Documentation Index
Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
Use this file to discover all available pages before exploring further.
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Overview
Attaches a latent image and a degrade sigma value to a CONDITIONING data. This is used for PiD (Pixel-in-Detail) decoding or upscaling, allowing you to control how much the latent is degraded before processing.Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
positive | CONDITIONING | Yes | - | The conditioning data to attach the latent and degrade sigma to. |
latent | LATENT | Yes | - | The latent image (from VAEEncode or a KSampler) to attach to the conditioning. |
latent_format | COMBO | Yes | "flux""sd3" | The format of the latent. Flux1 and Flux2 latents are auto-detected from the channel dimension. SD3 must be selected manually (default: “flux”). |
degrade_sigma | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | The amount of degradation to apply. 0 means a clean latent. Increase this value to denoise corrupted latent outputs (default: 0.0). |
Outputs
| Output Name | Data Type | Description |
|---|---|---|
CONDITIONING | CONDITIONING | The original conditioning data with the latent and degrade sigma values attached. |
Source fingerprint (SHA-256):
7c8de543629c2299fc2c1e035e433dfc249af594773a77e65c69dde67eb104d7