Skip to main content

SEGSDetailer

ImpactPack/Detailer
SEGSDetailer

This node enhances details by inpainting each region within the detected area bundle (SEGS) after enlarging them based on the guide size. This node is applied specifically to SEGS rather than the entire image. To apply it to the entire image, use the 'SEGS Paste' node.

Example

JSON Example
{
  "class_type": "SEGSDetailer",
  "inputs": {
    "image": [
      "node_id",
      0
    ],
    "segs": [
      "node_id",
      0
    ],
    "guide_size": 512,
    "guide_size_for": true,
    "max_size": 768,
    "seed": 0,
    "steps": 20,
    "cfg": 8,
    "sampler_name": "euler",
    "scheduler": "simple",
    "denoise": 0.5,
    "noise_mask": true,
    "force_inpaint": true,
    "basic_pipe": [
      "node_id",
      0
    ],
    "refiner_ratio": 0.2,
    "batch_size": 1,
    "cycle": 1
  }
}

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

Inputs

NameTypeStatusConstraintsDefault
imageIMAGErequired--
segsSEGSrequired--
guide_sizeFLOATrequiredmin: 64, max: 16384, step: 8512
guide_size_forBOOLEANrequired-true
max_sizeFLOATrequiredmin: 64, max: 16384, step: 8768
seedINTrequiredmin: 0, max: 1.84e+190
stepsINTrequiredmin: 1, max: 1000020
cfgFLOATrequiredmin: 0, max: 1008
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
17 options
  • simple
  • sgm_uniform
  • karras
  • exponential
  • ddim_uniform
  • beta
  • normal
  • linear_quadratic
  • kl_optimal
  • AYS SDXL
  • AYS SD1
  • AYS SVD
  • GITS[coeff=1.2]
  • LTXV[default]
  • OSS FLUX
  • OSS Wan
  • OSS Chroma
required--
denoiseFLOATrequiredmin: 0.0001, max: 1, step: 0.010.5
noise_maskBOOLEANrequired-true
force_inpaintBOOLEANrequired-true
basic_pipe?BASIC_PIPErequired--
refiner_ratioFLOATrequiredmin: 0, max: 10.2
batch_sizeINTrequiredmin: 1, max: 1001
cycleINTrequiredmin: 1, max: 10, step: 11
refiner_basic_pipe_optBASIC_PIPEoptional--
inpaint_modelBOOLEANoptional-false
noise_mask_featherINToptionalmin: 0, max: 100, step: 120
scheduler_func_optSCHEDULER_FUNCoptional--

Outputs

IndexNameTypeIs ListConnection Reference
0segsSEGSNo["{node_id}", 0]
1cnet_imagesIMAGEYes["{node_id}", 1]
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 SEGSDetailer node in your workflow, and output_index is the index from the table above.

Example

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

  • segs (SEGS): ["5", 0]
  • cnet_images (IMAGE): ["5", 1]
Was this page helpful?