Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

Seedance 2.0 Multi Reference To VideoMulti-Reference Video Control

Try Seedance 2.0 Multi Reference To VideoAPI Documentation

Control Motion. Lock Characters.

Multimodal Inputs

Combine Images Videos Audio

Use up to 9 images, 3 videos, 3 audio files with text in Seedance 2.0 Multi Reference To Video API.

Role Tagging

@Mentions Assign Roles

Tag assets with @Image1 for first frame or @Video1 for motion in seedance 2.0 multi reference to video model.

Native Audio

Sync Audio Video

Generate lip-synced dialogue and beat-aware music in one pass with Seedance 2.0 Multi Reference To Video.

Examples

See what Seedance 2.0 Multi Reference To Video can create

Copy any prompt below and try it yourself in the playground.

City Flyover

“Cinematic drone shot over futuristic city skyline at dusk, follow @Video1 camera path exactly, golden hour lighting from @Image1, ambient city hum synced to @Audio1 rhythm, 1080p, smooth transitions.”

Product Reveal

“Slow rotating reveal of metallic gadget on dark table, replicate @Video1 pan and zoom motion, product texture from @Image1, subtle electronic beat from @Audio1, high detail, 15 seconds.”

Ocean Waves

“Waves crashing on rocky shore during storm, match @Video1 wave motion and splash physics, moody blue tones from @Image1, thunder rumble synced to @Audio1, dynamic camera, 1080p.”

Abstract Flow

“Fluid geometric shapes morphing in space, copy @Video1 transition effects and speed, color palette from @Image1, pulsating synth from @Audio1, seamless loop, high resolution.”

For Developers

A few lines of code.
Videos from references. One call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/image-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "In a frozen, ancient Nordic valley, the shamanic warrior—cloaked in fur, wearing a skull mask with curled horns—stands at the edge of a glacier lake. The wind howls violently, whipping up snow around him as he slams his staff into the icy ground, causing the earth to tremble. Blue runes glow across his mask as magic awakens. A storm brews above as shadowy enemies rise from the snow-covered mountains and saying seedance 2.0 model is now live on Modelslab",
  "duration": "5",
  "init_audio": "https://assets.modelslab.ai/generations/ca8c4c05-c979-4c6c-bc6b-be161ddab2cb.mp3",
  "init_image": "",
  "init_video": "",
  "resolution": "720p",
  "aspect_ratio": "21:9"
}
)
print(response.json())

FAQ

Common questions about Seedance 2.0 Multi Reference To Video

Read the docs

Ready to create?

Start generating with Seedance 2.0 Multi Reference To Video on ModelsLab.

Try Seedance 2.0 Multi Reference To VideoAPI Documentation