Skip to main content
The Wan Reference to Video node uses the visual appearance and voice from one or more input reference videos, along with a text prompt, to generate a new video. It maintains consistency with the characters from the reference material while creating new content based on your description.

Inputs

Constraints:
  • Each video provided in reference_videos must be between 2 and 30 seconds in duration.
  • The duration parameter is limited to values of 5 or 10 seconds.

Outputs

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 65ca81a7b5e83f8d8f4c00db41e24d5238ef438887362838351464e77a3af0c2