Seedream API · Ace Data Cloud

Seedream API
ByteDance AI Image Generation

Access ByteDance Seedream image generation models through a simple API call. Supports text-to-image and image editing—up to 4K resolution, multiple model options, and pay-as-you-go pricing.

🎨 6 Models 📐 Up to 4K 💰 Starting at $0.032 ✏️ Text-to-Image + Image Editing
🎨
6
Model Versions
📐
4K
Maximum Resolution
💰
$0.032
Starting Price
✏️
Editing
Image Editing Supported

Why Choose Seedream?

Seedream is an AI image generation model launched by ByteDance, renowned for its exceptional image quality, precise text understanding, and rich aesthetic expression. The Seedream 5.0 series ranks among the industry's best in multiple image generation benchmark tests, particularly excelling at understanding Chinese prompts.

Ace Data Cloud providesa complete Seedream API proxy service—you do not need to apply for a ByteDance API account or overcome regional restrictions. Generate high-quality images through a simple REST API, with support for both text generation and image editing.

Seedream API Core Features

From text descriptions to exquisite images—Seedream provides comprehensive image generation and editing capabilities

✍️

Text-to-Image (T2I)

Enter a text description to generate high-quality images. Supports Chinese and English prompts, accurately understands complex semantics, and produces detailed, realistic visuals.

✏️

Image Editing (I2I)

Upload an original image and describe your editing intent. The SeedEdit model can intelligently modify image content while maintaining a consistent overall style.

📐

Multiple Resolution Support

Supports 1K, 2K, 4K, and various adaptive resolutions. Flexibly meets different needs, from quick previews to print-quality output.

🧩

Sequential Image Generation

Enable the sequential_image_generation option to generate a series of images with a consistent style, ideal for comics and storyboards.

🔄

Streaming Output

Supports stream mode, returning generated results progressively. Significantly improves the user waiting experience in high-resolution scenarios.

💧

Watermark Control

Use the watermark parameter to flexibly control whether an AI-generated watermark is added, meeting compliance requirements for different use cases.

Python
import requests
response = requests.post(
    "https://api.acedata.cloud/seedream/images",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro-260628",
        "prompt": "a white siamese cat"
    }
)
data = response.json()
print(data)
# {
#   "success": true,
#   "task_id": "c0aae74d-4442-4563-b620-3da86bae5434",
#   "trace_id": "581c4721-83e2-41a3-b7d8-b64378604bed",
#   "data": [
#     {
#       "prompt": "a white siamese cat",
#       "size": "1024x1024",
#       "image_url": "https://platform.cdn.acedata.cloud/seedream/819386b9-fab6-4bf3-acc6-df29f53c7248.jpg"
#     }
#   ]
# }

Generate AI Images with One Line of Code

Send a POST request with a text prompt to instantly get high-quality generated images.

1

Prepare Request Parameters

Select a model and provide a text prompt prompt, with optional resolution and seed parameters

2

Send a Generation Request

POST to /seedream/images to directly return the image URL of the generated result

3

Or Use Callback Notifications

Set callback_url to actively POST a notification to your server after generation is complete

What can Seedream be used for?

From creative design to commercial applications—Seedream is being used in these scenarios

📱

Social Media Content

Quickly generate eye-catching social media images, cover images, and post visuals

🛍️

E-commerce Assets

Generate product showcase images, lifestyle images, and advertising creative assets in batches to reduce design costs

🎮

Game & Concept Design

Generate game characters and scene concept art—quickly validate creative ideas and visual style directions

📰

Content Images

Automatically generate matching high-quality images for articles, blogs, news, and other content

Get Started in 3 Steps

From registration to generating your first image, it takes just a few minutes

01

Register and Get an API Key

Create a free account on Ace Data Cloud and generate your Bearer Token from the console.

02

Send an Image Generation Request

POST to /seedream/images with a text prompt and model name.

03

Get the Generated Result

Get the generated image URL directly from the response, then download and use it.

Compared with Direct ByteDance API Integration

Ace Data Cloud frees you from concerns about registration, authentication, and regional restrictions

Comparison Item Ace Data Cloud Direct ByteDance Connection
Registration Requirements Free registration, use immediately ByteDance account application required
Regional Restrictions Available worldwide ✗ Restricted in some regions
API Style Unified REST API Native ByteDance SDK
Billing Method Pay as you go, use upon top-up Contract required for activation
Technical Support 24/7 online support Ticket-based

Choose the Right Seedream Model

From text-to-image to image editing—multiple models cover different creative needs

Recommended

Seedream 5.0 Pro

Latest Flagship

Seedream's latest flagship single-image model. It leads in image quality and text understanding, supporting high-precision single images, interactive editing, transparent backgrounds, and layer separation (does not support image groups / streaming / web access), ideal for professional design workflows.

