Inputs
| Parameter | Description | Data Type | Required | Range |
|---|---|---|---|---|
coeff | The coefficient value that controls the noise schedule curve (default: 1.20) | FLOAT | Yes | 0.80 - 1.50 |
steps | The total number of sampling steps to generate sigmas for (default: 10) | INT | Yes | 2 - 1000 |
denoise | Denoising factor that reduces the number of steps used (default: 1.0) | FLOAT | Yes | 0.0 - 1.0 |
denoise is set to 0.0, the node returns an empty tensor. When denoise is less than 1.0, the actual number of steps used is calculated as round(steps * denoise). For steps greater than 20, the node uses log-linear interpolation to extend the pre-defined noise levels to the desired number of steps.
Outputs
| Output Name | Description | Data Type |
|---|---|---|
sigmas | The generated sigma values for the noise schedule | SIGMAS |
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):
e58c8c1c0e7cbf79554040a6684f12c1a2c59c69bb50770f9577a13d76ac8eb3