Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Animate a reference character using motion from a driving video, with text control over appearance and background.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Reference character
LoadImage
Driving video
LoadVideo
Appearance and background
CLIPTextEncode
Motion
CLIPTextEncode
Output size
ResizeImageMaskNode
Motion transfer
WanAnimate2ToVideo
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Context windows
ComfySwitchNode
Context window tuning
ContextWindowsManual
Sampling
SamplerCustom
Sampling schedule
BasicScheduler
Sampler
KSamplerSelect
Sampling shift
ModelSamplingSD3
Frame trimming
PrimitiveBoolean
Distillation LoRA
LoraLoaderModelOnly
Video output
SweetTeaPreviewVideo
Hardware and download-size estimates are not available yet.
Requirements
Vision model · Hugging Face · Comfy-Org/Wan-Animate-2 · Wan Animate 2
LoRA · Hugging Face · Comfy-Org/Wan-Animate-2 · Wan Animate 2
umt5_xxl_fp8_e4m3fn_scaled.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/Wan-Animate-2 · Wan Animate 2
wan_animate_2_int8_convrot.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Wan-Animate-2 · Wan Animate 2
VAE · Hugging Face · Comfy-Org/Wan-Animate-2 · Wan Animate 2
Node pack · GitHub · tea-time-labs/sweet-tea-nodes
