Nodes/ComfyUI/WanDancerVideo
ComfyUI Node Runs on cloud

WanDancerVideo

A ComfyUI node in model/conditioning/wan/dancer with 11 inputs and 3 outputs.

By Comfy-Org·Created 4 years ago·Updated 20 days ago· 121,575
WanDancerVideo
  • positive
  • negative
  • vae
  • clip_vision_output
  • clip_vision_output_ref
  • start_image
  • mask
  • audio_encoder_output
  • positive
  • negative
  • latent
width480
height832
length149
Categorymodel/conditioning/wan/dancer

Inputs (11)

NameTypeDefaultDescription
positiveCONDITIONING
negativeCONDITIONING
vaeVAE
widthINT48016–16384
heightINT83216–16384
lengthINT1491–16384The number of frames in the generated video. Should stay 149 for WanDancer.
clip_vision_outputoptCLIP_VISION_OUTPUTThe CLIP vision embeds for the first frame.
clip_vision_output_refoptCLIP_VISION_OUTPUTThe CLIP vision embeds for the reference image.
start_imageoptIMAGEThe initial image(s) to be encoded, can be any number of frames.
maskoptMASKImage conditioning mask for the start image(s). White is kept, black is generated. Used for the local generations.
audio_encoder_outputoptAUDIO_ENCODER_OUTPUT

Outputs (3)

NameTypeDescription
positiveCONDITIONING
negativeCONDITIONING
latentLATENTEmpty latent.