WaveSpeedAI APIBytedanceBytedance Seedance V1.5 Pro Video Extend Fast

Bytedance Seedance V1.5 Pro Video Extend Fast

Bytedance Seedance V1.5 Pro Video Extend Fast

Playground

Try it on WavespeedAI!

Seedance 1.5 Pro Fast Video Extend turns short shots into longer clips with natural motion continuation and strong temporal consistency. Supports 4–12 s extensions, 720p/1080p output with built-in upscaling, and seed-reproducible results for shot matching. Ideal for ads, trailers, and short-drama beats. Production-ready REST API with fast response, no cold starts, and affordable pricing.

Features

ByteDance Seedance V1.5 Pro Fast — Video Extend

Seedance V1.5 Pro Fast (Video Extend) extends an existing video into a longer clip while maintaining motion continuity, subject consistency, and scene coherence. Use a guiding prompt to control what happens next, choose duration and resolution, and optionally generate audio for the extended segment.


Why it stands out

  • Smooth continuation that follows the original clip’s motion rhythm and visual style
  • Prompt-guided extension to steer actions, mood, and camera behavior
  • Resolution control with a simple cost multiplier (720p vs 1080p)
  • Optional audio generation with transparent pricing impact

Key Capabilities

  • Natural motion continuation Extends movement in a way that feels consistent with the input clip.

  • Scene coherence preservation Keeps lighting, composition, and identity cues stable across the extension.

  • Prompt-guided direction Describe what should happen next without rebuilding the scene from scratch.

  • Optional audio generation Enable or disable audio generation (pricing differs).


Parameters

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, up to 12s (allowed values depend on the endpoint configuration).
resolutionOutput resolution: 720p or 1080p.
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 director’s note:

  • Action next: what happens after the input ends
  • Motion intensity: subtle / smooth / dynamic / dramatic
  • Camera behavior: fixed / slow pan / gentle zoom (if you care, say it)
  • Consistency constraints: “keep the same character, outfit, lighting, framing”

Example prompts:

  • Continue the scene with the woman giving a wink to the camera, keep the same lighting and framing, subtle motion, natural facial expression.
  • Extend with a slow zoom out to reveal more of the environment while keeping the subject centered and the mood unchanged.

Pricing

Reference pricing (generate_audio = true)

ResolutionPrice per secondExample (5s)Example (10s)
720p$0.04$0.20$0.40
1080p$0.06$0.30$0.60

Reference pricing (generate_audio = false)

ResolutionPrice per secondExample (5s)Example (10s)
720p$0.02$0.10$0.20
1080p$0.03$0.15$0.30

Best Practices

  • Use clean input videos (clear subject, stable exposure, minimal compression artifacts).
  • Keep prompts specific but short, and state what must stay the same.
  • Start with 5s to validate motion and framing before extending longer.
  • Use 720p for fast preview iterations, then switch to 1080p for final.
  • Set a fixed seed when you want consistent reruns while refining the prompt.

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 changes too much, add stronger constraints: “keep face unchanged”, “keep camera fixed”, “same outfit and lighting”.
  • Capability and allowed duration values can vary by deployment; rely on the endpoint’s UI/validator for the exact supported options.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1.5-pro/video-extend-fast" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true,
    "camera_fixed": false,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
videostringYes-The video URL to extend.
durationintegerNo54 ~ 12The duration of the generated media in seconds.
resolutionstringNo720p720p, 1080pVideo resolution.
generate_audiobooleanNotrue-Whether to generate audio.
camera_fixedbooleanNofalse-Whether to fix the camera position.
seedintegerNo-1-1 ~ 2147483647The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.