Seedream 5.0 Pro Image Generation API
Capabilities
Seedream 5.0 Pro supports text-to-image and image-to-image generation using the OpenAI Images API-compatible format.
The model code is doubao-seedream-5-0-pro.
Endpoints and Authentication
Base URL: https://api.88api.ai
Authorization: Bearer $API_KEY
Content-Type: application/json| Use case | Method | Endpoint |
|---|---|---|
| Text-to-image | POST | /v1/images/generations |
| Editing with public reference images | POST | /v1/images/generations |
| Editing a local image | POST | /v1/images/edits |
Text-to-Image
curl https://api.88api.ai/v1/images/generations \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-5-0-pro",
"prompt": "A little Shiba Inu wearing a red Tang suit, Chinese guochao illustration style, festive and cozy",
"n": 1,
"size": "1K",
"quality": "1K",
"response_format": "url"
}'Image-to-Image
Public Reference Images
Use image for a single reference image and images for multiple reference images. Reference images must be public HTTP(S) URLs,
with a combined maximum of 14 images.
curl https://api.88api.ai/v1/images/generations \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-5-0-pro",
"prompt": "Keep the person and the composition, change the outfit to a blue outdoor jacket",
"image": "https://example.com/reference.jpg",
"size": "2K",
"quality": "2K",
"response_format": "url"
}'Example with multiple reference images:
{
"model": "doubao-seedream-5-0-pro",
"prompt": "Blend the subjects and colors from the reference images",
"images": [
"https://example.com/reference-1.jpg",
"https://example.com/reference-2.jpg"
],
"size": "2K",
"quality": "2K"
}Local Images
Local images are sent as a multipart request, one image per upload:
curl https://api.88api.ai/v1/images/edits \
-H "Authorization: Bearer $API_KEY" \
-F "model=doubao-seedream-5-0-pro" \
-F "prompt=Change the background to a light-colored photo studio" \
-F "image=@reference.png" \
-F "size=2K" \
-F "quality=2K" \
-F "response_format=url"Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Yes | — | doubao-seedream-5-0-pro |
prompt | string | Yes | — | Text-to-image description or image-to-image editing instruction |
n | integer | No | 1 | 1 to 4 |
size | string | No | — | 1K or 2K |
quality | string | No | — | 1K or 2K |
response_format | string | No | url | url or b64_json |
image | string / file | No | — | A single public reference image URL, or the uploaded file on the edits endpoint |
images | array[string] | No | — | Array of public reference image URLs, up to 14 |
Response Format
{
"created": 1760000000,
"data": [
{
"url": "https://..."
}
],
"model": "doubao-seedream-5-0-pro"
}When response_format is url, read data[].url; when it is b64_json, read
data[].b64_json.
Midjourney V8.2 Image Generation API
Previous Page
88API Speech APIs: TTS & STT
Integration guide for Grok and Gemini speech models: /v1/audio/speech text to speech, WebSocket streaming text to speech, Grok realtime voice conversation, /v1/audio/transcriptions and audio chat transcription, with all voices, output formats, request fields, cURL, OpenAI SDK, Python and Node.js examples.