Seedance 2.0 is ByteDance's AI video model — and it handles text, images, video clips, and audio all at once. Feed it your references and a prompt, and it outputs cinematic video with real audio: lip-synced dialogue, background music, ambient sound. No studio, no timeline editor, no waiting list.
Each project accepts up to 12 files: 9 images, 3 video clips (combined ≤15s), and 3 audio files (combined ≤15s). Tag your assets directly in the prompt using @Image1, @Video1, or @Audio1 — the model reads exactly which files you mean.
Videos run from 4 to 15 seconds at up to 4K, in six aspect ratios: 16:9, 9:16, 4:3, 3:4, 21:9, and 1:1. Seedance 2.0 is available online right now — no download, no GPU required.
DeveloperByteDance (Seed Team)
Video length4–15 seconds
Output resolution480p / 720p / 1080p / 4K
Aspect ratios16:9 / 9:16 / 4:3 / 3:4 / 21:9 / 1:1
Reference inputsUp to 12 assets
Input typesText, image, video, audio
Native audioYes — lip sync included
AvailabilityAvailable now