  • ✓ Top-tier single-image quality
  • ✓ 1K / 1.5K / 2K resolution
  • ✓ Text-to-image + multi-image-to-image + layer separation
  • ✓ Selectable output formats
  • ✓ Charged per image based on actual output size

Seedream 5.0 Lite

5.0 Image Groups

The balanced version of the 5.0 series. Supports image group generation, streaming output, and web search, balancing quality and cost for batch and continuous creation.

  • ✓ High-quality images
  • ✓ 2K / 3K / 4K
  • ✓ Image groups + streaming + web access
  • ✓ Selectable output formats
  • ✓ Charged by the number of successfully generated images

Seedream 4.5

Previous-Generation Flagship

The previous-generation flagship model. Delivers outstanding image quality, text understanding, and aesthetic expression. Supports continuous image generation and streaming output.

  • ✓ Outstanding image quality
  • ✓ 2K / 4K
  • ✓ Continuous image generation
  • ✓ Streaming output
  • ✓ $0.040 / image

Seedream 4.0

Stable Version

A mature and stable core model. Achieves the best balance between image quality and cost-effectiveness, suitable for most production scenarios.

  • ✓ High-quality images
  • ✓ 1K / 2K / 4K
  • ✓ Continuous image generation
  • ✓ Streaming output
  • ✓ $0.032 / image
doubao-seedream-5-0-pro-260628 doubao-seedream-5-0-lite-260128 doubao-seedream-4-5-251128 doubao-seedream-4-0-250828

Seedream API Pricing

Billing is based on successful outputs. Prices depend on the model, scenario, and actual output size. The task query API is completely free.

Model Type Unit Price (per image)
Seedream 5.0 Pro Standard single image / layer splitting Tiered by size
Seedream 5.0 Lite Text-to-image / image groups Per successful image
Seedream 4.5 Text-to-image $0.040
Seedream 4.0 Text-to-image $0.032

The task query API /seedream/tasks is completely free

View full pricing →

Frequently Asked Questions

Everything you need to know about using the Seedream API

What is Seedream? ▾

Seedream is a family of AI image generation models launched by ByteDance, featuring two core capabilities: text-to-image (T2I) and image editing (I2I). The models are known for outstanding text understanding, visual aesthetics, and detail rendering, supporting output at up to 4K resolution.

Does it support image editing? ▾

Yes! Seedream 5.0 Pro, 5.0 Lite, 4.5, and 4.0 can all accept the URL or Base64 encoding of the original image in the image parameter, then use prompt to describe the editing intent, enabling local modifications or overall style transformations.

How long does image generation take? ▾

In most cases, Seedream can complete image generation within 5-15 seconds. The exact time depends on the model version and output resolution. 4K resolution images take longer than 1K resolution images. You can also use callback notifications (callback_url) to avoid blocking while waiting.

Which resolutions are supported? ▾

For standard generation, Seedream 5.0 Pro supports 1K/1.5K/2K, and layer splitting also supports auto; 5.0 Lite supports 2K/3K/4K; 4.5 supports 2K/4K; and 4.0 supports 1K/2K/4K. Standard generation also supports explicit dimensions that fall within each model's pixel and aspect ratio ranges.

How do I choose a model? ▾

Choose Seedream 5.0 Pro for the best single-image quality, precise editing, transparent backgrounds, or layer splitting; choose Seedream 5.0 Lite when you need image sets, streaming, or web search. Refer to the real-time pricing page for specific Credits unit prices.

What is sequential image generation? ▾

Set sequential_image_generation: "auto", and the Seedream 5.0 Lite, 4.5, and 4.0 models will generate a series of stylistically consistent, related images based on your input (Seedream 5.0 Pro does not support image groups). It is suitable for scenarios requiring visual consistency, such as comic panels, storyboards, and product series showcases.

How can I split an image into editable layers? ▾

Use Seedream 5.0 Pro, provide an image, and set layer_decomposition: true. The API will return the background image and up to 16 transparent PNG layers, along with z_index, names, descriptions, and bounding boxes; they can be recombined on a canvas according to their hierarchy and coordinates.

Can the watermark be turned off? ▾

Yes. Set watermark: false in the request to disable the AI-generated watermark. The watermark is enabled by default. Please use AI-generated content labels appropriately in accordance with local regulations.

Start Using the Seedream API Today

Generate high-quality AI images with simple API calls. Pay as you go—no subscription fees, no commitment.