Skip to main content

Latent Scale (on Pixel Space)

ImpactPack/Upscale
LatentPixelScale

Example

JSON Example
{
  "class_type": "LatentPixelScale",
  "inputs": {
    "samples": [
      "node_id",
      0
    ],
    "scale_method": "nearest-exact",
    "scale_factor": 1.5,
    "vae": [
      "node_id",
      0
    ],
    "use_tiled_vae": false
  }
}

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

Inputs

NameTypeStatusConstraintsDefault
samplesLATENTrequired--
scale_methodENUM
4 options
  • nearest-exact
  • bilinear
  • lanczos
  • area
required--
scale_factorFLOATrequiredmin: 0.1, max: 10000, step: 0.051.5
vaeVAErequired--
use_tiled_vaeBOOLEANrequired-false
upscale_model_optUPSCALE_MODELoptional--

Outputs

IndexNameTypeIs ListConnection Reference
0LATENTLATENTNo["{node_id}", 0]
1IMAGEIMAGENo["{node_id}", 1]
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 LatentPixelScale node in your workflow, and output_index is the index from the table above.

Example

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

  • LATENT (LATENT): ["5", 0]
  • IMAGE (IMAGE): ["5", 1]
Was this page helpful?