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

> ## Agent Instructions
> Send API requests to https://api.ttapi.io with the TT-API-KEY header. Midjourney account hosting uses https://hold.ttapi.io. Claude Code uses https://cc.ttapi.io.
> Most generation endpoints are asynchronous. The submit response returns a job id. Poll that product's fetch endpoint, or pass a webhook on the submit request. A fetch call does not start a new generation.
> 1 USD = 100 quota. Check the pricing page for that product before estimating cost.
> This file lists the English docs. Follow every /_llms/ link recursively for the API reference, Chinese, and Russian. Open a page's .md URL for the endpoint schema.

# Seedream Image Generation API Documentation

> View Seedream Image Generation API documentation, supporting text-to-image, image-to-image, multi-image fusion, layer decomposition, interactive editing, with async and sync endpoints.

# Seedream Image Generation API

This is the **Seedream Image Generation API** overview page. You can quickly understand Seedream's image generation capabilities and navigate to specific endpoint documentation.

## What Seedream Image Generation API Can Do

Seedream provides multiple image generation capabilities for different scenarios:

* **Text-to-Image**: Generate high-quality images directly from text prompts
* **Image-to-Image**: Style transfer or content editing based on reference image. Supports transparent background
* **Multi-Image Fusion**: Fuse and generate new image based on multiple reference images (2-10)
* **Layer Decomposition**: Decompose single image into base image and multiple layers (5.0 series)
* **Interactive Edit**: Precisely edit image using coordinates and other methods (5.0 series)

## Supported Models

| Model | Description |
| :- | :- |
| `doubao-seedream-5-0-pro-260628` | Pro, supports layer decomposition, interactive edit, text-to-image, image-to-image, multi-image fusion |
| `doubao-seedream-5-0-flash-260915` | Flash, supports layer decomposition, interactive edit, text-to-image, image-to-image, multi-image fusion |

## Async Endpoints (Recommended)

Submit a task and get `id`, then fetch results via query endpoint. Suitable for production integration, supports webhook callback.

| Scenario | Endpoint | Description |
| :- | :- | :- |
| Text-to-Image | [Text-to-Image API](/api/en/seedream/text-to-image.md) | Generate images only through text prompt |
| Image-to-Image | [Image-to-Image API](/api/en/seedream/image-to-image.md) | Generate image based on single reference image |
| Multi-Image Fusion | [Multi-Image Fusion API](/api/en/seedream/multi-image.md) | Fuse and generate based on multiple reference images |
| Layer Decomposition | [Layer Decomposition API](/api/en/seedream/layer-decomposition.md) | Decompose image into base image and layers |
| Interactive Edit | [Interactive Edit API](/api/en/seedream/interactive-edit.md) | Precisely edit image using coordinates |
| Fetch Result | [Fetch API](/api/en/seedream/fetch.md) | Query async task status and results |

## Sync Endpoint

Returns results directly after request, no additional query needed. See [Text-to-Image (Sync) API](/api/en/seedream/text-to-image-sync.md).

## Recommended Integration Flow

### Async Endpoints (Recommended)

1. Choose the appropriate async endpoint based on your scenario
2. Call the endpoint to submit a task, get `id`
3. Use [Fetch API](/api/en/seedream/fetch.md) to poll task status
4. When `status` is `SUCCESS`, get the image URL from the response

### Async Task Status

* `PENDING_QUEUE`: Task pending
* `ON_QUEUE`: Task in queue
* `SUCCESS`: Task completed
* `FAILED`: Task failed

## Why Use Seedream Image Generation API

* **High-quality output**: Supports multiple resolution tiers (1K / 1.5K / 2K), fine and clear image quality
* **Multiple generation modes**: Supports text-to-image, image-to-image, multi-image fusion, layer decomposition, interactive editing and more
* **Flexible calling methods**: Provides async (recommended) and sync endpoints, meets different business needs
* **Flexible control**: Supports transparent background, custom size, multiple output formats and other parameters
* **Unified gateway**: Uses TTAPI unified API gateway and authentication


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.