Seedance 2.0 Model Introduction

Seedance 2.0 supports four input modalities — images, videos, audio, and text — for richer expression and more controllable generation. Use an image to set the visual style, a video to specify character actions and camera movements, a few seconds of audio to set the rhythm and mood… combined with text prompts, the creation process becomes more natural, efficient, and truly director-like.

Current web app availability

seedance2.app currently exposes text-to-video and image-to-video. Seedance 2.0 is a paid upgrade, and current public outputs top out at 720p and 15 seconds. Some pages below describe broader model workflows or prompt ideas that are not fully available in the web app today.

Core Parameters

  • Image input: up to 9 images, formats jpeg/png/webp/bmp/tiff/gif, max 30MB each
  • Video input: up to 3 videos, total duration 2-15s, formats mp4/mov, max 50MB each, resolution 409600-927408
  • Audio input: up to 3 audio files, max 15s duration, formats mp3/wav, max 15MB each
  • Text input: natural language prompts, generation length freely adjustable from 4-15 seconds
  • Mixed input limit of 12 files total. Prioritize uploading materials that have the greatest impact on visuals or rhythm