Nodes/VRGameDevGirl Video Enhancement Nodes/Face Fix - Prepare Full Face Video (Shot Aware)
ComfyUI Node

Face Fix - Prepare Full Face Video (Shot Aware)

Prepares every frame as a shot-aware 512px face video for LTX; no legacy Z-Image anchor controls.

By vrgamegirl19·Created about a year ago·Updated about 17 hours ago· 662
Face Fix - Prepare Full Face Video (Shot Aware)
  • video_frames
  • face_video_512
  • face_fix_context
detection_confidence0.40
crop_padding0.08
minimum_face_pixels12
rotation_assistOff (fastest)
short_gap_tracking2
cut_sensitivity0.15
crop_smoothing0.85
CategoryVRGameDevGirl/Face Fix

Inputs (8)

NameTypeDefaultDescription
video_framesIMAGEComplete input video frame sequence.
detection_confidenceFLOAT0.400.05–0.95Minimum face detector confidence.
crop_paddingFLOAT0.080–0.5Extra space around each detected face crop.
minimum_face_pixelsINT124–2048Minimum detected face size before it is rejected.
rotation_assistCOMBOOff (fastest)Optional rotated detection for tilted faces.
short_gap_trackingINT20–12Frames to bridge when detection briefly misses a face.
cut_sensitivityFLOAT0.150.05–0.95Hard-cut threshold; lower values detect subtler cuts.
crop_smoothingFLOAT0.850–0.95Stabilizes crop position and size within each shot.

Outputs (2)

NameTypeDescription
face_video_512IMAGE
face_fix_contextVRGDG_FACE_FIX_CONTEXT