Doubao-Seedream-5.5 API
Doubao-Seedream-5.5 is ByteDance Seed's image generation and editing model, released November 9, 2026, with stable multi-round editing across up to 100 rounds and native transparent asset output.
Doubao-Seedream-5.5 is an image generation and editing model from ByteDance Seed, released on November 9, 2026. It accepts text and image input and produces image output. Its headline capability is multi-round editing: non-edited regions are preserved at pixel level across as many as 100 consecutive edits. It also generates native RGBA transparent assets with an Alpha channel, producing up to 100 transparent asset layers per output — one opaque base image plus up to 99 transparent PNG layers — so background removal is no longer needed.
Image quality improvements target realism, with reduced overexposure and plastic-like sheen. Text rendering is stronger for complex glyphs and dense small text, and multi-material compositing keeps physical occlusion accurate while recalculating lighting and shadows. A single image generation takes about 5 to 10 seconds. In an image-to-image realism comparison, it shows a positive preference gain of +55.62% over the previous generation.
The model suits tasks such as e-commerce marketing imagery, advertising design, film and game assets, home decor design, knowledge visualization, storyboards, sticker and character assets, UI icons, infographics, and poster copy. It is available on Doubao, Doubao Work, and Jimeng, with API access on Volcano Ark. As of November 9, 2026 it has not appeared on third-party leaderboards such as Artificial Analysis or Design Arena, and some benchmark data comes from official self-testing or media reports.
Updated:
MODEL ID
doubao-seedream-5-5-261028- Input
- text / image
- Output
- image
Highlights
- Stable edits across up to 100 rounds
- Native RGBA transparent output
- Up to 99 transparent PNG layers
- More realistic images, less plastic sheen
- Sharper rendering of small and complex text
- About 5 to 10 seconds per image
Providers
Best priceCompare API prices across providers. Select a provider to view all charges and conditions.
| Uptime | |||
|---|---|---|---|
Historical observations are not a live health check. Missing data does not mean an outage.
Benchmarks
- 0.4%
Severe text corruption rate
Official evaluation; lower is better
- 1.7%
Minor text corruption rate
Official evaluation; lower is better
- 95%
Small-text accuracy
Official evaluation
Scores as published by the model provider.
Quick Start
Submit an image task, poll its status, then save the images. These examples use curl and Python 3 (standard library only).
POST https://openapi.felo.ai/api/v1/images/generations
1Get your API key
Create a key from your Felo API Platform account and set it as an environment variable.
export FELO_API_KEY="YOUR_API_KEY"2Make your first request
Optional values vary by model. This example leaves them unset; confirm supported values in Playground before adding them. Request fields sit alongside model and prompt, without an input wrapper.
curl --fail-with-body --max-time 60 "https://openapi.felo.ai/api/v1/images/generations" \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-o created.json \
-d '{
"prompt": "A studio product photo of a ceramic coffee cup on warm linen, soft morning light",
"model": "doubao-seedream-5-5-261028"
}'3Poll the task
Submission returns task_id. Poll every 3 seconds while queued or running; stop on succeeded, failed or interrupted. This example stops waiting after 30 minutes. Keep created.json to resume querying the same task instead of submitting again.
python3 - <<'PY'
import json, os, time
from pathlib import Path
from urllib.parse import quote
from urllib.request import Request, urlopen
task = json.loads(Path("created.json").read_text())
task_id = task["task_id"]
url = "https://openapi.felo.ai/api/v1/images/generations/" + quote(task_id, safe="")
headers = {"Authorization": "Bearer " + os.environ["FELO_API_KEY"]}
deadline = time.monotonic() + 1800
while task["status"] in ("queued", "running"):
if time.monotonic() >= deadline:
raise TimeoutError(f"Keep task_id={task_id} to resume polling")
time.sleep(3)
with urlopen(Request(url, headers=headers), timeout=60) as response:
task = json.load(response)
if task.get("task_id") != task_id or task.get("kind") != "image":
raise ValueError("Unexpected task response")
print(task["status"])
if task["status"] != "succeeded":
raise RuntimeError(task.get("error") or task["status"])
if not task.get("outputs"):
raise ValueError("Task succeeded without image outputs")
Path("task.json").write_text(json.dumps(task))
print("Saved task.json")
PY4Download the output
After success, save outputs from task.json. Results may be HTTPS URLs, URL objects or b64_json. Download signed URLs promptly; media downloads do not use your API key.
python3 - <<'PY'
import base64, json
from pathlib import Path
from urllib.request import urlopen
task = json.loads(Path("task.json").read_text())
if task.get("status") != "succeeded" or not task.get("outputs"):
raise ValueError("No completed image outputs")
extensions = {"image/png": ".png", "image/jpeg": ".jpg", "image/webp": ".webp", "image/gif": ".gif", "image/avif": ".avif"}
for index, output in enumerate(task["outputs"], 1):
item = output if isinstance(output, dict) else {}
url = output if isinstance(output, str) else item.get("url") or item.get("unsigned_url")
mime = item.get("media_type") or "image/png"
if url and url.startswith("https://"):
with urlopen(url, timeout=60) as response:
data = response.read()
mime = response.headers.get_content_type()
elif url and url.startswith("data:image/") and ";base64," in url:
header, encoded = url.split(",", 1)
mime = header[5:].split(";", 1)[0]
data = base64.b64decode(encoded, validate=True)
elif item.get("b64_json"):
data = base64.b64decode(item["b64_json"], validate=True)
else:
raise ValueError("Unrecognized image output")
path = Path(f"image-{index}" + extensions.get(mime, ".bin"))
path.write_bytes(data)
print(path)
PYPrefer the full reference?
API reference →Frequently asked questions
What is Doubao-Seedream-5.5?
Doubao-Seedream-5.5 is an image generation and editing model from ByteDance Seed, released on November 9, 2026. It accepts text and image input and produces image output. Its headline capability is multi-round editing: non-edited regions are preserved at pixel level across as many as 100 consecutive edits. It also generates native RGBA transparent assets with an Alpha channel, producing up to 100 transparent asset layers per output — one opaque base image plus up to 99 transparent PNG layers — so background removal is no longer needed. Image quality improvements target realism, with reduced overexposure and plastic-like sheen. Text rendering is stronger for complex glyphs and dense small text, and multi-material compositing keeps physical occlusion accurate while recalculating lighting and shadows. A single image generation takes about 5 to 10 seconds. In an image-to-image realism comparison, it shows a positive preference gain of +55.62% over the previous generation. The model suits tasks such as e-commerce marketing imagery, advertising design, film and game assets, home decor design, knowledge visualization, storyboards, sticker and character assets, UI icons, infographics, and poster copy. It is available on Doubao, Doubao Work, and Jimeng, with API access on Volcano Ark. As of November 9, 2026 it has not appeared on third-party leaderboards such as Artificial Analysis or Design Arena, and some benchmark data comes from official self-testing or media reports.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.
What input types does Doubao-Seedream-5.5 support?
It accepts text input and image input, and produces image output.
How stable is multi-round editing?
Non-edited regions are preserved at pixel level across up to 100 consecutive edits.
Does it output transparent images?
Yes. It natively generates RGBA transparent assets with an Alpha channel, with up to 100 transparent asset layers per output — one opaque base image and up to 99 transparent PNG layers.
What tasks is it best suited for?
It is suited to e-commerce marketing imagery, advertising design, film and game assets, home decor design, knowledge visualization, storyboards, sticker and character assets, UI icons, infographics, and poster copy.
How does it differ from Seedream 5.0 Pro?
According to media reports it costs less than Seedream 5.0 Pro and generates faster. Expert usability in film storyboard and office illustration scenarios is more than double that of Seedream 5.0 Pro.
Where can I use it?
It is available on Doubao, Doubao Work, and Jimeng, with API access on Volcano Ark.