Seedream 4.0 by creates 4K images with editing, character/object consistency and sequential multi-image generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
Idle
$0.027per run·~37 / $1
ExamplesView all
Generate a set of 4 consecutive illustrations, capturing a high-octane giant robot battle in a classic mecha anime style, from two massive mechs charging at each other in a ruined cityscape, to a dynamic clash of energy swords creating a shower of sparks, a close-up on a pilot's determined face inside the cockpit, and the final explosive shot of the victorious mech standing over its defeated foe.
Generate a set of 4 consecutive illustrations, detailing the life cycle of a butterfly, from a tiny egg on a leaf, to a caterpillar, then to a chrysalis, and finally to a beautiful butterfly.
Generate a set of 4 consecutive illustrations, depicting the awe-inspiring moment an astronaut on a desolate alien planet discovers life, from their lone rover cresting a crater rim, to noticing a faint, bioluminescent glow in the darkness below, then cautiously approaching a cave entrance pulsating with light, and finally the breathtaking reveal of a vast, glowing subterranean forest inside.
Generate a set of 4 consecutive illustrations, showing the growth of a sunflower from a seed sprouting, to a young plant, then to a budding flower, and finally to a full bloom facing the sun.
Generate a set of 5 consecutive illustrations: A close-up of a cheerful person with short, dark hair and wearing a yellow bucket hat and an orange t-shirt, holding up a light blue smartphone as if taking a selfie. Their backpack strap is visible over their shoulder. The background is slightly blurred but hints at an outdoor setting. The person from the first image is now shown from the waist up, their arm extended holding the smartphone, capturing a selfie. Behind them, a vibrant cityscape begins to emerge, featuring traditional Chinese architecture like a temple with a blue roof, and modern skyscrapers, including the recognizable Oriental Pearl TV Tower. A river flows in the midground. A wider shot reveals the full scene: the person is standing in a lush green park by a river. The impressive skyline of Shanghai stretches across the background, showcasing a blend of historical and futuristic buildings. A high-speed train is visible on an elevated track to the right, adding a sense of movement to the modern urban landscape. A panoramic view of the Shanghai cityscape from the park's perspective, without the person. The traditional temple, gleaming skyscrapers, the Oriental Pearl TV Tower, the river, and the elevated train track are all prominently featured. The park's greenery fills the foreground. A slightly zoomed-out panoramic shot, emphasizing the grand scale of the Shanghai skyline at sunset, with warm colors reflecting on the buildings and the river. The high-speed train is now a blur in the distance, and the park is a beautiful, serene space in the foreground.
Generate a set of 6 consecutive illustrations, in a slapstick cartoon style, detailing a comical chain of events started by a cat chasing a mouse, showing the mouse darting under a table, the cat crashing into the table leg, which causes a vase of water to tip over, spilling on a sleeping dog, who then jumps up in surprise and runs through the house, leaving a trail of wet paw prints everywhere.
Generate a set of 4 consecutive illustrations, in a soft, dreamy bedtime story style, depicting a tiny star who wishes to visit Earth, showing the little star twinkling brightly in the vast sky, then gently falling as a shooting star, landing softly in a child's backyard, sparkling on the grass for a moment, and finally wishing the child sweet dreams before twinkling back up to its home.
Generate a set of 5 consecutive illustrations, in a clean, minimalist sci-fi style, showing a factory robot's journey to consciousness, from performing a repetitive task on an assembly line, to a moment of hesitation as it observes a bird outside the window, then it deviating from its programming to gently touch the glass, followed by it looking at its own metallic hands with a new sense of wonder, and the final scene of it stepping out of the factory into the dawn of a new world.
Generate a set of 4 consecutive illustrations, in a whimsical, fantasy art style, personifying the changing of seasons, depicting the gentle Autumn Spirit handing over a golden leaf to the sleeping Winter Spirit, who then awakens, blanketing the landscape in frost and snow, followed by the energetic Spring Spirit arriving to melt the ice with a touch, and finally the vibrant Summer Spirit laughing as they bring forth a bounty of flowers and sunshine.
Related Models
README
Seedream V4 Sequential
What is it?
Seedream v4 sequential is ’s SOTA image model that use for sequential/group generation in one pipeline—built for cross-image consistency and rapid iteration.
Why choose Seedream?
- All-in-one, multi-modal: T2I, edit, and multi-image sets without switching models.
