Bytedance Seedance 2.5 Video Extend API Documentation

Bytedance Seedance 2.5 Video Extend API Documentation

Playground

Seedance 2.5 (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Features

Seedance 2.5 Video Extend appends a new cinematic continuation to an existing video. The model continues from the ending of the input video, using the recent motion and audio context to generate a coherent new segment that preserves movement, subject continuity, and sound flow.

Why Choose This?

• Seamless video continuation
  Generate a new segment that continues naturally from the end of the source video.

• Motion and scene continuity
  Use the input video’s ending context to preserve subject movement, camera direction, and scene flow.

• Prompt-guided extension
  Describe what should happen next, including action, lighting, camera movement, mood, and atmosphere.

• Native audio synchronization
  Generate synchronized audio for the extended segment while preserving the original video’s audio.

• Flexible resolution options
  Choose 480p, 720p, 1080p, or 4k depending on quality and cost needs.

Parameters

How to Use

1. Upload the input video — Provide the source video you want to extend.
2. Write the continuation prompt — Describe what should happen after the original ending.
3. Set duration — Choose the length of the new segment from 4 to 30 seconds.
4. Choose resolution — Select 480p, 720p, 1080p, or 4k.
5. Configure audio optional — Keep generate_audio enabled when synchronized audio is needed.
6. Submit — Generate the final output with the original video and new segment joined together.

Writing Effective Prompts

Extension continues your source video forward or backward. Your prompt describes what happens in the new footage — the model matches the existing look and motion.

Direct the continuation

Use a continuation trigger (continue, extend forward, extend backward) and describe the new action.

• “Continue the video: the character walks off-screen to the right as the camera pans to follow.”
• “Extend backward: before the scene begins, show the same character entering the room and sitting down.”

Keep it continuous

Describe motion, camera, and pacing that flow naturally from where the source leaves off — abrupt changes break the seam. For longer extensions, use a timed shot list.

> 0-3s: The bee lifts off the flower, the camera following in a slow macro pull-back. > 3-5s: It drifts to a second flower and lands; pollen catches the light as it settles.

Camera language

Write these directly; the model understands them:

• Shot size — extreme wide, wide, medium, medium close-up, close-up
• Movement — push in, pull out, pan, track, follow, orbit, tilt up, handheld shake
• Angle — low angle, overhead, eye-level, first-person
• Techniques — one-shot / long take, dolly zoom, bullet time, speed ramp

For a niche term, add a plain-language gloss: “rack focus: the sharp foreground softens as the background comes into focus.”

Negative control

Positive descriptions work best, but you can suppress subtitles and audio:

• “No subtitles.”
• “No BGM — ambient and action sounds only.”
• “No audio.”

Weak vs. strong

Pricing

Pricing is based on the combined duration of reference duration + new segment duration.

The reference duration is calculated from the input video context, clamped to 2–30 seconds. The new segment duration is controlled by the duration parameter.

Example Costs: 10s Source + 5s Extension

Example Costs: 30s Source + 10s Extension

Best Use Cases

• Scene continuation — Extend an existing clip with a coherent new segment.
• Story progression — Continue character action, camera movement, and atmosphere from the original ending.
• Ad creative extension — Expand short campaign clips into longer variants.
• Social media content — Generate longer versions of short videos for different platforms.
• Creative prototyping — Test alternate continuations from the same source video.

Pro Tips

• Use a source video with a clear ending frame and stable final motion.
• Describe what should happen next instead of restating the full original video.
• Mention subject action, camera direction, lighting, atmosphere, and sound cues.
• Use 480p or 720p for iteration and 1080p or 4k for higher-quality output.
• Keep the input video focused on the part you want to continue from.
• Native audio generation is included for the new segment, and the original video’s audio is preserved.

Related Models

• Seedance 2.5 Image-to-Video — Generate video from a start image and prompt.
• Seedance 2.5 Video Edit — Edit an existing video with a prompt.
• Seedance 2.0 Video Extend — Previous-generation Seedance video extension model.

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",
  "resolution": "720p",
  "duration": 5,
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/video-extend" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters