KSamplerAdvanced - ComfyUI Built-in Node Documentation - ComfyUI

The KSamplerAdvanced node is designed to enhance the sampling process by providing advanced configurations and techniques. It aims to offer more sophisticated options for generating samples from a model, improving upon the basic KSampler functionalities.

Inputs

Parameter	Description	Data Type
`model`	Specifies the model from which samples are to be generated, playing a crucial role in the sampling process.	MODEL
`add_noise`	Determines whether noise should be added to the sampling process, affecting the diversity and quality of the generated samples.	COMBO[STRING]
`noise_seed`	Sets the seed for noise generation, ensuring reproducibility in the sampling process.	INT
`steps`	Defines the number of steps to be taken in the sampling process, impacting the detail and quality of the output.	INT
`cfg`	Controls the conditioning factor, influencing the direction and space of the sampling process.	FLOAT
`sampler_name`	Selects the specific sampler to be used, allowing for customization of the sampling technique.	COMBO[STRING]
`scheduler`	Chooses the scheduler for controlling the sampling process, affecting the progression and quality of samples.	COMBO[STRING]
`positive`	Specifies the positive conditioning to guide the sampling towards desired attributes.	CONDITIONING
`negative`	Specifies the negative conditioning to steer the sampling away from certain attributes.	CONDITIONING
`latent_image`	Provides the initial latent image to be used in the sampling process, serving as a starting point.	LATENT
`start_at_step`	Determines the starting step of the sampling process, allowing for control over the sampling progression.	INT
`end_at_step`	Sets the ending step of the sampling process, defining the scope of the sampling.	INT
`return_with_leftover_noise`	Indicates whether to return the sample with leftover noise, affecting the final output’s appearance.	COMBO[STRING]

Outputs

Parameter	Description	Data Type
`latent`	The output represents the latent image generated from the model, reflecting the applied configurations and techniques.	LATENT

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub