Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Generate a short, silent video transition between a first image and a last image, guided by a motion prompt. Both images are required. Wan 2.1 VACE conditions the endpoints; it does not guarantee pixel-exact reproduction. Uploaded alpha masks are not used.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
First frame
LoadImage
Last frame
LoadImage
Motion prompt
CLIPTextEncode
Output width
PrimitiveInt
Output height
PrimitiveInt
Video length
PrimitiveInt
Lightning mode
PrimitiveBoolean
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Frame guidance
WanVaceToVideo
Lightning strength
LoraLoaderModelOnly
Sampling
KSampler
Standard steps
PrimitiveInt
Standard guidance
PrimitiveFloat
Lightning steps
PrimitiveInt
Lightning guidance
PrimitiveFloat
Playback
CreateVideo
Noise schedule
ModelSamplingSD3
Video encoding
SweetTeaPreviewVideo
Hardware and download-size estimates are not available yet.
Requirements
LoRA · Hugging Face · Kijai/WanVideo_comfy
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Not resolvedText encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
wan2.1_vace_14B_fp16.safetensors
Not resolvedCheckpoint · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Node pack · GitHub · tea-time-labs/sweet-tea-nodes
