Rename core module src.controlnet_aux to src.custom_controlnet_aux to…

… avoid conflict with HuggingFace's controlnet_aux

README.md

@@ -180,6 +180,7 @@ for o in history['outputs']:
 
 # Testing workflow
 https://github.com/Fannovel16/comfyui_controlnet_aux/blob/main/examples/ExecuteAll.png
+Input image: https://github.com/Fannovel16/comfyui_controlnet_aux/blob/main/examples/comfyui-controlnet-aux-logo.png
 
 # Q&A:
 ## Why some nodes doesn't appear after I installed this repo?

__init__.py

@@ -8,7 +8,7 @@
 from .hint_image_enchance import NODE_DISPLAY_NAME_MAPPINGS as HIE_NODE_DISPLAY_NAME_MAPPINGS
 #Ref: https://github.com/comfyanonymous/ComfyUI/blob/76d53c4622fc06372975ed2a43ad345935b8a551/nodes.py#L17
 sys.path.insert(0, str(Path(here, "src").resolve()))
-for pkg_name in ["controlnet_aux", "custom_mmpkg"]:
+for pkg_name in ["custom_controlnet_aux", "custom_mmpkg"]:
  sys.path.append(str(Path(here, "src", pkg_name).resolve()))
 
 #Enable CPU fallback for ops not being supported by MPS like upsample_bicubic2d.out

dev_interface.py

@@ -3,4 +3,4 @@
 import sys
 sys.path.append(str(Path(here, "src")))
 
-from controlnet_aux import *
+from custom_controlnet_aux import *

node_wrappers/anime_face_segment.py

@@ -20,7 +20,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Semantic Segmentation"
 
  def execute(self, image, remove_background_using_abg=True, resolution=512, **kwargs):
- from controlnet_aux.anime_face_segment import AnimeFaceSegmentor
+ from custom_controlnet_aux.anime_face_segment import AnimeFaceSegmentor
 
  model = AnimeFaceSegmentor.from_pretrained().to(model_management.get_torch_device())
  if remove_background_using_abg:

node_wrappers/anyline.py

@@ -40,7 +40,7 @@ def __init__(self):
  self.device = model_management.get_torch_device()
 
  def get_anyline(self, image, merge_with_lineart="lineart_standard", resolution=512, lineart_lower_bound=0, lineart_upper_bound=1, object_min_size=36, object_connectivity=1):
- from controlnet_aux.teed import TEDDetector
+ from custom_controlnet_aux.teed import TEDDetector
  from skimage import morphology
  pbar = comfy.utils.ProgressBar(3)
 
@@ -53,14 +53,14 @@ def get_anyline(self, image, merge_with_lineart="lineart_standard", resolution=5
 
  # Process the image with the lineart standard preprocessor
  if merge_with_lineart == "lineart_standard":
- from controlnet_aux.lineart_standard import LineartStandardDetector
+ from custom_controlnet_aux.lineart_standard import LineartStandardDetector
  lineart_standard_detector = LineartStandardDetector()
  lineart_result = common_annotator_call(lineart_standard_detector, image, guassian_sigma=2, intensity_threshold=3, resolution=resolution, show_pbar=False).numpy()
  del lineart_standard_detector
  else:
- from controlnet_aux.lineart import LineartDetector
- from controlnet_aux.lineart_anime import LineartAnimeDetector
- from controlnet_aux.manga_line import LineartMangaDetector
+ from custom_controlnet_aux.lineart import LineartDetector
+ from custom_controlnet_aux.lineart_anime import LineartAnimeDetector
+ from custom_controlnet_aux.manga_line import LineartMangaDetector
  lineart_detector = dict(lineart_realisitic=LineartDetector, lineart_anime=LineartAnimeDetector, manga_line=LineartMangaDetector)[merge_with_lineart]
  lineart_detector = lineart_detector.from_pretrained().to(self.device)
  lineart_result = common_annotator_call(lineart_detector, image, resolution=resolution, show_pbar=False).numpy()

node_wrappers/binary.py

@@ -15,7 +15,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, bin_threshold=100, resolution=512, **kwargs):
- from controlnet_aux.binary import BinaryDetector
+ from custom_controlnet_aux.binary import BinaryDetector
 
  return (common_annotator_call(BinaryDetector(), image, bin_threshold=bin_threshold, resolution=resolution), )
 

