Add mascot auto-detect nodes

README.md

@@ -20,6 +20,11 @@ Additionally, the Openpose Editor node from [toyxyz/ComfyUI-ultimate-openpose-ed
 - **pose_keypoint resize**: Resizes `POSE_KEYPOINT` to a target size (pads then scales to avoid stretching when aspect differs)
 - **pose_keypoint input**: Converts JSON text to KeyPoints
 - **pose_keypoint preview**: Converts KeyPoints to JSON
+- **(Down)Load Mascot DWPose Model**: Downloads and loads a mascot DWPose ONNX model from HuggingFace
+- **(Down)Load Mascot BBox Model**: Downloads and loads a mascot bbox ONNX model from HuggingFace
+- **Mascot DWPose Detector**: Detects mascot body pose as `POSE_KEYPOINT`
+- **Mascot BBox Detector**: Detects mascot part bounding boxes as `BOUNDING_BOX`
+- **pose_keypoint to dw_poses**: Converts 25-point `POSE_KEYPOINT` to SCAIL-Pose `DWPOSES`
 
 ## Installation
 ### Install via ComfyUI Manager
@@ -64,6 +69,10 @@ Please refer to example_workflows.
 2. **Incorrect body proportions after transformation with reference image**: The `pose_keypoint` and `reference_pose_keypoint` aspect ratios (canvas width/height) may not match. **ProportionChanger Reference** has `auto_resize_reference` (default ON) to automatically align the reference to the pose canvas size. If needed, use **pose_keypoint resize** to explicitly align `width`/`height`. Fine-tune individual body parts using the "ProportionChanger Params" node.
 3. **Nothing displays after transformation with reference image**: The reference image's pose estimation by DWPose has failed. Use OpenposeEditor or similar tools to input parameter values manually.
 
+### Mascot OpenPose Models
+
+Mascot OpenPose nodes download model artifacts from `grmchn/mascot-openpose-detect-test` on HuggingFace into `ComfyUI/models/mascot_body_detect`. The current test model package is CC-BY-NC 4.0 because it includes the ViTPose-L variant derived from a non-commercial pretrained backbone. The node code remains part of this repository, but use of the downloaded test models is subject to that model license.
+
 ## Attribution and Credits
 ### Special Thanks
 - **[kijai/ComfyUI-WanVideoWrapper](https://github.com/kijai/ComfyUI-WanVideoWrapper)**

README_ja.md

@@ -20,6 +20,11 @@
 - **pose_keypoint resize**: `POSE_KEYPOINT`を指定サイズにリサイズ（アスペクト比が違う場合はパディング→スケールで歪みを防ぐ）
 - **pose_keypoint input**: JSONテキストからKeyPointに変換する
 - **pose_keypoint preview**: KeyPointからJSONに変換する
+- **(Down)Load Mascot DWPose Model**: HuggingFaceからマスコット用DWPose ONNXモデルをダウンロードして読み込む
+- **(Down)Load Mascot BBox Model**: HuggingFaceからマスコット用bbox ONNXモデルをダウンロードして読み込む
+- **Mascot DWPose Detector**: マスコットの姿勢を`POSE_KEYPOINT`として検出する
+- **Mascot BBox Detector**: マスコットのパーツbboxを`BOUNDING_BOX`として検出する
+- **pose_keypoint to dw_poses**: 25点`POSE_KEYPOINT`をSCAIL-Pose用`DWPOSES`に変換する
 
 ## インストール
 ### ComfyUI Managerでインストール
@@ -65,6 +70,10 @@ example_workflowsを参照してください。
 2. **リファレンス画像ありでプロポーション変換した後の体型がおかしい**: `pose_keypoint`と`reference_pose_keypoint`の縦横比（canvas幅/高さ）が一致していない可能性があります。**ProportionChanger Reference**の`auto_resize_reference`（デフォルトON）でリファレンス側を自動で揃えます。必要に応じて**pose_keypoint resize**ノードで明示的に`width`/`height`を揃えてください。体の各パーツの微調整は「ProportionChanger Params」ノードで行ってください。
 3. **リファレンス画像ありでプロポーション変換した後に何も表示されない**:リファレンス画像のDWPoseによる姿勢推定が失敗しています。OpenposeEditorなどを利用してパラメータの数値を入力してください。
 
