Seedream 5.0 Pro 정식 출시 | 이미지 생성기에서 사용해보기 →

Seedream V4

bytedance /

Seedream 4.0 by is a state-of-the-art image generation model delivering high-fidelity outputs and outperforming Nano Banana. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-image
입력

대기 중

$0.027실행당·~37 / $1

다음:

관련 모델

README

Seedream V4

A text-to-image model optimized for multi-panel/tiled posters, concept designs with copy, series KV, and social media assets. It excels at grid-based layouts, whitespace planning, and type readability.

Model Highlights

  • Layout-aware: Grids (2×2, triptych, comics), keeps whitespace/safe areas for title/subtitle/CTA.
  • Consistent series: Unified palette, lighting, and camera across panels/KV.
  • High fidelity: Strong identity/detail retention; clean edges, fewer artifacts.
  • High-res: 2K default; custom ratios; up to 8192×8192.

Price

Only $0.027 for one run!!!

Copy-ready Templates

2×2 Grid Poster

2×2 grid poster, clean margins for typography; title top-center: “{TITLE}”; subtitle: “{SUBTITLE}”. Panel 1: {SCENE_A}; Panel 2: {SCENE_B}; Panel 3: {SCENE_C}; Panel 4: {SCENE_D}. Consistent color grading, cinematic lighting, brand color {BRAND_COLOR}, high-legibility background, minimal clutter.

Triptych (Horizontal)

Horizontal triptych, left-to-right narrative: {SCENE_A} → {SCENE_B} → {SCENE_C}. Unified palette {BRAND_COLOR}, soft vignette, clear gutters, strong typographic hierarchy, reserved space for CTA: “{CTA}”.

Comic (4-Panel Strip)

4-panel comic layout with speech-bubble placeholders. Panel 1: {SCENE_A}; Panel 2: {SCENE_B}; Panel 3: {SCENE_C}; Panel 4: {SCENE_D}. Bold line art, flat shading, clear gutters, high readability.

Minimalist Poster

Minimalist poster; large centered title: “{TITLE}”; small subtitle below: “{SUBTITLE}”. Single focal object: {OBJECT}. Monochrome + accent {BRAND_COLOR}. High-legibility background; strict grid; generous whitespace.

How to Use

  1. Enter your prompt: Describe the subject, layout, text placement (title/subtitle/CTA), and style.

  2. Set size: Choose width/height. Maximum: 8192×8192.

  3. Run: Click Run to generate. If needed, tweak the prompt or size and run again.

Recommended Resolutions

Aspect RatioExact (W×H)Exact PixelsRounded (W×H, ÷64)Rounded Pixels
1:11448 × 14482,096,7041408 × 14081,982,464
3:21773 × 11822,095,6861728 × 11521,990,656
4:31672 × 12542,096,6881664 × 12162,023,424
16:91936 × 10892,108,3041920 × 10882,088,960
21:92212 × 9482,096,9762176 × 9602,088,960
1:11024 × 10241,048,5761024 × 10241,048,576
3:21254 × 8361,048,3441216 × 8321,011,712
4:31182 × 8871,048,4341152 × 8961,032,192
16:91365 × 7681,048,3201344 × 7681,032,192
21:91564 × 6701,047,8801536 × 640983,040
1:1323 × 323104,329320 × 320102,400
3:2397 × 264104,808384 × 25698,304
4:3374 × 280104,720448 × 320143,360
16:9432 × 243104,976448 × 256114,688
21:9495 × 212104,940576 × 256147,456
참고:이 웹사이트는 제3자가 제공하는 AI 모델을 사용합니다.

Seedream v4 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedream-v4 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 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"
}
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" \
  -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
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "size": "2048*2048"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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"
}

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", 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 API — Frequently asked questions

What is the Seedream v4 API?

Seedream v4 is a ByteDance model for image generation, exposed as a REST API on WaveSpeedAI. Seedream 4.0 by is a state-of-the-art image generation model delivering high-fidelity outputs and outperforming Nano Banana. Ready-to-use REST inference 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 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.

How much does Seedream v4 cost per run?

Seedream v4 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 accept?

Key inputs: `prompt`, `size`, `enable_base64_output`, `enable_sync_mode`. 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.

How long does Seedream v4 take to generate?

Median end-to-end generation time on WaveSpeedAI is around 13 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Seedream v4 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.

Seedream V4 | High-Quality Text-to-Image API | WaveSpeedAI