick example

API Reference

​Key capabilities

​Quick example

​Quick example

API Reference

Key capabilities

Quick example

Quick example