Seedance 1.5 Pro is Live Now!Try Now!
Home/Explore/Seedance Video Models/bytedance/seedance-v1.5-pro/video-extend
video-to-video

video-to-video

Seedance 1.5 Pro Video Extend

bytedance/seedance-v1.5-pro/video-extend

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.

Hint: You can drag and drop a file or click to upload

Whether to generate audio.
Whether to fix the camera position.

Idle

Your request will cost $0.26 per run.

For $10 you can run this model approximately 38 times.

One more thing::

ExamplesView all

README

ByteDance Seedance V1.5 Pro — 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

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 (commonly used values: 4–12s; exact allowed values depend on endpoint validation).
resolutionOutput resolution: 720p or 480p.
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 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)

ResolutionPrice per secondExample (5s)Example (10s)
720p$0.052$0.26$0.52
480p$0.024$0.12$0.24

Reference pricing (generate_audio = false)

ResolutionPrice per secondExample (5s)Example (10s)
720p$0.026$0.13$0.26
480p$0.012$0.06$0.12

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