Edge Detect

Filter

Extracts edges from an image using the Canny algorithm. Useful for creating line art, masks, or AI conditioning.

Edge Detect applies the Canny edge detection algorithm to find edges in an image. It outputs a binary image where white pixels mark detected edges. The two thresholds control sensitivity: the low threshold catches weak edges, the high threshold catches strong edges.

This node is commonly used to create line art from photographs, generate masks for compositing, or prepare reference images for AI image editing.

Parameters

Filter

Low ThresholdNumber

Default: 50.0 Range: 0–1000

Lower Canny threshold; below this rejected as non-edges

High ThresholdNumber

Default: 150.0 Range: 0–1000

Upper Canny threshold; above this accepted as edges

ApertureChoice

Default: 3

Sobel kernel size; larger=broader, smoother edges

• 3Smallest kernel — detects fine, detailed edges. May be noisy.
• 5Medium kernel — balanced between detail and smoothness.
• 7Largest kernel — detects broader, smoother edges. Less noise.

L2 GradientToggle

Default: false

Use L2 norm for more accurate gradient magnitude

Pre-BlurToggle

Default: false

Gaussian blur before detection to reduce noise

Blur KernelInteger

Default: 3 Range: 3–41

Pre-blur kernel size (must be odd)

InvertToggle

Default: false

Swap edges and background

Color

Edge ColorColor (RGBA)

Default: rgba(255, 255, 255, 255)

Edge pixel color

BackgroundColor (RGBA)

Default: rgba(0, 0, 0, 0)

Background pixel color

Notes

Blur Kernel only visible when Pre-Blur is enabled.

Usage Tips

• Enable Pre-Blur to reduce noise before detection, producing cleaner edges with fewer false positives.
• Lower thresholds detect more edges (including noise); higher thresholds detect only strong edges.
• Use custom edge and background colors to create colored line art.
• Wire Edge Detect output into AI Image Edit as a reference for structure-guided generation.

Related Nodes

• Blur
• AI Image Edit
• Emboss