Nodes/Node_Fun_ComfyUI/Fun KSampler
ComfyUI Node

Fun KSampler

Uses the provided model, positive and negative conditioning to denoise the latent image. Saves intermediate previews to the outputs folder using TAESD for better quality.

By nofunstudio·Created 2 years ago·Updated 7 months ago· 9
Fun KSampler
  • model
  • positive
  • negative
  • latent_image
  • vae
  • latent
  • preview_latents
seed0
steps20
cfg8.0
sampler_name
scheduler
denoise1.00
preview_steps5
skip_steps0
Categorysampling

Inputs (13)

NameTypeDefaultDescription
modelMODELThe model used for denoising the input latent.
seedINT00–18446744073709550000The random seed used for creating the noise.
stepsINT201–10000The number of steps used in the denoising process.
cfgFLOAT8.00–100The Classifier-Free Guidance scale balances creativity and adherence to the prompt. Higher values result in images more closely matching the prompt however too high values will negatively impact quality.
sampler_nameCOMBOThe algorithm used when sampling, this can affect the quality, speed, and style of the generated output.
schedulerCOMBOThe scheduler controls how noise is gradually removed to form the image.
positiveCONDITIONINGThe conditioning describing the attributes you want to include in the image.
negativeCONDITIONINGThe conditioning describing the attributes you want to exclude from the image.
latent_imageLATENTThe latent image to denoise.
vaeVAEThe VAE used for decoding the latent images.
denoiseFLOAT1.000–1The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling.
preview_stepsINT51–20Number of intermediate previews to generate during sampling.
skip_stepsINT00–10000Number of steps to skip before starting to save previews.

Outputs (2)

NameTypeDescription
latentLATENTThe final denoised latent.
preview_latentsLATENTPreview images are saved directly to the outputs folder using TAESD for better quality.