Reference to Video

Upload reference images, videos, and voice — WAN 2.7 generates a consistent video matching all your references.

Model

Reference Images (0/5 total refs: 0)

+ Image

or select from my creations

Reference Videos (optional)

+ Video

or select from my videos

Voice (optional, 1-10s)

+ Voice

First Frame (optional)

Frame

··200 credits

Input: 4 Reference Images

Ref 1

Ref 2

Ref 3

Ref 4

Prompt

"A group of friends having a picnic in a sunlit meadow, laughing and sharing food, warm golden hour lighting, cinematic wide shot."

Output

WAN 2.7 R2V used 4 reference images to generate a new scene with consistent style and characters

HOW IT WORKS

Three simple steps

Upload up to 5 reference images and videos. Add a voice clip to drive audio. Optionally set a first frame.

Write a prompt describing the scene. The AI will maintain character consistency and style from your references.

WAN 2.7 combines all references into a coherent video that matches your prompt and maintains visual consistency.