Uses the provided model, positive and negative conditioning to denoise the latent image. — ComfyUI node from Core ML Suite for ComfyUI. Run it in the cloud, no…

This extension contains a set of custom nodes for ComfyUI that allow you to use Core ML models in your ComfyUI workflows. The models can be obtained here, or you can convert your own models using coremltools. The main motivation behind using Core ML models in ComfyUI is to allow you to utilize the ANE (Apple Neural Engine) on Apple Silicon (M1/M2) machines to improve performance.

Core ML Suite for ComfyUI

coreml_model

seed

steps

sampler_name

scheduler

positive

denoise

negative

latent_image

Uses the provided model, positive and negative conditioning to denoise the latent image.

CoreMLSampler

LATENT

Core ML Sampler

Name	Type	Default	Description
coreml_model	COREML_UNET		—
seed	INT	00–18446744073709550000	The random seed used for creating the noise.
steps	INT	201–10000	The number of steps used in the denoising process.
cfg	FLOAT	8.00–100	The 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_name	COMBO		The algorithm used when sampling, this can affect the quality, speed, and style of the generated output.
scheduler	COMBO		The scheduler controls how noise is gradually removed to form the image.
positive	CONDITIONING		The conditioning describing the attributes you want to include in the image.
denoise	FLOAT	1.000–1	The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling.
negativeopt	CONDITIONING		—
latent_imageopt	LATENT		—

Core ML Sampler

Inputs (10)

Outputs (1)