Seedance 2.0
ByteDance's most capable video model — accepts up to 12 reference files simultaneously with native 2K output and director-level camera control.
- Max Duration
- 15 seconds max
- Resolution
- 720p, 1080p, 2K
- Aspect Ratios
- 16:9, 9:16, 1:1
- Audio
- Native audio
What makes Seedance 2.0 unique
Richest multi-modal input of any model
up to 9 reference images, 3 video clips, and 3 audio tracks simultaneously
Native 2K resolution output (2048x1080 or 1080x2048)
Director-level camera control and cinematic shot composition
Realistic physics simulation
collisions with weight, fabric tearing, believable action sequences
30% faster generation than Seedance 1.5 Pro
Native CapCut integration
the same engine behind TikTok's video tools
Best for
Prompt tips
- 1.
Use multiple reference images for consistent character identity across shots.
- 2.
Specify camera movements explicitly — Seedance 2.0 follows director-style instructions well.
- 3.
Include audio cues in your prompt for synchronized sound design.
- 4.
For action scenes, describe physics and weight to leverage its realistic simulation engine.
How Seedance 2.0 works
Seedance 2.0 uses a Diffusion Transformer (DiT) architecture that replaces the traditional U-Net backbone with a transformer for better scalability. It features a unified multimodal audio-video joint generation system that processes reference images, video clips, and audio tracks together to produce cinematic output with synchronized sound.
How to use on Flashloop
Select Seedance 2.0
Open Flashloop and choose Seedance 2.0 from the model selector in the video creator.
Write your prompt
Describe what you want to see in your video — be as detailed as you like.
Generate & download
Hit generate and your video will be ready in seconds. Download or share directly.
Frequently asked questions
Seedance 2.0 supports native 2K output, accepts up to 12 reference files simultaneously, has director-level camera control, and is 30% faster than 1.5 Pro.
Yes. It uses a unified multimodal system that generates synchronized audio and video together, not sequentially.
You can combine up to 9 reference images, 3 video clips, and 3 audio tracks in a single generation.
Yes. Its high resolution output, camera control, and CapCut integration make it well suited for advertising and film production workflows.
Other video models
View all →Veo 3
Generate 8-second videos with native dialogue, sound effects, and ambient audio in one pass.
Kling 3.0
Create up to 15-second multi-shot videos with character consistency, 4K 60fps support, and bilingual audio.
Kling 2.6
Turn images into 10-second 1080p videos with 48fps motion control and native speaking, singing, or rapping audio.
Ready to create with Seedance 2.0?
Available on iOS, Android, and web.
Start Creating