Skip to main content

Seedance 2.5 Flash video edit is ByteDance's instruction-editing endpoint: send a 4–30 second clip and a text prompt, and it returns the clip re-rendered at 480p or 720p with the change applied while the performers, their movement and the camera stay as in the source. Turn generate_audio off to keep your clip's own soundtrack.

From $0.18/s

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Output5s
    balcony-rainy-neon-red-dress

    The source was a 1280×720 daytime balcony clip of 4.958 seconds made with this model's text-to-video, plus one 864×1152 product photo of a red satin dress as @Image 1. With generate_audio on at 720p, the result was 1280×720 and 4.736 seconds: a night sky, falling rain and a pink-blue neon glow replaced the afternoon, her white sundress became the red satin dress from the photo, and both people, the glasses, the clink and her head on his shoulder kept their timing. A new track of rain and her laugh replaced the source sound; the reference image did not change the price, and the source was billed as 5 seconds.

    • 720p
    • audio
  • Output4s
    tram-street-snowfall-voice

    The same four-second clip and edit with a voice file as @Audio 1 and generate_audio on. The result ran 3.712 s with a new soundtrack and the same edit quality; the source was still billed as 4 seconds.

    • 480p
    • audio
  • Output4s
    tram-street-snowfall

    A four-second sunny street at 480p with generate_audio off. The result was 854×480 and exactly 4.000 s: both riders, the tram and the camera move matched the source frame by frame, with just weather and light changed, and the original soundtrack remained.

    • 480p

This example starts at $0.18 per output second. The Playground updates the estimate when you change the settings.