ComfyUI Node: Wan VACE → Video (hybrid subject swap)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
conditioning/video_models
Inputs
positive CONDITIONING
negative CONDITIONING
vae VAE
width INT
height INT
length INT
batch_size INT
strength FLOAT
control_strength FLOAT
reference_strength FLOAT
source_luma_strength FLOAT
source_detail_strength FLOAT
background_preserve_strength FLOAT
mask_feather_px FLOAT
control_video IMAGE
source_video IMAGE
control_masks MASK
reference_image IMAGE
Outputs
CONDITIONING
CONDITIONING
LATENT
INT
Extension: sweet-tea-nodes
Advanced ComfyUI node pack: seam-locked pose tiled upscaling and cap-based temporal stitch inpainting for WAN VACE.
Authored by tea-time-labs
Looking for a different node?
More nodes in sweet-tea-nodes
Other conditioning/video_models nodes
- AddNoiseToTrackPath
- WAN Three Frame To Video (Badman)
- Bernini Prompt Enhancer
- Bernini Prompt Result Parser
- Boyo Painter SVI (Motion + Infinite Length)
- GetTrackRange
- 🅛🅣🅧 LTXV Add Guide Advanced
- 🅛🅣🅧 LTXV Add Guide Advanced Attention
- LTX Video Context (TTP)
- LTX First Last Frame Control (TTP)
- 🅛🅣🅧 LTXV Img To Video Advanced
- 🅛🅣🅧 LTXV Img To Video Condition Only
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.