Wan 2.2 controlled video · Standard
Generate a silent video guided by uploaded control footage and a scene-and-motion prompt using Wan 2.2 14B Fun Control. This standard branch uses high-noise and low-noise models across a coordinated 20-step schedule; the separate four-step sibling uses Lightx2v LoRAs.
Workflow details
Workflow details
Perfil de ejecución
- Publicador
- Sweet Tea Automation
- Estado
- Publicado
- Versión
- Checking published version…
- Actualizado
- 23 oct 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Control video
LoadVideo
Reference image
LoadImage
Positive prompt
CLIPTextEncode
Output size and length
Wan22FunControlToVideo
Video playback
CreateVideo
Canny edge extraction
Canny
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Initial sampling
KSamplerAdvanced
Refinement sampling
KSamplerAdvanced
Initial schedule shift
ModelSamplingSD3
Refinement schedule shift
ModelSamplingSD3
Video Output
SweetTeaPreviewVideo
What you need
Hardware and download-size estimates are not available yet.
Output
- Sweet Tea Preview Video · video
Requisitos
Modelos
4umt5_xxl_fp8_e4m3fn_scaled.safetensors
No resueltoText encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
- No resuelto
VAE · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
wan2.2_fun_control_high_noise_14B_fp8_scaled.safetensors
Archivo sin verificarCheckpoint · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged · Wan 2.2 ComfyUI Repackaged
wan2.2_fun_control_low_noise_14B_fp8_scaled.safetensors
Archivo sin verificarCheckpoint · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged · Wan 2.2 ComfyUI Repackaged
Paquetes de nodos
1- Encontrado
Paquete de nodos · GitHub · tea-time-labs/sweet-tea-nodes
Fuentes
1 fuente
Fuentes
1 fuente