node_wrappers/canny.py

@@ -16,7 +16,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, low_threshold=100, high_threshold=200, resolution=512, **kwargs):
- from controlnet_aux.canny import CannyDetector
+ from custom_controlnet_aux.canny import CannyDetector
 
  return (common_annotator_call(CannyDetector(), image, low_threshold=low_threshold, high_threshold=high_threshold, resolution=resolution), )
 

node_wrappers/color.py

@@ -12,7 +12,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/T2IAdapter-only"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.color import ColorDetector
+ from custom_controlnet_aux.color import ColorDetector
 
  return (common_annotator_call(ColorDetector(), image, resolution=resolution), )
 

node_wrappers/densepose.py

@@ -16,7 +16,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Faces and Poses Estimators"
 
  def execute(self, image, model="densepose_r50_fpn_dl.torchscript", cmap="Viridis (MagicAnimate)", resolution=512):
- from controlnet_aux.densepose import DenseposeDetector
+ from custom_controlnet_aux.densepose import DenseposeDetector
  model = DenseposeDetector \
  .from_pretrained(filename=model) \
  .to(model_management.get_torch_device())

node_wrappers/depth_anything.py

@@ -17,7 +17,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, ckpt_name="depth_anything_vitl14.pth", resolution=512, **kwargs):
- from controlnet_aux.depth_anything import DepthAnythingDetector
+ from custom_controlnet_aux.depth_anything import DepthAnythingDetector
 
  model = DepthAnythingDetector.from_pretrained(filename=ckpt_name).to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution)
@@ -38,7 +38,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, environment="indoor", resolution=512, **kwargs):
- from controlnet_aux.zoe import ZoeDepthAnythingDetector
+ from custom_controlnet_aux.zoe import ZoeDepthAnythingDetector
  ckpt_name = "depth_anything_metric_depth_indoor.pt" if environment == "indoor" else "depth_anything_metric_depth_outdoor.pt"
  model = ZoeDepthAnythingDetector.from_pretrained(filename=ckpt_name).to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution)

node_wrappers/depth_anything_v2.py

@@ -18,7 +18,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, ckpt_name="depth_anything_v2_vitl.pth", resolution=512, **kwargs):
- from controlnet_aux.depth_anything_v2 import DepthAnythingV2Detector
+ from custom_controlnet_aux.depth_anything_v2 import DepthAnythingV2Detector
 
  model = DepthAnythingV2Detector.from_pretrained(filename=ckpt_name).to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, max_depth=1)
@@ -39,7 +39,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, environment, resolution=512, max_depth=20.0, **kwargs):
- from controlnet_aux.depth_anything_v2 import DepthAnythingV2Detector
+ from custom_controlnet_aux.depth_anything_v2 import DepthAnythingV2Detector
  filename = dict(indoor="depth_anything_v2_metric_hypersim_vitl.pth", outdoor="depth_anything_v2_metric_vkitti_vitl.pth")[environment]
  model = DepthAnythingV2Detector.from_pretrained(filename=filename).to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, max_depth=max_depth)

node_wrappers/diffusion_edge.py

@@ -24,7 +24,7 @@ def INPUT_TYPES(s):
 
  def execute(self, image, environment="indoor", patch_batch_size=4, resolution=512, **kwargs):
  install_deps()
- from controlnet_aux.diffusion_edge import DiffusionEdgeDetector
+ from custom_controlnet_aux.diffusion_edge import DiffusionEdgeDetector
 
  model = DiffusionEdgeDetector \
  .from_pretrained(filename = f"diffusion_edge_{environment}.pt") \

node_wrappers/dsine.py

@@ -16,7 +16,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, fov=60.0, iterations=5, resolution=512, **kwargs):
- from controlnet_aux.dsine import DsineDetector
+ from custom_controlnet_aux.dsine import DsineDetector
 
  model = DsineDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, fov=fov, iterations=iterations, resolution=resolution)

node_wrappers/dwpose.py

@@ -2,7 +2,7 @@
 import comfy.model_management as model_management
 import numpy as np
 import warnings
-from controlnet_aux.dwpose import DwposeDetector, AnimalposeDetector
+from custom_controlnet_aux.dwpose import DwposeDetector, AnimalposeDetector
 import os
 import json
 

node_wrappers/hed.py

@@ -15,7 +15,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.hed import HEDdetector
+ from custom_controlnet_aux.hed import HEDdetector
 
  model = HEDdetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, safe = kwargs["safe"] == "enable")
@@ -36,7 +36,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.hed import HEDdetector
+ from custom_controlnet_aux.hed import HEDdetector
 
