Skip to main content
This node generates a video from a text prompt and optional reference images, videos, and audio using the Wan 3.0 model. Reference media can be combined freely and mentioned in the prompt as @Image1, @Video1, and @Audio1. The node submits the generation request to the Wan API and returns the finished video.

Inputs

Common Inputs

wan3.0-video and wan3.0-video-prime Inputs

Both model options share the same parameter set.

Reference Inputs

Constraints:
  • The prompt must contain at least one non-empty character, or at least one reference image, video, or audio input must be connected.
  • Reference tags in the prompt must match connected inputs. For example, @Image1 refers to the first connected reference image, @Video2 to the second connected reference video, and @Audio1 to the first connected reference audio. Tags are numbered separately per type in input order.
  • Each connected reference image must contain exactly one image, not a batch.
  • Each reference video must be 15 seconds or shorter. The total duration of all reference videos must not exceed 15 seconds.
  • Each reference audio must be 15 seconds or shorter. The total duration of all reference audios must not exceed 15 seconds.
  • When duration is not “auto”, the total duration of all reference videos plus the selected output duration must not exceed 30 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): 09caa8142d71235417a3dfc5676c5f6accc2af1287fad3b7050844dd9453cc64