Nodes/ComfyUI-DisPose/Sampler_DisPose
ComfyUI Node

Sampler_DisPose

A ComfyUI node in DisPose with 12 inputs and 3 outputs.

By bombax-xiaoice·Created about a year ago·Updated about a year ago· 0
Sampler_DisPose
  • pipe
  • ref_video
  • ref_image
  • latent
  • ref_image
  • poses
resolution576
seed42
tile_size16
tile_overlap6
num_inference_steps25
noise_aug_strength0.00
min_guidance_scale2.0
max_guidance_scale2.0
cpu_offloadmodel
CategoryDisPose

Inputs (12)

NameTypeDefaultDescription
pipeDisPosePipelineoutput from (Down)Loader_DisPose
ref_videoIMAGEvideo or concatenated images as reference poses, recommend to use VideoHelperSuite
ref_imageIMAGEone image as driving image, keeping everything but pose
resolutionINT576256–640shorter edge pixels, aspect ratio is 16/9
seedINT42set control_after_generation as fixed to make result reproducible
tile_sizeINT161–640larger size makes better motion quality but requires more vram
tile_overlapINT60–64larger overlap makes better motion quality but increase processing time, vram remains the same
num_inference_stepsINT251–100
noise_aug_strengthFLOAT0.000–1larger value makes better motion quality but less alike to ref_image
min_guidance_scaleFLOAT2.00.1–10
max_guidance_scaleFLOAT2.00.1–10
cpu_offloadCOMBOmodelsequence is slowest but consume the least VRAM, model also spare some vram and slightly slower than none

Outputs (3)

NameTypeDescription
latentLATENT
ref_imageIMAGE
posesIMAGE