+### Mascot OpenPoseモデル
+
+Mascot OpenPoseノードは、HuggingFaceの`grmchn/mascot-openpose-detect-test`から`ComfyUI/models/mascot_body_detect`へモデルをダウンロードします。現在のtestモデルパッケージは、非商用のpretrained backboneに由来するViTPose-L variantを含むため、CC-BY-NC 4.0です。ノードコードはこのリポジトリの一部ですが、ダウンロードされたtestモデルの利用はモデル側のライセンスに従います。
+
 ## 帰属とクレジット
 ### Special Thanks
 - **[kijai/ComfyUI-WanVideoWrapper](https://github.com/kijai/ComfyUI-WanVideoWrapper)**

nodes.py

@@ -5,6 +5,16 @@ Backward compatibility maintained for existing workflows
 
 from .utils import log
 import json
+import os
+
+try:
+    import folder_paths
+    folder_paths.add_model_folder_path(
+        "mascot_body_detect",
+        os.path.join(folder_paths.models_dir, "mascot_body_detect"),
+    )
+except ImportError:
+    folder_paths = None
 
 # Import all nodes from our organized structure
 from .proportion_changer import (
@@ -15,6 +25,11 @@ from .proportion_changer import (
     ProportionChangerInterpolator,
     PoseDataToPoseKeypoint,
     PoseKeypointResize,
+    DownloadAndLoadMascotDWPoseModel,
+    DownloadAndLoadMascotBBoxModel,
+    MascotDWPoseDetector,
+    MascotBBoxDetector,
+    ConvertToSCAILPose,
     # TODO: Re-enable after fixing Kalman filter issues
     # ProportionChangerKeypointDenoiser,
     # ProportionChangerKeypointDenoiserAdvanced
@@ -208,6 +223,13 @@ NODE_CLASS_MAPPINGS = {
     "PoseKeypointResize": PoseKeypointResize,
     "PoseJSONToPoseKeypoint": PoseJSONToPoseKeypoint,
     "PoseKeypointPreview": PoseKeypointPreview,
+
+    # Mascot OpenPose nodes
+    "DownloadAndLoadMascotDWPoseModel": DownloadAndLoadMascotDWPoseModel,
+    "DownloadAndLoadMascotBBoxModel": DownloadAndLoadMascotBBoxModel,
+    "MascotDWPoseDetector": MascotDWPoseDetector,
+    "MascotBBoxDetector": MascotBBoxDetector,
+    "ConvertToSCAILPose": ConvertToSCAILPose,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -227,4 +249,11 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "PoseKeypointResize": "pose_keypoint resize",
     "PoseJSONToPoseKeypoint": "pose_keypoint input",
     "PoseKeypointPreview": "pose_keypoint preview",
+
+    # Mascot OpenPose nodes
+    "DownloadAndLoadMascotDWPoseModel": "(Down)Load Mascot DWPose Model",
+    "DownloadAndLoadMascotBBoxModel": "(Down)Load Mascot BBox Model",
+    "MascotDWPoseDetector": "Mascot DWPose Detector",
+    "MascotBBoxDetector": "Mascot BBox Detector",
+    "ConvertToSCAILPose": "pose_keypoint to dw_poses",
 }

proportion_changer/__init__.py

@@ -34,6 +34,15 @@ from .converter_nodes import (
     PoseKeypointResize,
 )
 
+# Mascot OpenPose nodes
+from .mascot_nodes import (
+    DownloadAndLoadMascotDWPoseModel,
+    DownloadAndLoadMascotBBoxModel,
+    MascotDWPoseDetector,
+    MascotBBoxDetector,
+    ConvertToSCAILPose,
+)
+
 # Import keypoint denoiser node classes
 from .keypoint_denoiser_node import (
     ProportionChangerKeypointDenoiser,
@@ -59,6 +68,13 @@ __all__ = [
     # Converter nodes
     "PoseDataToPoseKeypoint",
     "PoseKeypointResize",
+
+    # Mascot OpenPose nodes
+    "DownloadAndLoadMascotDWPoseModel",
+    "DownloadAndLoadMascotBBoxModel",
+    "MascotDWPoseDetector",
+    "MascotBBoxDetector",
+    "ConvertToSCAILPose",
     
     # KeyPoint Denoiser nodes
     "ProportionChangerKeypointDenoiser",

requirements.txt

@@ -7,6 +7,8 @@ opencv-python
 
 # Progress bars and utilities  
 tqdm
+huggingface_hub
 
-# Optional: ONNX Runtime (for ONNX-based pose detection - currently not used in active nodes)
-# onnxruntime
+# ONNX Runtime for Mascot OpenPose nodes. Install onnxruntime-gpu instead if
+# your ComfyUI environment manages CUDA providers separately.
+onnxruntime