Skip to main content

WanVideoNAG

KJNodes/experimentalExperimental
WanVideoNAG

https://github.com/ChenDarYen/Normalized-Attention-Guidance

Experimental: This node is experimental and its behavior may change without notice.

Example

JSON Example
{
  "class_type": "WanVideoNAG",
  "inputs": {
    "model": [
      "node_id",
      0
    ],
    "conditioning": [
      "node_id",
      0
    ],
    "nag_scale": 11,
    "nag_alpha": 0.25,
    "nag_tau": 2.5
  }
}

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

Inputs

NameTypeStatusConstraintsDefault
modelMODELrequired--
conditioningCONDITIONINGrequired--
nag_scale?FLOATrequiredmin: 0, max: 100, step: 0.00111
nag_alpha?FLOATrequiredmin: 0, max: 1, step: 0.0010.25
nag_tau?FLOATrequiredmin: 0, max: 10, step: 0.0012.5
input_type?ENUM
2 options
  • default
  • batch
optional--

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 WanVideoNAG 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?