ComfyUI Node: Core ML Sampler (Advanced)
Authored by aszc-dev
Created about a year ago
Updated 2 months ago
120 stars
Category
Core ML Suite
Inputs
coreml_model COREML_UNET
add_noise
- enable
- disable
noise_seed INT
steps INT
cfg FLOAT
sampler_name
- euler
- euler_ancestral
- heun
- heunpp2
- dpm_2
- dpm_2_ancestral
- lms
- dpm_fast
- dpm_adaptive
- dpmpp_2s_ancestral
- dpmpp_sde
- dpmpp_sde_gpu
- dpmpp_2m
- dpmpp_2m_sde
- dpmpp_2m_sde_gpu
- dpmpp_3m_sde
- dpmpp_3m_sde_gpu
- ddpm
- lcm
- ddim
- uni_pc
- uni_pc_bh2
scheduler
- normal
- karras
- exponential
- sgm_uniform
- simple
- ddim_uniform
positive CONDITIONING
start_at_step INT
end_at_step INT
return_with_leftover_noise
- disable
- enable
negative CONDITIONING
latent_image LATENT
Outputs
LATENT
Extension: Core ML Suite for ComfyUI
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.
Authored by aszc-dev