🔧 KSampler Stochastic Variations

essentials/sampling

KSamplerVariationsStochastic+

Example

JSON Example

{
  "class_type": "KSamplerVariationsStochastic+",
  "inputs": {
    "model": [
      "node_id",
      0
    ],
    "latent_image": [
      "node_id",
      0
    ],
    "noise_seed": 0,
    "steps": 25,
    "cfg": 7,
    "sampler": "euler",
    "scheduler": "simple",
    "positive": [
      "node_id",
      0
    ],
    "negative": [
      "node_id",
      0
    ],
    "variation_seed": [
      "node_id",
      0
    ],
    "variation_strength": 0.2,
    "cfg_scale": 1
  }
}

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

Inputs

Name	Type	Status	Constraints	Default
model	MODEL	required	-	-
latent_image	LATENT	required	-	-
noise_seed	INT	required	min: 0, max: 1.84e+19	0
steps	INT	required	min: 1, max: 10000	25
cfg	FLOAT	required	min: 0, max: 100, step: 0.1	7
sampler	ENUM 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	-	-
scheduler	ENUM 9 options simple sgm_uniform karras exponential ddim_uniform beta normal linear_quadratic kl_optimal	required	-	-
positive	CONDITIONING	required	-	-
negative	CONDITIONING	required	-	-
variation_seed	INT:seed	required	min: 0, max: 1.84e+19	0
variation_strength	FLOAT	required	min: 0, max: 1, step: 0.05	0.2
cfg_scale	FLOAT	required	min: 0, max: 1, step: 0.05	1

Outputs

Index	Name	Type	Is List	Connection Reference
0	LATENT	LATENT	No	["{node_id}", 0]

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 KSamplerVariationsStochastic+ node in your workflow, and output_index is the index from the table above.

Example

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

• LATENT (LATENT): ["5", 0]

Package: comfyui-essentials