Nodes/WanImageToVideoTiledVAE for ComfyUI/WanPhantomSubjectToVideo (Tiled VAE encode)
ComfyUI Node

WanPhantomSubjectToVideo (Tiled VAE encode)

A ComfyUI node in conditioning/video_models with 12 inputs and 4 outputs.

By stduhpf·Created about a year ago·Updated 10 months ago· 16
WanPhantomSubjectToVideo (Tiled VAE encode)
  • positive
  • negative
  • vae
  • images
  • positive
  • negative_text
  • negative_img_text
  • latent
width832
height480
length81
batch_size1
tile_size512
overlap64
temporal_size64
temporal_overlap8
Categoryconditioning/video_models

Inputs (12)

NameTypeDefaultDescription
positiveCONDITIONING
negativeCONDITIONING
vaeVAE
widthINT83216–16384
heightINT48016–16384
lengthINT811–16384
batch_sizeINT11–4096
tile_sizeINT51264–4096
overlapINT640–4096
temporal_sizeINT648–4096Amount of frames to encode at a time.
temporal_overlapINT84–4096Amount of frames to overlap.
imagesoptIMAGE

Outputs (4)

NameTypeDescription
positiveCONDITIONING
negative_textCONDITIONING
negative_img_textCONDITIONING
latentLATENT