- Five strengths: precise instruction editing, high feature retention, deep understanding, ultra-fast inference, ultra-high-res output.
- Speed: as little as ~1.8 s for a 2K image (T2I).
- Powerful edits: add/remove objects, attribute & style changes, structural ops (e.g., face swap), texture/brush/frame edits.
- Sequential consistency: maintains identity, palette, and layout across a set/series.
Designed for
- Commercial design — Posters, apparel, packaging, e-commerce visuals; fast varianting and brand-safe edits.
- Entertainment IP — Anime/film characters; style-consistent key art, poses, and look dev.
- Art creation — High-res illustration, stylistic explorations, and series with coherent aesthetics.
- Architecture — Concept renders, façade studies, material/lighting variations across sets.
- Brand content — Campaign assets and social creatives with locked palette, logo, and identity.
How to use
- Write prompt: action + object + target feature. For sets add “a series of N images” and style locks.
- Set the parameter: size, max_images.
Price
- $0.027 per image.
- Total price = max_images * $0.027
Prompt Examples
- Instruction edit:
Replace [A] with [B]; keep [lighting/style]; preserve [logo/identity]. - T2I coherent:
A [subject] in [scene/time/weather], [camera/lens], [lighting], [style]; key props [X]; composition [framing]. - Sequential set:
Generate a series of [N] images of [subject/brand] in [scenario]; keep consistent [palette/logo/identity]; vary [poses/angles/backgrounds].
Note
Please set the max_image first, and then input how many images you want to generate in prompt! Such as:
- max_image = 4.
- Prompt: I want to generate 4 images... + (your prompt)
Recommended Resolutions
| Aspect Ratio | Exact (W×H) | Exact Pixels | Rounded (W×H, ÷64) | Rounded Pixels |
|---|---|---|---|---|
| 1:1 | 1448 × 1448 | 2,096,704 | 1408 × 1408 | 1,982,464 |
| 3:2 | 1773 × 1182 | 2,095,686 | 1728 × 1152 | 1,990,656 |
| 4:3 | 1672 × 1254 | 2,096,688 | 1664 × 1216 | 2,023,424 |
| 16:9 | 1936 × 1089 | 2,108,304 | 1920 × 1088 | 2,088,960 |
| 21:9 | 2212 × 948 | 2,096,976 | 2176 × 960 | 2,088,960 |
| 1:1 | 1024 × 1024 | 1,048,576 | 1024 × 1024 | 1,048,576 |
| 3:2 | 1254 × 836 | 1,048,344 | 1216 × 832 | 1,011,712 |
| 4:3 | 1182 × 887 | 1,048,434 | 1152 × 896 | 1,032,192 |
| 16:9 | 1365 × 768 | 1,048,320 | 1344 × 768 | 1,032,192 |
| 21:9 | 1564 × 670 | 1,047,880 | 1536 × 640 | 983,040 |
| 1:1 | 323 × 323 | 104,329 | 320 × 320 | 102,400 |
| 3:2 | 397 × 264 | 104,808 | 384 × 256 | 98,304 |
| 4:3 | 374 × 280 | 104,720 | 448 × 320 | 143,360 |
| 16:9 | 432 × 243 | 104,976 | 448 × 256 | 114,688 |
| 21:9 | 495 × 212 | 104,940 | 576 × 256 | 147,456 |
Seedream v4 Sequential API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedream-v4/sequential with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seedream v4 Sequential below.
HTTP example
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "2048*2048",
"max_images": 1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4/sequential" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneNode.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4/sequential";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "2048*2048",
"max_images": 1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}Python example
import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "2048*2048",
"max_images": 1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bytedance/seedream-v4/sequential", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Seedream v4 Sequential API — Frequently asked questions
What is the Seedream v4 Sequential API?
Seedream v4 Sequential is a ByteDance model for image generation, exposed as a REST API on WaveSpeedAI. Seedream 4.0 by creates 4K images with editing, character/object consistency and sequential multi-image generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Seedream v4 Sequential API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4-sequential.
How much does Seedream v4 Sequential cost per run?
Seedream v4 Sequential starts at $0.027 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Seedream v4 Sequential accept?
Key inputs: `prompt`, `size`, `enable_base64_output`, `enable_sync_mode`, `max_images`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4-sequential.
How do I get started with the Seedream v4 Sequential API?
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Can I use Seedream v4 Sequential outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.