Skip to main content

KSampler Config (rgthree)

rgthree
KSampler Config (rgthree)

Example

JSON Example
{
  "class_type": "KSampler Config (rgthree)",
  "inputs": {
    "steps_total": 30,
    "refiner_step": 24,
    "cfg": 8,
    "sampler_name": "euler",
    "scheduler": "simple"
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

NameTypeStatusConstraintsDefault
steps_totalINTrequiredmin: 1, max: 16384, step: 130
refiner_stepINTrequiredmin: 1, max: 16384, step: 124
cfgFLOATrequiredmin: 0, max: 100, step: 0.58
sampler_nameENUM
44 options
  • 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
required--
schedulerENUM
9 options
  • simple
  • sgm_uniform
  • karras
  • exponential
  • ddim_uniform
  • beta
  • normal
  • linear_quadratic
  • kl_optimal
required--

Outputs

IndexNameTypeIs ListConnection Reference
0STEPSINTNo["{node_id}", 0]
1REFINER_STEPINTNo["{node_id}", 1]
2CFGFLOATNo["{node_id}", 2]
3SAMPLEReulereuler_cfg_ppeuler_ancestraleuler_ancestral_cfg_ppheunheunpp2exp_heun_2_x0exp_heun_2_x0_sdedpm_2dpm_2_ancestrallmsdpm_fastdpm_adaptivedpmpp_2s_ancestraldpmpp_2s_ancestral_cfg_ppdpmpp_sdedpmpp_sde_gpudpmpp_2mdpmpp_2m_cfg_ppdpmpp_2m_sdedpmpp_2m_sde_gpudpmpp_2m_sde_heundpmpp_2m_sde_heun_gpudpmpp_3m_sdedpmpp_3m_sde_gpuddpmlcmipndmipndm_vdeisres_multistepres_multistep_cfg_ppres_multistep_ancestralres_multistep_ancestral_cfg_ppgradient_estimationgradient_estimation_cfg_pper_sdeseeds_2seeds_3sa_solversa_solver_peceddimuni_pcuni_pc_bh2No["{node_id}", 3]
4SCHEDULERsimplesgm_uniformkarrasexponentialddim_uniformbetanormallinear_quadratickl_optimalNo["{node_id}", 4]
How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this KSampler Config (rgthree) node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

  • STEPS (INT): ["5", 0]
  • REFINER_STEP (INT): ["5", 1]
  • CFG (FLOAT): ["5", 2]
Was this page helpful?