VRAM Debug

KJNodes/misc

VRAM_Debug

Returns the inputs unchanged, they are only used as triggers, and performs comfy model management functions and garbage collection, reports free VRAM before and after the operations.

Example

JSON Example

{
  "class_type": "VRAM_Debug",
  "inputs": {
    "empty_cache": true,
    "gc_collect": true,
    "unload_all_models": false
  }
}

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
empty_cache	BOOLEAN	required	-	true
gc_collect	BOOLEAN	required	-	true
unload_all_models	BOOLEAN	required	-	false
any_input	*	optional	-	-
image_pass	IMAGE	optional	-	-
model_pass	MODEL	optional	-	-

Outputs

Index	Name	Type	Is List	Connection Reference
0	any_output	*	No	["{node_id}", 0]
1	image_pass	IMAGE	No	["{node_id}", 1]
2	model_pass	MODEL	No	["{node_id}", 2]
3	freemem_before	INT	No	["{node_id}", 3]
4	freemem_after	INT	No	["{node_id}", 4]

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 VRAM_Debug node in your workflow, and output_index is the index from the table above.

Example

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

• any_output (*): ["5", 0]
• image_pass (IMAGE): ["5", 1]
• model_pass (MODEL): ["5", 2]

Package: comfyui-kjnodes