Adaptive Projected Guidance
sampling/custom_sampling
APGExample
JSON Example
{
"class_type": "APG",
"inputs": {
"model": [
"node_id",
0
],
"eta": 1,
"norm_threshold": 5,
"momentum": 0
}
}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 |
|---|---|---|---|---|
model | MODEL | required | - | - |
eta? | FLOAT | required | min: -10, max: 10, step: 0.01 | 1 |
norm_threshold? | FLOAT | required | min: 0, max: 50, step: 0.1 | 5 |
momentum? | FLOAT | required | min: -5, max: 1, step: 0.01 | 0 |
Outputs
| Index | Name | Type | Is List | Connection Reference |
|---|---|---|---|---|
0 | MODEL | MODEL | No | ["{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 APG 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?