dola-seedream-5.5-t2i API

Seedream 5.5 is the newest Seedream image model: t2i creates images from text and i2i edits or restyles 1–10 reference images, with transparent backgrounds, one image per request at 1k, 1.5k or 2k. seedream-v5.5 runs in China and dola-seedream-5.5 is the international version.

Try online · Get an API key · Read the docs

Capabilities

Model
Image
API model
dola-seedream-5.5-t2i
Endpoints
POST /v1/image/generations, GET /v1/image/generations/{id}
Parameters
prompt: 5–5000, images: 1–10 (i2i), metadata.resolution: 1k / 1.5k / 2k, metadata.width / metadata.height: 240–11520, 921,600–8,294,400 px, metadata.background: auto / transparent / opaque, metadata.output_format: jpeg / png, metadata.watermark

Current pricing

≈¥0.14–0.25 per request

Gallery examples

  • Will Anyone Care If I Get Soaked?Will Anyone Care If I Get Soaked?

    API model: dola-seedream-5.5-t2i

    Will Anyone Care If I Get Soaked? — explore this dola-seedream-5.5-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Ancient StyleAncient Style

    API model: dola-seedream-5.5-t2i

    Ancient Style — explore this dola-seedream-5.5-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Ice and SnowIce and Snow

    API model: dola-seedream-5.5-t2i

    Ice and Snow — explore this dola-seedream-5.5-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Rainy DayRainy Day

    API model: dola-seedream-5.5-t2i

    Rainy Day — explore this dola-seedream-5.5-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Private BathroomPrivate Bathroom

    API model: dola-seedream-5.5-t2i

    Private Bathroom — explore this dola-seedream-5.5-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • FoxFox

    API model: dola-seedream-5.5-t2i

    Fox — explore this dola-seedream-5.5-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.

Explore the prompt gallery

Quick start

Example workflow: create a product cut-out with t2i (background: transparent with png), then switch to i2i and add images to change the backdrop or style. A prompt of 5–5000 characters is required; t2i accepts no references and i2i needs 1–10 (30 MB each at most). metadata.resolution is 1k, 1.5k or 2k (default 2k) and takes priority over width and height; alternatively send metadata.width and metadata.height (240–11520 each, 921,600–8,294,400 pixels in total, aspect ratio 1:16 to 16:1). background is auto, transparent or opaque, and transparent requires png; output_format is jpeg or png; watermark is a boolean. seed and n are not supported.

cURL

curl --fail-with-body https://www.zzai.app/v1/image/generations \
  -H "Authorization: Bearer $SEEDANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"metadata":{"background":"transparent","output_format":"png","resolution":"2k"},"model":"dola-seedream-5.5-t2i","prompt":"A glass serum bottle on soft studio light, premium skincare product shot, clean cut-out."}'

Python

import json, os, requests

payload = json.loads(r'''{"metadata":{"background":"transparent","output_format":"png","resolution":"2k"},"model":"dola-seedream-5.5-t2i","prompt":"A glass serum bottle on soft studio light, premium skincare product shot, clean cut-out."}''')
response = requests.post(
    "https://www.zzai.app/v1/image/generations",
    headers={"Authorization": "Bearer " + os.environ["SEEDANCE_API_KEY"]},
    json=payload, timeout=120,
)
response.raise_for_status()
print(response.json()["id"])

JavaScript

const response = await fetch("https://www.zzai.app/v1/image/generations", {
  method: 'POST',
  headers: { Authorization: 'Bearer ' + process.env.SEEDANCE_API_KEY, 'Content-Type': 'application/json' },
  body: JSON.stringify({"metadata":{"background":"transparent","output_format":"png","resolution":"2k"},"model":"dola-seedream-5.5-t2i","prompt":"A glass serum bottle on soft studio light, premium skincare product shot, clean cut-out."}),
});
if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).id);

Save the returned id as TASK_ID in the query example. Query every 3–5 seconds until success or failure; submission does not mean generation is complete. Save result files promptly. data.status: SUCCESS / FAILURE; data.result_url.

curl --fail-with-body https://www.zzai.app/v1/image/generations/$TASK_ID \
  -H "Authorization: Bearer $SEEDANCE_API_KEY"

Frequently asked questions

How do I call this model?

Create an API key, choose the model name below, and send a request to the documented OpenAI-compatible endpoint. Final billing follows the current price and usage parameters.