WanMove motion-guided image to video
Create a motion-guided video from an uploaded image, a scene-and-action prompt, and editable motion paths.
Loading this version’s controls and setup…
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- v0.1.2
- Updated
- Nov 4, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Positive prompt
CLIPTextEncode
Output size
ImageScale
Video and motion guidance
WanMoveTrackToVideo
Motion path 1
GenerateTracks
Turbo mode
PrimitiveBoolean
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Motion path 2
GenerateTracks
Motion path 3
GenerateTracks
Turbo LoRA
LoraLoaderModelOnly
Sampling
KSampler
Standard sampling steps
PrimitiveInt
Standard prompt guidance
PrimitiveFloat
Turbo sampling steps
PrimitiveInt
Turbo prompt guidance
PrimitiveFloat
Sampling shift
ModelSamplingSD3
Video playback
CreateVideo
Video encoding
SweetTeaPreviewVideo
Visual reference
CLIPVisionEncode
What you need
- Model files
- 7.7 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Sweet Tea Preview Video · video
Requirements
Models
5Clip Vision · 1.18 GB · SAFETENSORS · FP16 + I64 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
LoRA · Hugging Face · Kijai/WanVideo_comfy
Text encoder · 6.27 GB · SAFETENSORS · U8 + FP16 + FP32 + FP8 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · 242 MB · SAFETENSORS · BF16 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors
Not resolvedDiffusion model · Hugging Face · Kijai/WanVideo_comfy_fp8_scaled
Node packs
2- Found
Node pack · Unknown
Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 sourceModel artifacts
1 artifact
Model artifacts
1 artifact443411d8-9a48-43fb-a6f8-d81992a25f35-comfy-video-wanmove-480p-draft-0.1.2.tea
tea · 41.7 KB · SHA-256 18b6a3eba68f…f14c
Download file