Bytedance Seedance 2.0 Mini Video Extend API Documentation

Bytedance Seedance 2.0 Mini Video Extend API Documentation

Playground

Seedance 2.0 Mini Video Extend is ByteDance’s faster, lower-cost video extension model for cinematic multi-shot continuation. It extends existing videos into seamless narrative sequences with AI camera control, consistent characters, motion continuity, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ByteDance Seedance 2.0 Mini Video Extend continues an existing video by generating a new segment from the input video’s last frame. Upload a source video, describe the cinematic continuation, optionally provide a target last frame, and generate an extended video segment with synchronized native audio.

• Need to generate from text instead? Try ByteDance Seedance 2.0 Mini Text-to-Video.
• Need to generate from a start image instead? Try ByteDance Seedance 2.0 Mini Image-to-Video.

Why Choose This?

• Video continuation
  Extend an existing video by generating a new segment that continues from the input video’s last frame.

• Prompt-guided extension
  Describe the action, camera movement, lighting, and mood for the new segment.

• Optional target last frame
  Provide last_image when you want the new segment to interpolate toward a specific ending frame.

• Native audio generation
  Generate synchronized audio together with the extended video segment using generate_audio.

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

• Web search option
  Enable enable_web_search when the continuation needs real-time information.

Parameters

How to Use

1. Write your prompt — Describe how the video should continue, including subject action, camera movement, lighting, and mood.
2. Upload the source video — Provide the input video that should be extended.
3. Add a last image optional — Use last_image when you want to guide the ending frame of the new segment.
4. Choose resolution — Select 480p, 720p, 1080p, or 4k.
5. Set duration — Choose the length of the new segment between 4 and 15 seconds.
6. Configure audio optional — Keep generate_audio enabled for synchronized native audio, or disable it if audio is not needed.
7. Submit — Generate the extended video segment.

Example Prompt

Continue the scene with a slow forward camera movement, the character walking deeper into the neon-lit street, soft rain falling, reflections glowing on the pavement, cinematic lighting, calm but mysterious atmosphere.

Writing Effective Prompts

Extension here continues your video by generating a new segment from its final frame and stitching it on. So your prompt describes what happens next, starting from that last frame — the same way you’d direct an image-to-video shot. (This differs from native extension: don’t write “continue” or “extend backward” triggers; just describe the new action.)

Direct the new segment

Describe the action, motion, and camera work that begin from the final frame. Don’t re-describe what’s already on screen — build forward from it.

From the final frame, the surfer rides the wave to shore; the camera pulls back to a wide shot.

Keep it continuous

Match the motion, camera, and pacing of the source so the seam is invisible. 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

Per 5 Seconds

Per Second

Example Costs

Best Use Cases

• Video extension — Continue an existing clip with a newly generated segment.
• Scene continuation — Extend character action, camera movement, lighting, and atmosphere from the source video.
• Target-frame continuation — Use last_image to guide the ending direction of the new segment.
• Cinematic short clips — Generate continued video segments with synchronized native audio.
• Creative prototyping — Test alternate continuations from the same source video.

Pro Tips

• Use a source video with a clear ending frame.
• Keep the prompt focused on what should happen next.
• Use last_image when the final frame or ending direction matters.
• Describe visible motion, camera behavior, lighting, and mood.
• Use 480p for quick testing, 720p for standard output, 1080p for higher-resolution results, and 4k for maximum-resolution output.
• Keep generate_audio enabled when you want the extended segment to include synchronized native audio.

Related Models

• ByteDance Seedance 2.0 Mini Text-to-Video — Generate video directly from text prompts.
• ByteDance Seedance 2.0 Mini Image-to-Video — Generate video from a start image and prompt.

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,
  "enable_web_search": false,
  "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-2.0-mini/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