ComfyUI Node: Model Matrix Lab
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
ComfyUI-KSampler-Matrix-Lab
Inputs
latent_image LATENT
positive_text STRING
negative_text STRING
seed INT
steps INT
cfg FLOAT
denoise FLOAT
sampler_name
- euler
- euler_cfg_pp
- euler_ancestral
- euler_ancestral_cfg_pp
- heun
- heunpp2
- exp_heun_2_x0
- exp_heun_2_x0_sde
- dpm_2
- dpm_2_ancestral
- lms
- dpm_fast
- dpm_adaptive
- dpmpp_2s_ancestral
- dpmpp_2s_ancestral_cfg_pp
- dpmpp_sde
- dpmpp_sde_gpu
- dpmpp_2m
- dpmpp_2m_cfg_pp
- dpmpp_2m_sde
- dpmpp_2m_sde_gpu
- dpmpp_2m_sde_heun
- dpmpp_2m_sde_heun_gpu
- dpmpp_3m_sde
- dpmpp_3m_sde_gpu
- ddpm
- lcm
- ipndm
- ipndm_v
- deis
- res_multistep
- res_multistep_cfg_pp
- res_multistep_ancestral
- res_multistep_ancestral_cfg_pp
- gradient_estimation
- gradient_estimation_cfg_pp
- er_sde
- seeds_2
- seeds_3
- sa_solver
- sa_solver_pece
- ddim
- uni_pc
- uni_pc_bh2
scheduler
- simple
- sgm_uniform
- karras
- exponential
- ddim_uniform
- beta
- normal
- linear_quadratic
- kl_optimal
model_01
- None
model_02
- None
model_03
- None
model_04
- None
model_05
- None
model_06
- None
model_07
- None
model_08
- None
model_09
- None
model_10
- None
model_11
- None
model_12
- None
model_13
- None
model_14
- None
model_15
- None
model_16
- None
model_17
- None
model_18
- None
model_19
- None
model_20
- None
diffusion_weight_dtype
- default
- fp8_e4m3fn
- fp8_e4m3fn_fast
- fp8_e5m2
grid_columns INT
cell_scale FLOAT
font_size INT
padding INT
background
- white
- gray
- black
show_grid_lines BOOLEAN
show_cell_labels BOOLEAN
show_run_header BOOLEAN
continue_on_error BOOLEAN
clip CLIP
vae VAE
Outputs
IMAGE
Extension: ComfyUI-KSampler-Matrix-Lab
ComfyUI KSampler Matrix Lab is a custom node for comparing multiple sampler and scheduler combinations in one labeled image grid.
Authored by btitkin
Looking for a different node?
More nodes in ComfyUI-KSampler-Matrix-Lab
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.