Nodes/ComfyUI-BrainDead/BD ATR Human Parser
ComfyUI Node

BD ATR Human Parser

Parse a human image into 18 semantic regions using an ATR-scheme SegFormer. Default weights (mattmdjaga/segformer_b2_clothes) are MIT-licensed. Outputs a HUMAN_PARSE_MAP for the mask-split node.

By BizaNator·Created 7 months ago·Updated 16 days ago· 14
BD ATR Human Parser
  • image
  • parse_map
model_idmattmdjaga/segformer_b2_clothes
deviceauto
dtypefp16
confidence_threshold0.00
cache_dir
Category🧠BrainDead/Segmentation

Inputs (6)

NameTypeDefaultDescription
imageIMAGE
model_idSTRINGmattmdjaga/segformer_b2_clothesHuggingFace repo id (must use ATR 18-class scheme)
deviceoptCOMBOauto3 options: auto, cuda, cpu
dtypeoptCOMBOfp163 options: fp16, bf16, fp32
confidence_thresholdoptFLOAT0.000–1Pixels with max-softmax below this become background. 0 = off. Try 0.5–0.7 to clean noise. Tip: for sharper boundaries, downsize the image to ~512px before this node (ATR was trained at 512×512). Large inputs blur edges on the upsample.
cache_diroptSTRINGOverride HF cache dir. Blank → HF_HOME env var, or ComfyUI models/huggingface/, or HF default.

Outputs (1)

NameTypeDescription
parse_mapHUMAN_PARSE_MAP