Nano Banana

Seedance 2.0 — Cinematic AI Video with Native Audio by ByteDance

Seedance 2.0 is ByteDance Seed's video model that generates picture and sound together. It handles fast motion, several characters interacting and multi-shot sequences up to 15 seconds. Type a prompt below to try it.

  • ByteDance Seed video model
  • Picture and sound generated together
  • Multi-shot clips up to 15 s
  • Up to 15 reference images
Open the full workspace

More models

Why Seedance 2.0 Is One of the Best AI Video Generators

Seedance 2.0 is built for action and storytelling. Where many video models struggle with fast movement or several people interacting, it keeps motion physical and believable — and it can cut between shots inside one clip.

  • Complex motion

    Dance, sports, fights and chases with physically plausible movement and multiple subjects interacting.

  • Multi-shot storytelling

    Describe several shots in order and get a 15-second sequence that cuts between them.

  • Audio and video together

    Sound is generated jointly with the picture, including stereo ambience and effects. You can also turn it off.

  • Three ways to start

    From text, from a first frame (and optional last frame), or from up to 15 reference images.

What Seedance 2.0 can do

  • Text to video

    Describe the action, camera moves and shot order in plain language.

  • First and last frame

    Upload 1 image as the opening frame, or 2 to set both the start and the end of the clip.

  • Reference images

    Use 1–15 images of characters, products or settings and let the model build a scene around them.

  • Prompt-driven camera

    Ask for dolly-ins, orbits, tracking shots or handheld feel, and the camera follows.

  • 4 to 15 seconds

    Durations of 4, 5, 6, 8, 10, 12 or 15 seconds at 480p, 720p or 1080p.

  • 7 aspect ratios

    21:9, 16:9, 4:3, 1:1, 3:4 and 9:16, or Adaptive to follow your input image.

Use cases

Starting points you can copy into the generator above.

Use caseGood forExample prompt
Dance and sportsFast, energetic motion that stays coherent.

A street dancer performing a breakdance routine in an empty parking garage, spins and freezes, camera circling around her, sneakers squeaking, echoing beat

Multi-shot storiesA short sequence that cuts between several shots.

Shot 1: wide shot of a girl running to catch a bus in the rain. Shot 2: close-up of her hand slapping the closing door. Shot 3: the driver smiles and opens it again. Warm cinematic tones, rain and engine sounds

Product videos from referencesBuild a product scene from a few photos.

The smartwatch from the reference images rotates slowly on a floating glass platform, light sweeps across the screen, it lands on a wrist, clean studio, subtle electronic sound

Start-to-end transitionsSet the first and last frame and let the model fill the motion in between.

Smooth transition from the empty room in the first frame to the fully furnished room in the last frame, furniture sliding into place, timelapse feel

Character interactionSeveral characters acting together in one scene.

Two kids and a golden retriever playing tug-of-war with a rope on a sunny lawn, the dog wins and runs off, laughter and barking, handheld camera

Cinematic widescreen21:9 shots for trailers and title sequences.

21:9 tracking shot of a lone rider on horseback crossing a desert at golden hour, dust trailing behind, wind and hoofbeats, epic film score feel

Seedance 2.0 in 3 steps

  1. 1

    Write the action or add images

    Describe the shots in order, or switch to first/last frame (1–2 images) or reference mode (1–15 images).

  2. 2

    Pick duration, resolution and format

    Choose 4–15 seconds, 480p to 1080p, an aspect ratio and whether to generate audio. The credit cost is shown before you submit.

  3. 3

    Generate and keep your video

    Videos take a few minutes and are saved to My works. If a video fails, its credits are refunded automatically.

X Posts About Seedance 2.0 — Cinematic AI Video with Native Audio by ByteDance

YouTube Videos About Seedance 2.0 — Cinematic AI Video with Native Audio by ByteDance

Frequently asked questions

Dynamic scenes: complex motion, several subjects interacting, prompt-controlled camera moves and multi-shot sequences up to 15 seconds, with sound generated together with the picture.

Ready for Smooth Motion with Seedance 2.0?

Fluid camera and character motion in 1080p, guided by images, video and audio references.

Explore All Models
  • Clips up to 15s
  • Native audio
  • Failed outputs refunded