Skip to main content
This node scales the input image to an optimal size used during Flux Kontext model training using the Lanczos algorithm, based on the input image’s aspect ratio. This node is particularly useful when inputting large-sized images, as oversized inputs may lead to degraded model output quality or issues such as multiple subjects appearing in the output.

Inputs

Parameter NameData TypeInput TypeDefault ValueValue RangeDescription
imageIMAGERequired--Input image to be resized

Outputs

Output NameData TypeDescription
imageIMAGEResized image

Preset Size List

The following is a list of standard sizes used during model training. The node will select the size closest to the input image’s aspect ratio:
WidthHeightAspect Ratio
67215680.429
68815040.457
72014560.494
75213920.540
80013280.603
83212480.667
88011840.743
94411040.855
102410241.000
11049441.170
11848801.345
12488321.500
13288001.660
13927521.851
14567202.022
15046882.186
15686722.333