gaussian-blur — Traditional AI Model
Gaussian blur at full resolution, with kernel size and iteration count under your control — soft backgrounds, redacted faces, or a gentler input downstream. Holds edges better than downsample blur. CPU, instant.
Details
- CategoryTraditional
- Year-1
- License
Inputs & Outputs
- ImageInputimage
Source image to blur
- ImageOutputimage
Gaussian-blurred output image
Parameters
- kernel_sizeintegerdefault 5range 3–15
Gaussian kernel size (3-15)
Size of the Gaussian kernel. Must be odd. Larger values blur over a wider neighborhood — 3 = mild, 9 = strong, 15 = very heavy. Default 5.
- color_multiplierfloatdefault 1range 1–30
Brightness multiplier (1-30)
Multiplies output pixel values to brighten the blurred result. 1.0 (default) preserves brightness; raise it when the blur visibly darkens the image.
- num_iterationintegerdefault 3range 1–10
Iterations (1-10)
Number of times to apply the Gaussian kernel. Each iteration strengthens the blur — 3 (default) produces a moderate effect, 10 a very soft cloud. Cheaper than scaling up kernel size for the same visual blur strength.
Tags
Alternatives in Blur & Effects
- Image Blur (Fast)
Fast blur via downsample-then-upsample.
- Image Blur (Simple)
Single-slider blur (1-10). Fastest blur option.
- Lens Blur
Circular disc-kernel blur for camera-bokeh look.
- Selective Blur
Blur only a drawn region (rect/circle/polygon).