Skip to main content
This node specializes in enhancing the resolution of images through a 4x upscale process, incorporating conditioning elements to refine the output. It leverages diffusion techniques to upscale images while allowing for the adjustment of scale ratio and noise augmentation to fine-tune the enhancement process.

Inputs

ParameterDescriptionComfy dtype
imagesThe input images to be upscaled. This parameter is crucial as it directly influences the quality and resolution of the output images.IMAGE
positivePositive conditioning elements that guide the upscale process towards desired attributes or features in the output images.CONDITIONING
negativeNegative conditioning elements that the upscale process should avoid, helping to steer the output away from undesired attributes or features.CONDITIONING
scale_ratioDetermines the factor by which the image resolution is increased. A higher scale ratio results in a larger output image, allowing for greater detail and clarity.FLOAT
noise_augmentationControls the level of noise augmentation applied during the upscale process. This can be used to introduce variability and improve the robustness of the output images.FLOAT

Outputs

ParameterDescriptionData Type
positiveThe refined positive conditioning elements resulting from the upscale process.CONDITIONING
negativeThe refined negative conditioning elements resulting from the upscale process.CONDITIONING
latentA latent representation generated during the upscale process, which can be utilized in further processing or model training.LATENT
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub