Convert Checkpoint to Core ML is a ComfyUI node in the Core ML Suite category from Core ML Suite for ComfyUI. Inputs: ckpt_name, model_version, height, width…

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

ckpt_name

model_version

height

width

batch_size

attention_implementation

compute_unit

controlnet_support

quantize_nbits

lora_params

Core ML Converter

coreml_model

Convert Checkpoint to Core ML

Name	Type	Default	Description
ckpt_name	COMBO		0 options:
model_version	COMBO		2 options: SD15, SDXL
height	INT	512	—
width	INT	512	—
batch_size	INT	11–64	—
attention_implementation	COMBO		3 options: SPLIT_EINSUM, SPLIT_EINSUM_V2, ORIGINAL
compute_unit	COMBO		4 options: CPU_AND_NE, CPU_AND_GPU, ALL, CPU_ONLY
controlnet_support	BOOLEAN	false	—
quantize_nbitsopt	COMBO	none	4 options: none, 8, 6, 4
lora_paramsopt	LORA_PARAMS		—

Convert Checkpoint to Core ML

Inputs (10)

Outputs (1)