Wan 2.2 four-step frame-to-video
Generate a silent video from a scene and motion prompt, optionally guided by a start image, an end image, or both.
Workflow details
Workflow details
Profil d'exécution
- Éditeur
- Sweet Tea Automation
- Statut
- Présenté
- Version
- Checking published version…
- Mis à jour
- 23 oct. 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Start image
LoadImage
End image
LoadImage
Scene and motion
CLIPTextEncode
Video shape
WanFunInpaintToVideo
Video playback
CreateVideo
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Initial sampling
KSamplerAdvanced
Refinement
KSamplerAdvanced
Initial sampling schedule
ModelSamplingSD3
Refinement sampling schedule
ModelSamplingSD3
Initial acceleration
LoraLoaderModelOnly
Refinement acceleration
LoraLoaderModelOnly
Video output
SweetTeaPreviewVideo
What you need
- Model files
- 2.3 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Sweet Tea Preview Video · video
Exigences
Modèles
6umt5_xxl_fp8_e4m3fn_scaled.safetensors
Non résoluText encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
- Non résolu
VAE · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
wan2.2_fun_inpaint_high_noise_14B_fp8_scaled.safetensors
Fichier non vérifiéCheckpoint · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged · Wan 2.2 ComfyUI Repackaged
wan2.2_fun_inpaint_low_noise_14B_fp8_scaled.safetensors
Fichier non vérifiéCheckpoint · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged · Wan 2.2 ComfyUI Repackaged
LoRA · 1.14 GB · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
LoRA · 1.14 GB · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
Packs de nœuds
1Pack de nœud · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source