Skip to main content

SEGSDetailer For Video (SEGS/pipe)

ImpactPack/Detailer
SEGSDetailerForAnimateDiff

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. As a specialized detailer node for improving video details, such as in AnimateDiff, this node can handle cases where the masks contained in SEGS serve as batch masks spanning multiple frames.

Example

JSON Example
{
  "class_type": "SEGSDetailerForAnimateDiff",
  "inputs": {
    "image_frames": [
      "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,
    "basic_pipe": [
      "node_id",
      0
    ],
    "refiner_ratio": 0.2
  }
}

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

Inputs

NameTypeStatusConstraintsDefault
image_framesIMAGErequired--
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
basic_pipe?BASIC_PIPErequired--
refiner_ratioFLOATrequiredmin: 0, max: 10.2
refiner_basic_pipe_optBASIC_PIPEoptional--
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 SEGSDetailerForAnimateDiff 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?