Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The SD_4XUpscale_Conditioning node prepares conditioning data for upscaling images using diffusion models. It takes input images and conditioning data, then applies scaling and noise augmentation to create modified conditioning that guides the upscaling process. The node outputs both positive and negative conditioning along with latent representations for the upscaled dimensions.

Inputs

ParameterData TypeRequiredRangeDescription
imagesIMAGEYes-Input images to be upscaled
positiveCONDITIONINGYes-Positive conditioning data that guides the generation toward desired content
negativeCONDITIONINGYes-Negative conditioning data that steers the generation away from unwanted content
scale_ratioFLOATNo0.0 - 10.0Scaling factor applied to the input images (default: 4.0)
noise_augmentationFLOATNo0.0 - 1.0Amount of noise to add during the upscaling process (default: 0.0)

Outputs

Output NameData TypeDescription
positiveCONDITIONINGModified positive conditioning with upscaling information applied
negativeCONDITIONINGModified negative conditioning with upscaling information applied
latentLATENTEmpty latent representation matching the upscaled dimensions