GPT Image 2가 출시되었습니다. Image Generator에서 사용해보기→
/탐색/Seedance 2.0 Models /bytedance/seedance-2.0-fast/video-extend

Seedance 2.0 Fast Video-Extend

bytedance /

Seedance 2.0 Fast (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt — at the faster, cheaper Seedance 2.0 Fast tier.

video-extend
입력

드래그 앤 드롭 또는 클릭하여 업로드

드래그 앤 드롭 또는 클릭하여 업로드

Enable web search for real-time information.

대기 중

이 요청에는 $0.5 실행당가 필요합니다.

$10으로 이 모델을 약 20회 실행할 수 있습니다.

예시전체 보기

README

Seedance 2.0 Fast Video-Extend

Seedance 2.0 Fast Video-Extend is the faster, cheaper tier of Seedance 2.0 Video-Extend. It appends a new cinematic continuation to an existing video by generating a fresh segment from the input video's last frame and a natural-language prompt, then concatenating original and new segment into a single output.

Key Features

  • Seamless continuation — Generation starts from the input video's last frame so the join is visually consistent.
  • Optional target last frame — Provide last_image to steer the new segment toward a specific end frame.
  • Director-level control — Camera movement, lighting, shadows, and character performance via prompts.
  • Native audio synchronization — Audio from both the original video and the new segment are preserved in the final output.
  • Faster, cheaper — ~17% cheaper than the standard Seedance 2.0 Video-Extend at every resolution.

Parameters

ParameterRequiredDescription
promptYesDescribe the cinematic continuation.
videoYesInput video URL. Generation continues from the last frame.
last_imageNoOptional target last-frame URL. Interpolates from the input's last frame to this image.
durationNoLength in seconds of the new segment (4-15, default 5).
resolutionNo480p, 720p (default), or 1080p.
enable_web_searchNoEnable web search for real-time context.

How to Use

  1. Upload the input video. The new segment will be appended to it.
  2. Write the prompt. Describe the continuation in cinematic detail.
  3. (Optional) Upload a target last frame. The new segment will interpolate to this image.
  4. Pick a duration and resolution.
  5. Run. Receive the original video plus the new segment concatenated into one output.

Pricing

Billed per second of the new segment only. Resolution multipliers match Seedance 2.0 Fast image-to-video.

ResolutionPer second
480p$0.10
720p$0.20
1080p$0.50

Examples (5s extension):

ResolutionCost
480p$0.50
720p$1.00
1080p$2.50

Notes

  • Pricing is based on the new segment length only — the input video is not re-billed.
  • Aspect ratio of the new segment matches the input video's last frame automatically.
  • Native audio generation is included for the new segment; the original video's audio is preserved.

Related Models