SDXL Empty Latent Image (rgthree)

rgthree

SDXL Empty Latent Image (rgthree)

Example

JSON Example

{
  "class_type": "SDXL Empty Latent Image (rgthree)",
  "inputs": {
    "dimensions": "1024 x 1024  (square)",
    "clip_scale": 2,
    "batch_size": 1
  }
}

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
dimensions	ENUM 9 options 1536 x 640 (landscape) 1344 x 768 (landscape) 1216 x 832 (landscape) 1152 x 896 (landscape) 1024 x 1024 (square) 896 x 1152 (portrait) 832 x 1216 (portrait) 768 x 1344 (portrait) 640 x 1536 (portrait)	required	-	"1024 x 1024 (square)"
clip_scale	FLOAT	required	min: 1, max: 10, step: 0.5	2
batch_size	INT	required	min: 1, max: 64	1

Outputs

Index	Name	Type	Is List	Connection Reference
0	LATENT	LATENT	No	["{node_id}", 0]
1	CLIP_WIDTH	INT	No	["{node_id}", 1]
2	CLIP_HEIGHT	INT	No	["{node_id}", 2]

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 SDXL Empty Latent Image (rgthree) 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]
• CLIP_WIDTH (INT): ["5", 1]
• CLIP_HEIGHT (INT): ["5", 2]

Package: rgthree-comfy