Skip to main content

PatchModelAddDownscale (Kohya Deep Shrink)

model_patches/unet
PatchModelAddDownscale

Example

JSON Example
{
  "class_type": "PatchModelAddDownscale",
  "inputs": {
    "model": [
      "node_id",
      0
    ],
    "block_number": 3,
    "downscale_factor": 2,
    "start_percent": 0,
    "end_percent": 0.35,
    "downscale_after_skip": true,
    "downscale_method": null,
    "upscale_method": null
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

NameTypeStatusConstraintsDefault
modelMODELrequired--
block_numberINTrequiredmin: 1, max: 32, step: 13
downscale_factorFLOATrequiredmin: 0.1, max: 9, step: 0.0012
start_percentFLOATrequiredmin: 0, max: 1, step: 0.0010
end_percentFLOATrequiredmin: 0, max: 1, step: 0.0010.35
downscale_after_skipBOOLEANrequired-true
downscale_methodCOMBOrequired--
upscale_methodCOMBOrequired--

Outputs

IndexNameTypeIs ListConnection Reference
0MODELMODELNo["{node_id}", 0]
How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this PatchModelAddDownscale node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

  • MODEL (MODEL): ["5", 0]
Was this page helpful?