lhk229
a6d84845c6
- Segmentation backend now defaults to birefnet (ZhengPeng7/BiRefNet); anime-seg is selected at runtime with --seg-backend anime-seg, which also swaps in the matching weights (unknown backends raise). Config files stay for detailed tuning, not backend selection. - Default device is now cpu everywhere (dataclass defaults, default.yaml, birefnet.yaml); pass --device cuda for GPU. Avoids a hard CUDA-required failure on machines without a CUDA-enabled PyTorch build. - Docs: README + workflow status note updated (backend via --seg-backend, CPU default, examples no longer force --device cuda). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
123 lines
4.9 KiB
Python
123 lines
4.9 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class ChromaSettings:
|
|
border_ratio: float = 0.04
|
|
min_samples: int = 2048
|
|
hue_sigma_min: float = 7.0
|
|
lab_sigma_min: float = 10.0
|
|
rgb_sigma_min: float = 0.08
|
|
# Background-colour auto-detection (used when screen_color is None): find the
|
|
# flat colour that dominates the image border; raise if none is clean enough.
|
|
detect_cluster_radius: float = 12.0 # Lab radius grouping border pixels into the background cluster
|
|
detect_min_border_share: float = 0.55 # min fraction of the border that must be this one colour
|
|
detect_corner_tol: float = 20.0 # max Lab distance a corner may sit from the cluster centre
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class TrimapSettings:
|
|
sure_bg_threshold: float = 0.92
|
|
sure_fg_threshold: float = 0.12
|
|
unknown_radius_ratio: float = 0.012
|
|
fg_safe_radius_ratio: float = 0.006
|
|
min_unknown_radius: int = 4
|
|
min_fg_safe_radius: int = 2
|
|
# Semantic fusion thresholds (used by fuse_trimap when segmentation is on).
|
|
seg_core_threshold: float = 0.60
|
|
seg_loose_threshold: float = 0.08
|
|
# Trimap mode for the segmentation pipeline (the chroma-only pipeline ignores it):
|
|
# "directional" (default) -- chroma magnitude + seg + a hue-direction split. In
|
|
# the chroma-unknown zone a confidently-segmented pixel stays foreground
|
|
# unless it is displaced toward the background hue: a neutral background-
|
|
# coloured garment (e.g. a white shirt) is kept, while a background-hued
|
|
# residual (e.g. blue trapped between hair strands) is left UNKNOWN for
|
|
# ViTMatte / chroma-suppress to clear.
|
|
# "seg" -- original fuse_trimap: seg topology + chroma veto, no hue split.
|
|
# "directional-hard-bg" -- like "directional" but hard-marks background-hued
|
|
# pixels as background; more aggressive, can eat cool/shadowed white cloth.
|
|
mode: str = "directional"
|
|
seg_low: float = 0.15 # seg below this -> background-eligible; at/above -> foreground-eligible
|
|
bg_hue_proj_min: float = 4.0 # Lab a*/b* projection onto bg direction above which a pixel is background-hued
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class AlphaPostSettings:
|
|
min_component_area_ratio: float = 0.00001
|
|
fill_hole_area_ratio: float = 0.00002
|
|
alpha_floor: float = 0.002
|
|
alpha_ceil: float = 0.998
|
|
# Chroma-guided alpha suppression: in the unknown band, pull alpha toward 0
|
|
# where background (green) confidence is high, clearing spill in gaps/holes.
|
|
chroma_suppress: bool = True
|
|
chroma_suppress_bg_low: float = 0.35
|
|
chroma_suppress_bg_high: float = 0.80
|
|
chroma_suppress_strength: float = 1.0
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class ForegroundSettings:
|
|
enabled: bool = True
|
|
method: str = "ml" # "ml" (pymatting) or "unmix" (legacy heuristic)
|
|
fallback_to_unmix: bool = True
|
|
ml_regularization: float = 1e-5
|
|
# Legacy "unmix" method parameters (used only when method == "unmix").
|
|
edge_low: float = 0.005
|
|
edge_high: float = 0.995
|
|
min_unmix_alpha: float = 0.08
|
|
unmix_strength: float = 0.70
|
|
local_strength: float = 0.45
|
|
local_blur_radius: int = 11
|
|
local_alpha_threshold: float = 0.92
|
|
local_bg_confidence_max: float = 0.20
|
|
green_excess_margin: float = 0.015
|
|
bg_confidence_weight: float = 0.70
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class DespillSettings:
|
|
enabled: bool = True
|
|
edge_low: float = 0.005
|
|
strength: float = 0.92
|
|
green_excess_margin: float = 0.015
|
|
edge_expand_radius: int = 2
|
|
alpha_weight_floor: float = 0.35
|
|
# Custom-screen despill (when screen_color is set): margin, in Lab a*/b*
|
|
# units, of chroma allowed along the background colour direction before it is
|
|
# treated as spill. Larger keeps more of the subject's own colour.
|
|
color_margin_lab: float = 4.0
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class ModelSettings:
|
|
model_name: str = "hustvl/vitmatte-small-composition-1k"
|
|
device: str = "cpu"
|
|
matting_method: str = "vitmatte"
|
|
fallback_to_chroma_alpha: bool = False
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class SegmentationSettings:
|
|
enabled: bool = True # False = chroma-only pipeline (no seg model)
|
|
backend: str = "birefnet" # "birefnet" (general) or "anime-seg" (anime characters)
|
|
model_name: str = "ZhengPeng7/BiRefNet"
|
|
device: str = "cpu"
|
|
input_size: int = 1024
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class PipelineSettings:
|
|
chroma: ChromaSettings = ChromaSettings()
|
|
trimap: TrimapSettings = TrimapSettings()
|
|
alpha_post: AlphaPostSettings = AlphaPostSettings()
|
|
foreground: ForegroundSettings = ForegroundSettings()
|
|
despill: DespillSettings = DespillSettings()
|
|
model: ModelSettings = ModelSettings()
|
|
segmentation: SegmentationSettings = SegmentationSettings()
|
|
# Background-colour prior. None = auto-detect the flat background colour from the
|
|
# image border (raises if there is no clean flat background). A hex string like
|
|
# "#CFEFFF" sets it explicitly.
|
|
screen_color: str | None = None
|