Seedance 2.5 est en ligne | Essayez-le dans le générateur vidéo →

bytedance/

Seedance 1.5 Pro Fast Video Extend turns short shots into longer clips with natural motion continuation and strong temporal consistency. Supports 4–12 s extensions, 720p/1080p output with built-in upscaling, and seed-reproducible results for shot matching. Ideal for ads, trailers, and short-drama beats. Production-ready REST API with fast response, no cold starts, and affordable pricing.

video-extend
Entrée

En attente

$0.2par exécution·~50 / $10

ExemplesTout voir

The woman is smiling at the camera, and the sun is shining on her hair

The woman is giving a wink to the camera

Santa Claus stands up and walks away

The woman is smiling at the camera, and the sun is shining on her hair

Modèles associés

README

Seedance V1.5 Pro Fast — Video Extend

Seedance V1.5 Pro Fast (Video Extend) extends an existing video into a longer clip while maintaining motion continuity, subject consistency, and scene coherence. Use a guiding prompt to control what happens next, choose duration and resolution, and optionally generate audio for the extended segment.

Why it stands out

  • Smooth continuation that follows the original clip’s motion rhythm and visual style
  • Prompt-guided extension to steer actions, mood, and camera behavior
  • Resolution control with a simple cost multiplier (720p vs 1080p)
  • Optional audio generation with transparent pricing impact

Key Capabilities

  • Natural motion continuation Extends movement in a way that feels consistent with the input clip.

  • Scene coherence preservation Keeps lighting, composition, and identity cues stable across the extension.

  • Prompt-guided direction Describe what should happen next without rebuilding the scene from scratch.

  • Optional audio generation Enable or disable audio generation (pricing differs).

Parameters

ParameterDescription
video*Input video (public URL or uploaded file reference, depending on client).
prompt*Describe what should happen next and what must remain consistent.
durationOutput duration in seconds, up to 12s (allowed values depend on the endpoint configuration).
resolutionOutput resolution: 720p or 1080p.
generate_audioWhether to generate audio for the output video (true/false).
camera_fixedWhether to fix the camera position (true/false).
seedRandom seed (-1 for random; set a fixed integer for reproducible results).

Prompt Tips

Write prompts like a continuation director’s note:

  • Action next: what happens after the input ends
  • Motion intensity: subtle / smooth / dynamic / dramatic
  • Camera behavior: fixed / slow pan / gentle zoom (if you care, say it)
  • Consistency constraints: “keep the same character, outfit, lighting, framing”

Example prompts:

  • Continue the scene with the woman giving a wink to the camera, keep the same lighting and framing, subtle motion, natural facial expression.
  • Extend with a slow zoom out to reveal more of the environment while keeping the subject centered and the mood unchanged.

Pricing

Reference pricing (generate_audio = true)

ResolutionPrice per secondExample (5s)Example (10s)
720p$0.04$0.20$0.40
1080p$0.06$0.30$0.60

Reference pricing (generate_audio = false)

ResolutionPrice per secondExample (5s)Example (10s)
720p$0.02$0.10$0.20
1080p$0.03$0.15$0.30

Best Practices

  • Use clean input videos (clear subject, stable exposure, minimal compression artifacts).
  • Keep prompts specific but short, and state what must stay the same.
  • Start with 5s to validate motion and framing before extending longer.
  • Use 720p for fast preview iterations, then switch to 1080p for final.
  • Set a fixed seed when you want consistent reruns while refining the prompt.

Use Cases

  • Ad creative extension (turn short shots into longer deliverables)
  • Social content variations (longer cuts from a base clip)
  • Storytelling continuity (extend key moments with controlled motion)
  • Marketing edits (extend hero scenes with stable aesthetics)

Notes

  • The input video must be accessible to the runtime (public URL or valid uploaded reference).
  • If motion drifts or changes too much, add stronger constraints: “keep face unchanged”, “keep camera fixed”, “same outfit and lighting”.
  • Capability and allowed duration values can vary by deployment; rely on the endpoint’s UI/validator for the exact supported options.

Related Models

Remarque :Ce site utilise des modèles d'IA fournis par des tiers. Les prix de la documentation sont indicatifs et peuvent être obsolètes. Le bouton Generate affiche une estimation ; le montant final de la tâche prévaut.

Seedance v1.5 Pro Video Extend Fast API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-v1.5-pro/video-extend-fast 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 Seedance v1.5 Pro Video Extend Fast 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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true,
    "camera_fixed": false,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1.5-pro/video-extend-fast" \
  -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/seedance-v1.5-pro/video-extend-fast";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "duration": 5,
        "resolution": "720p",
        "generate_audio": true,
        "camera_fixed": false,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": True,
    "camera_fixed": False,
    "seed": -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/seedance-v1.5-pro/video-extend-fast", 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)

Seedance v1.5 Pro Video Extend Fast API — Frequently asked questions

What is the Seedance v1.5 Pro Video Extend Fast API?

Seedance v1.5 Pro Video Extend Fast is a ByteDance model for video extension, exposed as a REST API on WaveSpeedAI. Seedance 1.5 Pro Fast Video Extend turns short shots into longer clips with natural motion continuation and strong temporal consistency. Supports 4–12 s extensions, 720p/1080p output with built-in upscaling, and seed-reproducible results for shot matching. Ideal for ads, trailers, and short-drama beats. Production-ready REST API with fast response, no cold starts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Seedance v1.5 Pro Video Extend Fast 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-seedance-v1.5-pro-video-extend-fast.

How much does Seedance v1.5 Pro Video Extend Fast cost per run?

Seedance v1.5 Pro Video Extend Fast starts at $0.20 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 Seedance v1.5 Pro Video Extend Fast accept?

Key inputs: `prompt`, `video`, `resolution`, `duration`, `seed`, `camera_fixed`. 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-seedance-v1.5-pro-video-extend-fast.

How long does Seedance v1.5 Pro Video Extend Fast take to generate?

Median end-to-end generation time on WaveSpeedAI is around 260 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 Seedance v1.5 Pro Video Extend Fast 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.

Seedance V1.5 Pro Video Extend Fast | AI Video Extension API on WaveSpeedAI