Nodes/HommageTools for ComfyUI/HT Detection Batch Processor
ComfyUI Node

HT Detection Batch Processor

A ComfyUI node in image/upscaling with 39 inputs and 3 outputs.

By ArtHommage·Created 2 years ago·Updated about a year ago· 4
HT Detection Batch Processor
  • image
  • model
  • positive
  • negative
  • vae
  • upscale_model
  • detection_model
  • segs
  • detection_upscale_model
  • upscaled_image
  • cropped_batch
  • scale_info
console_labelDetection Batch Processing
seed0
steps20
cfg8.00
sampler_name
scheduler
denoise0.20
mode_type
tile_width512
tile_height512
mask_blur8
tile_padding32
seam_fix_mode
seam_fix_denoise1.00
seam_fix_width64
seam_fix_mask_blur8
seam_fix_padding16
detection_threshold0.50
detection_dilation4
crop_factor3.0
drop_size10
scale_modemax
short_edge_divDIV_BY_8
mask_dilation1.00
use_bucketstrue
force_uniform_tilestrue
tiled_decodefalse
bucket_scale_factor1.0
use_provided_segsfalse
segs_upscale_separatelytrue
Categoryimage/upscaling

Inputs (39)

NameTypeDefaultDescription
console_labelSTRINGDetection Batch Processing
imageIMAGE
modelMODEL
positiveCONDITIONING
negativeCONDITIONING
vaeVAE
seedINT00–18446744073709550000
stepsINT201–10000
cfgFLOAT8.000–100
sampler_nameCOMBO44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
schedulerCOMBO9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
denoiseFLOAT0.200–1
upscale_modelUPSCALE_MODEL
mode_typeCOMBO3 options: Linear, Chess, None
tile_widthINT51264–8192
tile_heightINT51264–8192
mask_blurINT80–64
tile_paddingINT320–8192
seam_fix_modeCOMBO4 options: None, Band Pass, Half Tile, Half Tile + Intersections
seam_fix_denoiseFLOAT1.000–1
seam_fix_widthINT640–8192
seam_fix_mask_blurINT80–64
seam_fix_paddingINT160–8192
detection_modelBBOX_DETECTOR
detection_thresholdFLOAT0.500–1
detection_dilationINT4-512–512
crop_factorFLOAT3.01–100
drop_sizeINT101–8192
scale_modeCOMBOmax4 options: max, up, down, closest
short_edge_divCOMBODIV_BY_82 options: DIV_BY_8, DIV_BY_64
mask_dilationFLOAT1.001–2
use_bucketsBOOLEANtrue
force_uniform_tilesBOOLEANtrue
tiled_decodeBOOLEANfalse
bucket_scale_factorFLOAT1.00.1–4
segsoptSEGS
use_provided_segsoptBOOLEANfalse
segs_upscale_separatelyoptBOOLEANtrue
detection_upscale_modeloptUPSCALE_MODEL

Outputs (3)

NameTypeDescription
upscaled_imageIMAGE
cropped_batchIMAGE
scale_infoSTRING