Generate a silent video guided by start and end images and a motion prompt using Wan 2.2 14B.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Start frame
LoadImage
End frame
LoadImage
Motion and scene
CLIPTextEncode
Video shape
WanFirstLastFrameToVideo
Playback and bit depth
CreateVideo
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Initial sampling
KSamplerAdvanced
Refinement sampling
KSamplerAdvanced
Initial sampling shift
ModelSamplingSD3
Refinement sampling shift
ModelSamplingSD3
Video output
SweetTeaPreviewVideo
Hardware and download-size estimates are not available yet.
Requirements
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Not resolvedText encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged · Wan 2.2 ComfyUI Repackaged
wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged · Wan 2.2 ComfyUI Repackaged
Node pack · GitHub · tea-time-labs/sweet-tea-nodes