Load Image + Pad 🆎

Loads an image and pads it into an outpaint canvas in one node. Drag any edge of the canvas drawn on the node to set the per-side padding visually; the mask covers exactly the new padding, optionally feathered inward across the seam. The canvas rounds up to a clean multiple, and a megapixel target rescales the source first so the mask seam stays crisp.

By ausboss·Created about a month ago·Updated 7 days ago· 2

Load Image + Pad 🆎

image
mask
width
height
stitcher
reference

◄image▾►

◄pad_left0►

◄pad_top0►

◄pad_right0►

◄pad_bottom0►

◄modecolor►

◄fill_color#808080►

◄backdrop_blur0.50►

◄feather0►

◄canvas_multiple8►

◄target_megapixels0.00►

Category🆎 AusBoss/Image

Inputs (11)

Name	Type	Default	Description
image	COMBO		Choose or upload an image from ComfyUI's input folder.
pad_left	INT	00–16384	Pixels added to the left edge (drag the canvas edge on the node).
pad_top	INT	00–16384	Pixels added to the top edge (drag the canvas edge on the node).
pad_right	INT	00–16384	Pixels added to the right edge (drag the canvas edge on the node).
pad_bottom	INT	00–16384	Pixels added to the bottom edge (drag the canvas edge on the node).
mode	COMBO	color	color = solid fill_color; edge = each side takes the average color of the nearest image edge; edge pixel = the outermost rows and columns smear outward; pillarbox blur = the image itself, stretched to cover the canvas, blurred and dimmed behind the sharp original.
fill_color	STRING	#808080	Padding color for the color mode; accepts #RGB/#RRGGBB hex, R, G, B (0-255 or 0..1 floats), one grayscale number, or a CSS color name. Other modes ignore it.
backdrop_blur	FLOAT	0.500–1	Pillarbox blur only: one knob for how strongly the backdrop is blurred and dimmed; 0 keeps it sharp and full brightness.
feather	INT	00–2048	Ramps the mask inward across the image edge on each padded side so the sampler blends the seam; 0 keeps the seam hard.
canvas_multiple	INT	81–4096	Rounds the final canvas up to this multiple; the remainder joins the right and bottom padding.
target_megapixels	FLOAT	0.000–64	0 = off. Rescales the SOURCE so the padded canvas lands on this many megapixels (then re-rounds to canvas_multiple) — resizing before padding keeps the mask seam crisp.

Outputs (6)

Name	Type	Description
image	IMAGE	The padded image; the original pixels are untouched (resized only when a megapixel target is set).
mask	MASK	White over the new padding, feathered inward per the feather widget — feed it straight to an inpainter as the outpaint mask.
width	INT	Final canvas width after multiple/megapixel rounding.
height	INT	Final canvas height after multiple/megapixel rounding.
stitcher	AUSBOSS_STITCHER	Hand to Stitch Inpaint 🆎 with the sampled result to keep only the new padding and restore the original pixels bit-identically. Also carries where the source sits on the canvas, which Krea 2 Outpaint Model Patch 🆎 reads to place the reference.
reference	IMAGE	The source alone, no padding, fitted to a small multiple of 16 — the reference image for Krea 2 Encode 🆎 and other reference conditioning. Wire it nowhere and nothing is computed.