kanibus

AdvancedTrackingPro

Multi-object tracking with AI refinement

Kanibus · 2 Eingaben · 7 Parameter · 4 Ausgaben

AIDepthControl

Advanced depth estimation using multiple models with intelligent fusion

Kanibus/Depth · 1 Eingabe · 7 Parameter · 3 Ausgaben

BodyPoseEstimator

Full body pose estimation with detailed skeleton tracking

Kanibus · 1 Eingabe · 7 Parameter · 4 Ausgaben

EmotionAnalyzer

Advanced emotion analysis detecting basic emotions and micro-expressions

Kanibus · 2 Eingaben · 6 Parameter · 4 Ausgaben

HandTracking

Advanced hand tracking with gesture recognition

Kanibus · 1 Eingabe · 7 Parameter · 4 Ausgaben

KanibusMaster

Primary orchestrator node integrating all features. Inputs: - inputsource: "image" | "video" | "webcam" - pipelinemode: "realtime" | "batch" | "streaming" | "analysis" - wanversion: "wan2.1" | "wan2.2" | "autodetect" - targetfps: Target processing framerate - Feature enables: enableeyetracking, enabledepthestimation, etc. - Quality settings: trackingquality, temporalsmoothing - ControlNet weights: eyemaskweight, depthweight, etc. Outputs: - kanibusresult: Complete processing result - processedimage: Processed frame - eyemask: Combined eye mask - depthmap: Depth estimation - normalmap: Surface normals - posevisualization: Pose overlay - controlnetconditioning: ControlNet conditions - processingreport: Performance metrics

Kanibus/Master · 2 Eingaben · 20 Parameter

LandmarkPro468

Advanced 468-point facial landmark detection with micro-expression analysis

Kanibus · 1 Eingabe · 8 Parameter · 4 Ausgaben

MultiControlNetApply

Apply multiple ControlNet conditions with proper WAN 2.1/2.2 compatibility

Kanibus/ControlNet · 3 Eingaben · 9 Parameter · 4 Ausgaben

NeuralPupilTracker

Advanced eye tracking with MediaPipe integration. Key Features: - 468-point facial mesh with iris landmarks (468-475) - 6-DOF Kalman filtering for smooth tracking - Blink detection via Eye Aspect Ratio - Saccade detection with velocity thresholds - 3D gaze vector calculation - Pupil dilation measurement Inputs: - image: Input frame - sensitivity: Detection sensitivity (0.1-3.0) - smoothing: Temporal smoothing (0.0-1.0) - blinkthreshold: EAR threshold for blinks - saccadethreshold: Velocity threshold (degrees/second) Outputs: - trackingresult: Complete eye tracking data - annotatedimage: Visualization overlay - gazevisualization: 3D gaze vectors - lefteyemask: Left eye binary mask - righteyemask: Right eye binary mask

Kanibus/Tracking · 2 Eingaben · 8 Parameter · 5 Ausgaben

NormalMapGenerator

Generate surface normal maps from depth maps

Kanibus · 1 Eingabe · 6 Parameter · 3 Ausgaben

ObjectSegmentation

Advanced object segmentation using SAM (Segment Anything Model)

Kanibus · 1 Eingabe · 8 Parameter · 4 Ausgaben

SmartFacialMasking

Intelligent facial masking with semantic segmentation

Kanibus · 2 Eingaben · 9 Parameter · 4 Ausgaben

TemporalSmoother

Temporal smoothing for video consistency

Kanibus/Processing · 2 Eingaben · 7 Parameter · 4 Ausgaben

VideoFrameLoader

Intelligent video processing with caching. Features: - Multiple format support (MP4, AVI, MOV, MKV, WEBM) - Intelligent caching system (memory + disk) - Quality optimization (original/high/medium/low) - Color space conversion (RGB/BGR/GRAY/HSV/LAB) - FPS adjustment and frame stepping - Batch processing with preloading Performance: - 4K video: 15-30 FPS processing - 1080p video: 30-60 FPS processing - 720p video: 60+ FPS processing - Cache hit rate: 85-95% typical

Kanibus/Input · 0 Eingaben · 9 Parameter · 4 Ausgaben