Bytedance Seedance V1.5 Pro Video Extend API Documentation

Bytedance Seedance V1.5 Pro Video Extend API Documentation

Playground

Seedance 1.5 Pro Video-Extend turns short video clips into longer videos with natural motion continuation, stable aesthetics, and upscaled output. It supports 4–12s duration control, multiple aspect ratios/resolutions, and seed-reproducible results—ideal for extending ad creatives and short-drama shots. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.

Features

> Notice — Service Stability > > The Seedance 1.5 family is being retired or has already been retired by its original provider. Until it is fully removed, the service is unstable: generations may fall back to alternative models without notice, results can differ from what this model used to produce, and the service can be temporarily unavailable. > > If you need an equally capable, stable alternative, we recommend Seedance 2: bytedance/seedance-2.0/video-extend.

Seedance V1.5 Pro (Video Extend) extends an existing video into a longer clip while preserving motion continuity, subject identity, and scene coherence. Use a prompt to guide what happens next, set duration and resolution, and optionally enable audio generation for the extended segment.

Why it stands out

• Smooth continuation that matches the original clip’s rhythm and aesthetics
• Prompt-guided extension to steer action, mood, and camera behavior
• Resolution options with transparent multipliers (480p / 720p)
• Optional audio generation with clear pricing impact

Key Capabilities

• Natural motion continuation Extends movement with consistent pacing and visual logic.

• Scene coherence preservation Maintains lighting, framing, and subject consistency across the extension.

• Prompt-guided direction Describe the next action and constraints without rebuilding the scene.

• Optional audio generation Enable or disable audio generation depending on your workflow needs.

Parametrs

Prompt Tips

Write prompts like a continuation brief:

• Describe what happens next (action + timing)
• Add motion intensity (subtle / smooth / dynamic)
• Specify camera behavior if needed (fixed / slow pan / gentle zoom)
• Add constraints: “keep the same character, outfit, lighting, framing”

Example prompts:

• Continue the scene with the subject holding the glowing ball, the light intensifies near the end, keep the same camera angle and lighting style.
• Extend with subtle hand movement and a slow push-in, keep the subject centered and the environment unchanged.

Pricing

Reference pricing (generate_audio = true)

Reference pricing (generate_audio = false)

Best Practices

• Use clean input videos (clear subject, stable exposure, minimal compression artifacts).
• Keep prompts specific but short, and explicitly state what must stay the same.
• Start with 5 seconds to validate motion and framing before extending longer.
• Use a fixed seed when iterating to compare small prompt changes.

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 the scene changes too much, add stronger constraints: “keep camera fixed”, “same outfit and lighting”, “do not change background”.
• Supported durations and modes can vary by deployment; rely on the endpoint UI/validator for exact allowed values.

Related Models

• Seedance V1.5 Pro Video Extend Fast — Faster processing with higher-resolution options for rapid iteration and production outputs.
• Seedance V1.5 Pro (Text-to-Video) — Generate new videos from text prompts for end-to-end creation.
• Seedance V1.5 Pro (Image-to-Video) — Animate still images into videos with guided motion and stable aesthetics.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "duration": 5,
  "resolution": "720p",
  "generate_audio": true,
  "camera_fixed": false
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1.5-pro/video-extend" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters