PatchModelAddDownscale - ComfyUI Built-in Node Documentation

PatchModelAddDownscale (Kohya Deep Shrink) applies the Kohya Deep Shrink technique to a model by shrinking intermediate features at a chosen block and then scaling them back to the

PatchModelAddDownscale (Kohya Deep Shrink) applies the Kohya Deep Shrink technique to a model by shrinking intermediate features at a chosen block and then scaling them back to their original size. The shrinking only happens during a selected part of the denoising process, which can reduce processing cost while keeping the final result close to the original.

Inputs

Parameter	Description	Data Type	Required	Range
model	The model to apply the downscale patch to	MODEL	Yes	-
block_number	The specific block number where downscaling will be applied (default: 3)	INT	Yes	1-32
downscale_factor	The factor by which to downscale the features (default: 2.0)	FLOAT	Yes	0.1-9.0
start_percent	The starting point in the denoising process where downscaling begins (default: 0.0)	FLOAT	Yes	0.0-1.0
end_percent	The ending point in the denoising process where downscaling stops (default: 0.35)	FLOAT	Yes	0.0-1.0
downscale_after_skip	Whether to apply downscaling after skip connections (default: True)	BOOLEAN	Yes	-
downscale_method	The interpolation method used for downscaling operations (default: “bicubic”)	COMBO	Yes	”bicubic" "nearest-exact" "bilinear" "area" "bislerp”
upscale_method	The interpolation method used for upscaling operations (default: “bicubic”)	COMBO	Yes	”bicubic" "nearest-exact" "bilinear" "area" "bislerp”

The downscale patch is applied only when the current denoising step falls within the range defined by start_percent and end_percent, and only at the block selected by block_number. When downscale_after_skip is enabled, the patch is applied after the skip connection; when disabled, it is applied before the skip connection. Features are scaled back up to their original size afterwards, but only when the current feature size no longer matches the size recorded before downscaling.

The parameters block_number, start_percent, end_percent, and downscale_after_skip are marked as advanced options in the node interface.

Outputs

Output Name	Description	Data Type
model	The modified model with downscale patch applied	MODEL

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): aa9434a521ab585b290a3bd8db804469bd3bb02103a0d830b6be6eb8e8c26a5e