Iterative Upscale (Latent/on Pixel Space)

ImpactPack/Upscale

IterativeLatentUpscale

Example

JSON Example

{
  "class_type": "IterativeLatentUpscale",
  "inputs": {
    "samples": [
      "node_id",
      0
    ],
    "upscale_factor": 1.5,
    "steps": 3,
    "temp_prefix": "",
    "upscaler": [
      "node_id",
      0
    ],
    "step_mode": "simple",
    "vae_compression": 8
  }
}

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

Inputs

Name	Type	Status	Constraints	Default
samples	LATENT	required	-	-
upscale_factor	FLOAT	required	min: 1, max: 10000, step: 0.1	1.5
steps	INT	required	min: 1, max: 10000, step: 1	3
temp_prefix	STRING	required	-	""
upscaler	UPSCALER	required	-	-
step_mode	ENUM 2 options simple geometric	required	-	"simple"
vae_compression	INT	required	min: 0, max: 256, step: 8	8

Outputs

Index	Name	Type	Is List	Connection Reference
0	latent	LATENT	No	["{node_id}", 0]
1	vae	VAE	No	["{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 IterativeLatentUpscale 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]
• vae (VAE): ["5", 1]

Package: comfyui-impact-pack