  model = HEDdetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, scribble=True, safe=kwargs["safe"]=="enable")

node_wrappers/leres.py

@@ -17,7 +17,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, rm_nearest=0, rm_background=0, resolution=512, boost="disable", **kwargs):
- from controlnet_aux.leres import LeresDetector
+ from custom_controlnet_aux.leres import LeresDetector
 
  model = LeresDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, thr_a=rm_nearest, thr_b=rm_background, boost=boost == "enable")

node_wrappers/lineart.py

@@ -15,7 +15,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.lineart import LineartDetector
+ from custom_controlnet_aux.lineart import LineartDetector
 
  model = LineartDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, coarse = kwargs["coarse"] == "enable")

node_wrappers/lineart_anime.py

@@ -12,7 +12,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.lineart_anime import LineartAnimeDetector
+ from custom_controlnet_aux.lineart_anime import LineartAnimeDetector
 
  model = LineartAnimeDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution)

node_wrappers/lineart_standard.py

@@ -16,7 +16,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, guassian_sigma=6, intensity_threshold=8, resolution=512, **kwargs):
- from controlnet_aux.lineart_standard import LineartStandardDetector
+ from custom_controlnet_aux.lineart_standard import LineartStandardDetector
  return (common_annotator_call(LineartStandardDetector(), image, guassian_sigma=guassian_sigma, intensity_threshold=intensity_threshold, resolution=resolution), )
 
 NODE_CLASS_MAPPINGS = {

node_wrappers/manga_line.py

@@ -12,7 +12,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.manga_line import LineartMangaDetector
+ from custom_controlnet_aux.manga_line import LineartMangaDetector
 
  model = LineartMangaDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution)

node_wrappers/mediapipe_face.py

@@ -27,7 +27,7 @@ def INPUT_TYPES(s):
  def detect(self, image, max_faces=10, min_confidence=0.5, resolution=512):
  #Ref: https://github.com/Fannovel16/comfy_controlnet_preprocessors/issues/70#issuecomment-1677967369
  install_deps()
- from controlnet_aux.mediapipe_face import MediapipeFaceDetector
+ from custom_controlnet_aux.mediapipe_face import MediapipeFaceDetector
  return (common_annotator_call(MediapipeFaceDetector(), image, max_faces=max_faces, min_confidence=min_confidence, resolution=resolution), )
 
 NODE_CLASS_MAPPINGS = {

node_wrappers/mesh_graphormer.py

@@ -61,7 +61,7 @@ def INPUT_TYPES(s):
 
  def execute(self, image, mask_bbox_padding=30, mask_type="based_on_depth", mask_expand=5, resolution=512, rand_seed=88, detect_thr=0.6, presence_thr=0.6, **kwargs):
  install_deps()
- from controlnet_aux.mesh_graphormer import MeshGraphormerDetector
+ from custom_controlnet_aux.mesh_graphormer import MeshGraphormerDetector
  model = kwargs["model"] if "model" in kwargs \
  else MeshGraphormerDetector.from_pretrained(detect_thr=detect_thr, presence_thr=presence_thr).to(model_management.get_torch_device())
 
@@ -120,7 +120,7 @@ def INPUT_TYPES(s):
 
  def execute(self, image, bbox_detector, bbox_threshold=0.5, bbox_dilation=10, bbox_crop_factor=3.0, drop_size=10, resolution=512, **mesh_graphormer_kwargs):
  install_deps()
- from controlnet_aux.mesh_graphormer import MeshGraphormerDetector
+ from custom_controlnet_aux.mesh_graphormer import MeshGraphormerDetector
  mesh_graphormer_node = Mesh_Graphormer_Depth_Map_Preprocessor()
  model = MeshGraphormerDetector.from_pretrained(detect_thr=0.6, presence_thr=0.6).to(model_management.get_torch_device())
  mesh_graphormer_kwargs["model"] = model

