CFG Override
The CFG Override node allows you to set a fixed CFG (Classifier-Free Guidance) scale value for a specific range of the sampling process, defined as a percentage of the total steps. When multiple CFG Override nodes are connected, the one closest to the sampler in the chain takes priority for overlapping ranges.Inputs
| Parameter | Description | Data Type | Required | Range |
|---|---|---|---|---|
model | The model to apply the CFG override to | MODEL | Yes | |
cfg | The fixed CFG scale value to use during the override range (default: 1.0) | FLOAT | Yes | 0.0 to 100.0 |
start_percent | The starting point of the override range as a percentage of the sampling process (default: 0.0) | FLOAT | Yes | 0.0 to 1.0 |
end_percent | The ending point of the override range as a percentage of the sampling process (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 |
Outputs
| Output Name | Description | Data Type |
|---|---|---|
MODEL | The model with the CFG override wrapper applied | MODEL |
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256):
1fe57a4e78a2f18c4e7da49fa7a6c473d64dc0ebf6662535dfb5379c37936662