bytedance/seedance-2.0/video-extendFrom 53 credits for a 5-second clip· Extend Video

Continue a clip with Seedance 2.0: the last frame of your video opens a new 4 to 15 second segment, and you get back one file with the original and the continuation joined, at 480p, 720p, 1080p or 4k.

Call it with the model name bytedance/seedance-2.0/video-extend on POST /jobs/createTask, from 53 credits for a 5-second clip ($0.53). New accounts get 30 free credits to try it in the Playground first.

  • Create Video
  • Image to Video
  • Reference to Video
  • Extend Video
  • Up to 4K
  • 4–15s clips
  • Sound included
  • Start and end frames
  • Up to 9 reference images
  • 6 aspect ratios

Introduction

Seedance 2.0 Video extend continues a clip you already have. Send it as video_url, and add a prompt for what happens next if you want to steer it. The final frame of your clip becomes the opening frame of a new Seedance 2.0 image-to-video shot of 4 to 15 seconds, and the two are joined into one MP4: your original first, then the continuation, with the repeated seam frame removed. The new segment also comes back as its own file, so you can keep extending or edit the pieces separately.

Key features

Continuity comes from the last frame. Wardrobe, set, light and where everyone stands carry over because the new segment literally starts on your final frame. Motion does not carry over the same way: the model sees one still, not the whole clip, so describe the movement you want to continue instead of assuming it will keep its speed or direction.

You choose how it ends. last_image_url is optional: give it and the new segment lands on that image, leave it out and the model decides. The prompt is optional too, so a one-click extend works without writing a word.

One file back, plus the new piece on its own. The first output asset is the joined clip (role video) and the second is the new segment alone (role segment), ready for another extend or for an editor. Sound from your source stays; sound generated for the new segment follows it; a silent side is padded with silence so picture and sound stay in step at the seam.

Everything else is Seedance 2.0 image-to-video.

Request parameters

ParameterRequiredDescription
bitrate_modeNoEncoding bitrate of the delivered file: standard, or high for crisper detail and a larger file. standard · high · Default: standard
duration_secondsNoHow long the clip runs. You pay per second. -1–15 · Default: 5
generate_audioNoAdds sound made to match the picture: voices, ambience and effects. Default: true
last_image_urlNoOptional final frame, so the clip ends exactly where you want.
promptNoWhat happens next: the action that follows, the camera move and the sound. Optional.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 480p · 720p · 1080p · 4k · Default: 720p
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647
video_urlYesThe clip to work on.
watermarkNoAdd the model’s visible "AI generated" watermark to the video. Default: false

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

OptionCredits per second≈ USD
resolution 480p10.5$0.11
resolution 720p22.8$0.23
resolution 1080p56.1$0.56
resolution 4K116.7$1.17

Each task is rounded up to whole credits, so one run at the lowest tier costs 53 credits for a 5-second clip ($0.53).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Lengthen a shot that ended too early: a product turntable that stops before the label faces camera, or a walk that cuts before the subject reaches the door. Extend it by a few seconds and describe only the remaining motion.

Build a longer sequence step by step. Because every step starts from a single frame, watch each seam before stacking the next one.

Prompt guide & pro tips

Describe the next beat, not the whole scene. The frame already fixes who and where, so spend the prompt on the action that follows and the camera move, and name the sound you want. Repeat the camera language your clip ended on, such as a slow push in or a locked shot, so the seam reads as one take.

Trim before you extend. The last frame is the only thing the model sees, so a blurred, mid-cut or heavily compressed ending carries straight into the continuation. Cut your source on a clean, sharp frame first. Sources of up to 60 seconds are accepted as MP4, MOV or WebM.

The framing of the new segment follows the last frame of your clip, so there is no aspect ratio to choose; expect a close match to the source, not a pixel-exact one. If the model returns a noticeably different shape, the new segment is scaled to fill your frame and centered, cropping what spills over.

API quick start

Call the Seedance 2.0 API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
  2. Send the request. POST /jobs/createTask with model bytedance/seedance-2.0/video-extend and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "bytedance/seedance-2.0/video-extend",
  "input": {
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "resolution": "720p",
    "duration_seconds": 5,
    "generate_audio": true
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Seedance 2.0 API questions

How much does the Seedance 2.0 API cost?

Seedance 2.0 starts at 53 credits ($0.53) for a 5-second clip with Extend Video, its cheapest task. Prices by option: 480p 10.5 credits per second, 720p 22.8 credits per second, 1080p 56.1 credits per second, 4K 116.7 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Seedance 2.0 in the API?

Put bytedance/seedance-2.0/text-to-video for Create Video; bytedance/seedance-2.0/image-to-video for Image to Video; bytedance/seedance-2.0/reference-to-video for Reference to Video; bytedance/seedance-2.0/video-extend for Extend Video in the model field of POST /jobs/createTask.

How long can a Seedance 2.0 clip be?

4 to 15 whole seconds, default 5. That is half the ceiling of Seedance 2.5, so if a single take has to run longer than fifteen seconds, either cut shorter takes together or move the job to the 2.5 family.

How many reference images does Seedance 2.0 accept?

Up to 9 on reference-to-video, alongside up to 3 reference videos and 3 reference audio tracks. Three angles of the same subject carry more than nine unrelated frames, and the prompt still has to say which reference is doing what.

Does Seedance 2.0 generate audio?

Yes, in the same pass as the picture. generate_audio defaults to true and produces ambience, movement effects and voice already locked to the frames. Turn it off for silent loops or anything that will be scored later.

Can I reproduce a take exactly?

No. There is no seed field here, and two requests with identical fields come back as different takes. Keep the file you like instead of planning to regenerate it, and judge a prompt change over a couple of runs rather than a single pair.

Can I send both a first and a last frame?

Yes, on image-to-video. last_image_url is accepted only together with image_url, never alone. Two stills give the shot a defined destination, which is what makes transitions, reveals and loops repeatable across runs.

What are the limits of the Seedance 2.0 API?

Clip length: 4–15 s; Resolutions: 480p · 720p · 1080p · 4K; Longest input clip: 60 s. Requests outside these limits are rejected before anything is charged.

Can I try Seedance 2.0 without writing code?

Yes. The Playground runs Seedance 2.0 on your PopNow credits, needs no API key, and shows the matching code for every run.

All Seedance models

Seedance 2.5 runs single takes up to 30 seconds; Seedance 2.0 goes up to 4K but stops at 15 seconds.

More about Seedance 2.0