Nodes/IAMCCS-nodes/IAMCCS WanAnimate Extends
ComfyUI Node

IAMCCS WanAnimate Extends

IAMCCS WanAnimate long-video wrapper. It runs WanAnimateToVideo + KSampler + VAE decode in chunks, uses the previous visible tail as continue_motion, trims native latent/image anchors, and can grade only the first boundary frames of each joined chunk.

By IAMCCS·Created 10 months ago·Updated about a month ago· 109
IAMCCS WanAnimate Extends
  • model
  • positive
  • negative
  • vae
  • clip_vision_output
  • reference_image
  • face_video
  • pose_video
  • background_video
  • character_mask
  • images
  • frame_count
  • source_frames
  • trimmed_frames
  • chunk_plan
width832
height480
target_frames0
first_chunk_length81
next_chunk_length77
continue_motion_max_frames5
batch_size1
seed0
seed_modefixed
steps6
cfg1.0
sampler_nameeuler
schedulersimple
denoise1.00
continuity_profileiamccs_boundary_ramp
color_methodreinhard_lab
boundary_frames8
boundary_strength0.35
live_chunk_previewmiddle_frame
empty_cache_each_chunkfalse
CategoryIAMCCS/video/WanAnimate

Inputs (30)

NameTypeDefaultDescription
modelMODEL
positiveCONDITIONING
negativeCONDITIONING
vaeVAE
widthINT83216–8192
heightINT48016–8192
target_framesINT00–1000000 = infer from pose/background/face/mask frame count.
first_chunk_lengthINT815–1024
next_chunk_lengthINT775–1024Matches the common WanAnimate loop math: 77 length with 5 continue frames contributes 72 visible frames.
continue_motion_max_framesINT51–129
batch_sizeINT11–64
seedINT00–18446744073709550000
seed_modeCOMBOfixed2 options: fixed, increment
stepsINT61–10000
cfgFLOAT1.00–100
sampler_nameCOMBOeuler44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
schedulerCOMBOsimple9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
denoiseFLOAT1.000–1
continuity_profileCOMBOiamccs_boundary_rampboundary_ramp only color matches the first frames after a chunk seam.
color_methodCOMBOreinhard_lab3 options: reinhard_lab, mkl_lab, histogram
boundary_framesINT81–96
boundary_strengthFLOAT0.350–1
live_chunk_previewSTRINGmiddle_frameoff, first_frame, middle_frame, last_frame. Stale numeric values are treated as middle_frame.
empty_cache_each_chunkBOOLEANfalse
clip_vision_outputoptCLIP_VISION_OUTPUT
reference_imageoptIMAGE
face_videooptIMAGE
pose_videooptIMAGE
background_videooptIMAGE
character_maskoptMASK

Outputs (5)

NameTypeDescription
imagesIMAGE
frame_countINT
source_framesINT
trimmed_framesINT
chunk_planSTRING