Generate a silent, prompt-guided video conditioned on an uploaded source video using the fixed Wan 2.1 VACE 14B model.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Source video
LoadVideo
Video prompt
CLIPTextEncode
Reference image
LoadImage
Video dimensions and conditioning
WanVaceToVideo
Video playback
CreateVideo
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Edge guidance
Canny
CausVid LoRA
LoraLoader
Sampling
KSampler
Sampling shift
ModelSamplingSD3
Video Output
SweetTeaPreviewVideo
Hardware and download-size estimates are not available yet.
Requirements
Text encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
wan2.1_vace_14B_fp16.safetensors
Not resolvedCheckpoint · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Wan21_CausVid_14B_T2V_lora_rank32.safetensors
Not resolvedLoRA · Hugging Face · Kijai/WanVideo_comfy
Node pack · GitHub · tea-time-labs/sweet-tea-nodes