Animate a reference character using motion poses from a source video, producing one animation assembled from five sequential generated segments. Provide a character reference image and a motion video file path accessible to the execution runtime. The image supplies appearance, reference pose and an automatic caption; the video supplies motion poses. Source audio and uploaded image transparency are not used.
Bring this Pipe into Studio
Add to Studio uses this exact version. New releases do not replace a saved copy automatically.
Workflow details
Perfil de execução
Fontes
1 fonteHover nodes for Pipe controls
Core
Primary Pipe surface
Motion source
VHS_LoadVideoPath
Character reference
LoadImage
Positive prompt
StringFunction|pysssss
Negative prompt
WanVideoTextEncode
Output width
JWInteger
Output height
JWInteger
Frame rate
Float
Video output
SweetTeaPreviewVideoFromImages
Extended
Additional surfaced controls
Segment length
JWInteger
Segment overlap
JWInteger
Reference framing
ImageResizeKJv2
Motion framing
ImageResizeKJv2
Character guidance
WanVideoAddOneToAllReferenceEmbeds
Motion pose components
MimicMotionGetPoses
Reference pose components
MimicMotionGetPoses
Segment 1 pose guidance
WanVideoAddOneToAllPoseEmbeds
Segment 2 pose guidance
WanVideoAddOneToAllPoseEmbeds
Segment 3 pose guidance
WanVideoAddOneToAllPoseEmbeds
Segment 4 pose guidance
WanVideoAddOneToAllPoseEmbeds
Segment 5 pose guidance
WanVideoAddOneToAllPoseEmbeds
Sampling
JWInteger
Segment 1 sampling
WanVideoSampler
Segment 2 sampling
WanVideoSampler
Segment 3 sampling
WanVideoSampler
Segment 4 sampling
WanVideoSampler
Segment 5 sampling
WanVideoSampler
Automatic caption
Florence2Run
Distillation LoRA
WanVideoLoraSelect
Segment 2 continuation context
WanVideoEncode
Segment 2 motion window
WanVideoAddOneToAllExtendEmbeds
Segment 3 continuation context
WanVideoEncode
Segment 3 motion window
WanVideoAddOneToAllExtendEmbeds
Segment 4 continuation context
WanVideoEncode
Segment 4 motion window
WanVideoAddOneToAllExtendEmbeds
Segment 5 continuation context
WanVideoEncode
Segment 5 motion window
WanVideoAddOneToAllExtendEmbeds
Remaining hardware or download-size estimates are not available yet.
Requisitos
LoRA · 601 MB · SAFETENSORS · Unknown
Vision model · Hugging Face · microsoft/Florence-2-base
One-to-All-14b-Q4_K_M.gguf
Não resolvidoCheckpoint · Unknown
umt5-xxl-enc-bf16.safetensors
Não resolvidoText encoder · Unknown
wan_2.1_vae.safetensors
Arquivo não verificadoVAE · Unknown
ComfyLiterals
EncontradoPacote de nós · Registry
ComfyUI_Comfyroll_CustomNodes
EncontradoPacote de nós · Registry
comfyui-custom-scripts
EncontradoPacote de nós · Registry
comfyui-florence2
PossívelPacote de nós · Registry
Pacote de nós · Registry
comfyui-mimicmotionwrapper
EncontradoPacote de nós · Registry
comfyui-various
EncontradoPacote de nós · Registry
comfyui-videohelpersuite
EncontradoPacote de nós · Registry
ComfyUI-WanVideoWrapper
EncontradoPacote de nós · Registry
rgthree-comfy
EncontradoPacote de nós · Registry
Pacote de nós · GitHub · tea-time-labs/sweet-tea-nodes