Seedream 5.0 Lite

Seedream 5.0 Lite is ByteDance's image generation model for text-to-image and reference-guided generation. Upload up to 5 reference images and receive 2K or 4K output in PNG or JPG format.

Base URL

https://api.icreat.ai

Authentication

All API requests must be authenticated with an API Key. You can obtain an API Key from the console.

export ICREAT_API_KEY="your-api-key-here"

HTTP Request Headers

import os

API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + API_KEY,
}

Protect your API Key

Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

Image and video generation uses a three-step async flow: submit a task to obtain a task_id, poll until the task completes, then fetch the result when status is SUCCEEDED. The examples below reuse the same task_id across all three steps.

1. Submit Task

Send the generation request to the submit endpoint. On success, the response returns a task_id—save it for polling and fetching results.

POST/v1/task/submit/bytedance/seedream-5.0

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/submit/bytedance/seedream-5.0" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "image": [
    "https://upload.icreat.ai/upload/xxx.png"
  ],
  "prompt": "An eagle flying",
  "size": "2K",
  "watermark": false,
  "outputFormat": "png"
}'

2. Poll Status

Query progress with the task_id from submit. The response contains only status (SUBMITTED | SUCCEEDED | FAILED). Call get-result when SUCCEEDED; FAILED means the task did not complete.

POST/v1/task/query-status

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/query-status" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"task_id": "task-xxx"}'

3. Get Result

After success, fetch the output with the same task_id. The response is a top-level array; each item has type, url, and download_url—use url for preview and download_url to download.

POST/v1/task/get-result

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/get-result" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"task_id": "task-xxx"}'

Input Schema

Submit Task — Input Schema

The following parameters are accepted in the submit request body.

Total: 5 Required: 3 Optional: 2

promptstringrequired

The image generation prompt, with a maximum length of 10,000 characters.

sizestringrequired

Output image resolution.

Default"2K"

2K4K

outputFormatstringrequired

Output image format.

Default"png"

pngjpg

imagearray[string]

A list of reference image URLs. Up to 5 images are supported. Common image formats are accepted, with a maximum size of 10 MB per image. Omit for text-to-image.

watermarkboolean

Whether to add a watermark to the generated image.

Default"true"

Poll Status — Input Schema

Total: 1 Required: 1 Optional: 0

task_idstringrequired

The task ID returned from the submit endpoint.

Get Result — Input Schema

Total: 1 Required: 1 Optional: 0

task_idstringrequired

The task ID returned from the submit endpoint.

Output Schema

Submit Task — Output Schema

Total: 1

task_idstring

Unique identifier for the async task. Use this ID to poll status and retrieve the result.

Poll Status — Output Schema

Total: 1

statusstring

Current task status. When the status is SUCCEEDED, you can retrieve the result.

SUBMITTEDSUCCEEDEDFAILED

Get Result — Output Schema

Response body is an array of resource objects (array[object]).

Total: 3

typestring

Resource type. Use Image for image models.

urlstring

Preview or access URL of the generated image.

download_urlstring

Download URL with attachment disposition.

LLM Prompt

The Markdown below is an LLM-friendly prompt you can paste into AI assistants (e.g. Cursor, ChatGPT) to help them understand this model's API, call flow, and key parameters. Use Copy for AI or copy from the code block below.

# bytedance/seedream-5.0

> Seedream 5.0 Lite is ByteDance's image generation model for text-to-image and reference-guided generation.

## Overview

Use the iCreat three-step async task API: submit a generation request, poll status, then fetch the image URL on success.

## API Info

- **Base URL**：`https://api.icreat.ai`
- **Submit endpoint (POST)**：`/v1/task/submit/bytedance/seedream-5.0`
- **Poll endpoint (POST)**：`/v1/task/query-status`
- **Get result endpoint (POST)**：`/v1/task/get-result`
- **Model ID**：`bytedance/seedream-5.0`
- **Auth**：`Authorization: Bearer ${ICREAT_API_KEY}`

## Call Flow

1. **Submit**: POST submit path with body per Input Notes; response `{ "task_id": "..." }`
2. **Poll**: POST `/v1/task/query-status` with `{ "task_id": "..." }`; response contains **only** `{ "status": "SUBMITTED|SUCCEEDED|FAILED" }`
3. **Get result**: when `status` is `SUCCEEDED`, POST `/v1/task/get-result`; top-level array; read `url` or `download_url` when `type` is `Image`

### Input Notes

- Request body uses top-level flat fields
- Required: `prompt`, `size`, `outputFormat`
- Optional: `image`, `watermark`
- `prompt` (required): The image generation prompt, with a maximum length of 10,000 characters.
- `size` (required): Output image resolution. (default `2K`)
- `outputFormat` (required): Output image format. (default `png`)
- `image` (optional): A list of reference image URLs. Up to 5 images are supported. Common image formats are accepted, with a maximum size of 10 MB per image. Omit for text-to-image.
- `watermark` (optional): Whether to add a watermark to the generated image. (default `true`)

### Output Notes

- Poll: read `status` only
- Result: top-level `[{ "type": "Image", "url": "...", "download_url": "..." }]`

## Notes

- Use the same `task_id` across all three steps; do not skip polling
- `FAILED` is terminal — check request parameters or reference media