This article introduces how to complete Wan VACE video generation examples in ComfyUI
Model | 480P | 720P |
---|---|---|
VACE-1.3B | ✅ | ❌ |
VACE-14B | ✅ | ✅ |
Load Diffusion Model
node has loaded wan2.1_vace_14B_fp16.safetensors
Load CLIP
node has loaded umt5_xxl_fp8_e4m3fn_scaled.safetensors
or umt5_xxl_fp16.safetensors
Load VAE
node has loaded wan_2.1_vae.safetensors
Mode
-> Always
to switch to Always modeBypass
option to toggle the Bypass statusCLIP Text Encode (Positive Prompt)
nodeCLIP Text Encode (Negative Prompt)
nodeWanVaceToVideo
Run
button or use the shortcut Ctrl(cmd) + Enter
to execute video generationComfyUI/output/video
directory (subfolder location depends on save video
node settings)Load image
node in Load reference image and input your image. You can also use the image below - in this file we’ve already set up the corresponding parameters.
Load image
nodeWanVaceToVideo
Run
button or use the shortcut Ctrl(cmd) + Enter
to execute video generationComfyUI/output/video
directory (subfolder location depends on save video
node settings)Load Image
node under Load reference image
Load Video
node under Load control video
. Since the provided video is preprocessed, no additional processing is neededImage preprocessing
group or use comfyui_controlnet_aux
nodes to complete the preprocessingWanVaceToVideo
Run
button or use the shortcut Ctrl(cmd) + Enter
to execute video generationComfyUI/output/video
directory (subfolder location depends on save video
node settings)length
setting must satisfy that length-1
is divisible by 4.
The corresponding Batch_size
setting must satisfy Batch_size = length - 2