Introduction
Seedance 2.0 generates cinematic HD video up to 15 seconds long with consistent characters, precise motion control, and multi-modal input.
How to get started
From the homepage, click Generative models → See all → select Seedance 2.0
Upload a reference image, video, or audio, or start from a text prompt alone
Enter a detailed description of your scene
Select your resolution and duration, confirm the credit cost, and generate
Download your video, watermark free on all paid plans
Spec information
Minimum duration | 4 seconds |
Maximum duration | 15 seconds |
Resolution | 480p – 1080p |
Aspect ratios | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
Input types | Text, image, video, audio |
Prompt best practices
Seedance 2.0 responds well to structured, specific prompts. A strong prompt typically covers:
Shot type → Subject → Action → Environment → Lighting → Style
Example: Bright sunny afternoon on a tree-lined city sidewalk. Golden light filters through leaves, creating warm, dappled highlights. Soft bokeh of pedestrians and storefronts. Dry, warm tone.
💡 Tips for better results | Why it helps |
Be explicit about camera movement - dolly in, tracking shot, wide pan, bird's eye | Seedance reads motion direction directly from the prompt |
Describe lighting specifically - "golden hour backlight" or "soft studio rim light" | Gives the model a visual anchor to work from |
Keep character descriptions in the first prompt | Seedance uses this as its consistency reference across the generation |
For video references, prompt only for what changes | Describe the new subject and environment - not the motion itself |
Content restrictions
Seedance 2.0 has restrictions on realistic human faces in input images and videos. If your reference contains a clearly visible face, the generation is likely to be blocked by the provider. To work around this, use obscured or blurred faces in reference inputs, or switch to an illustrated or 3D rendered style for character references.