Nodes/ComfyUI-WanAnimatePlus/WanAnimatePlus ContextOptions
ComfyUI Node

WanAnimatePlus ContextOptions

Context options for WanVideo, allows splitting the video into context windows and attemps blending them for longer generations than the model and memory otherwise would allow.

By wuwukaka·Created 3 months ago·Updated 22 days ago· 402
WanAnimatePlus ContextOptions
  • reference_latent
  • context_options
context_schedule
context_frames81
context_stride4
context_overlap16
freenoisetrue
verbosefalse
fuse_methodlinear
CategoryWanAnimatePlus

Inputs (8)

NameTypeDefaultDescription
context_scheduleCOMBO3 options: uniform_standard, uniform_looped, static_standard
context_framesINT812–1000Number of pixel frames in the context, NOTE: the latent space has 4 frames in 1
context_strideINT44–100Context stride as pixel frames, NOTE: the latent space has 4 frames in 1
context_overlapINT164–100Context overlap as pixel frames, NOTE: the latent space has 4 frames in 1
freenoiseBOOLEANtrueShuffle the noise
verboseBOOLEANfalsePrint debug output
fuse_methodoptCOMBOlinearWindow weight function: linear=ramps at edges only, pyramid=triangular weights peaking in middle
reference_latentoptLATENTImage to be used as init for I2V models for windows where first frame is not the actual first frame. Mostly useful with MAGREF model

Outputs (1)

NameTypeDescription
context_optionsWANVIDCONTEXT