node_wrappers/metric3d.py

@@ -17,7 +17,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, backbone="vit-small", fx=1000, fy=1000, resolution=512):
- from controlnet_aux.metric3d import Metric3DDetector
+ from custom_controlnet_aux.metric3d import Metric3DDetector
  model = Metric3DDetector.from_pretrained(filename=f"metric_depth_{backbone.replace('-', '_')}_800k.pth").to(model_management.get_torch_device())
  cb = lambda image, **kwargs: model(image, **kwargs)[0]
  out = common_annotator_call(cb, image, resolution=resolution, fx=fx, fy=fy, depth_and_normal=True)
@@ -40,7 +40,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, backbone="vit-small", fx=1000, fy=1000, resolution=512):
- from controlnet_aux.metric3d import Metric3DDetector
+ from custom_controlnet_aux.metric3d import Metric3DDetector
  model = Metric3DDetector.from_pretrained(filename=f"metric_depth_{backbone.replace('-', '_')}_800k.pth").to(model_management.get_torch_device())
  cb = lambda image, **kwargs: model(image, **kwargs)[1]
  out = common_annotator_call(cb, image, resolution=resolution, fx=fx, fy=fy, depth_and_normal=True)

node_wrappers/midas.py

@@ -17,7 +17,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, a=np.pi * 2.0, bg_threshold=0.1, resolution=512, **kwargs):
- from controlnet_aux.midas import MidasDetector
+ from custom_controlnet_aux.midas import MidasDetector
 
  model = MidasDetector.from_pretrained().to(model_management.get_torch_device())
  #Dirty hack :))
@@ -41,7 +41,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, a=np.pi * 2.0, bg_threshold=0.1, resolution=512, **kwargs):
- from controlnet_aux.midas import MidasDetector
+ from custom_controlnet_aux.midas import MidasDetector
 
  # Ref: https://github.com/lllyasviel/ControlNet/blob/main/gradio_depth2image.py
  model = MidasDetector.from_pretrained().to(model_management.get_torch_device())

node_wrappers/mlsd.py

@@ -17,7 +17,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, score_threshold, dist_threshold, resolution=512, **kwargs):
- from controlnet_aux.mlsd import MLSDdetector
+ from custom_controlnet_aux.mlsd import MLSDdetector
 
  model = MLSDdetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, thr_v=score_threshold, thr_d=dist_threshold)

node_wrappers/normalbae.py

@@ -12,7 +12,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Normal and Depth Estimators"
 
  def execute(self, image, resolution=512, **kwargs):
- from controlnet_aux.normalbae import NormalBaeDetector
+ from custom_controlnet_aux.normalbae import NormalBaeDetector
 
  model = NormalBaeDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution)

node_wrappers/oneformer.py

@@ -12,7 +12,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Semantic Segmentation"
 
  def semantic_segmentate(self, image, resolution=512):
- from controlnet_aux.oneformer import OneformerSegmentor
+ from custom_controlnet_aux.oneformer import OneformerSegmentor
 
  model = OneformerSegmentor.from_pretrained(filename="150_16_swin_l_oneformer_coco_100ep.pth")
  model = model.to(model_management.get_torch_device())
@@ -31,7 +31,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Semantic Segmentation"
 
  def semantic_segmentate(self, image, resolution=512):
- from controlnet_aux.oneformer import OneformerSegmentor
+ from custom_controlnet_aux.oneformer import OneformerSegmentor
 
  model = OneformerSegmentor.from_pretrained(filename="250_16_swin_l_oneformer_ade20k_160k.pth")
  model = model.to(model_management.get_torch_device())

node_wrappers/openpose.py

@@ -18,7 +18,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Faces and Poses Estimators"
 
  def estimate_pose(self, image, detect_hand, detect_body, detect_face, resolution=512, **kwargs):
- from controlnet_aux.open_pose import OpenposeDetector
+ from custom_controlnet_aux.open_pose import OpenposeDetector
 
  detect_hand = detect_hand == "enable"
  detect_body = detect_body == "enable"

node_wrappers/pidinet.py

@@ -15,7 +15,7 @@ def INPUT_TYPES(s):
  CATEGORY = "ControlNet Preprocessors/Line Extractors"
 
  def execute(self, image, safe, resolution=512, **kwargs):
- from controlnet_aux.pidi import PidiNetDetector
+ from custom_controlnet_aux.pidi import PidiNetDetector
 
  model = PidiNetDetector.from_pretrained().to(model_management.get_torch_device())
  out = common_annotator_call(model, image, resolution=resolution, safe = safe == "enable")

node_wrappers/pose_keypoint_postprocess.py

@@ -8,7 +8,7 @@
 import torch
 import itertools
 
-from ..src.controlnet_aux.dwpose import draw_poses, draw_animalposes, decode_json_as_poses
+from ..src.custom_controlnet_aux.dwpose import draw_poses, draw_animalposes, decode_json_as_poses
 
 
 """