wow

.gitignore

@@ -0,0 +1,142 @@
+# Custom
+e_*
+.vscode
+ckpt
+preds
+evaluation/eval-*
+nohup.out*
+tmp*
+*.pth
+core-*-python-*
+.DS_Store
+__MACOSX/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

BiRefNet_config.py

@@ -0,0 +1,11 @@
+from transformers import PretrainedConfig
+
+class BiRefNetConfig(PretrainedConfig):
+    model_type = "SegformerForSemanticSegmentation"
+    def __init__(
+        self,
+        bb_pretrained=False,
+        **kwargs
+    ):
+        self.bb_pretrained = bb_pretrained
+        super().__init__(**kwargs)

handler.py

@@ -1,7 +1,7 @@
 # handler.py — BiRefNet endpoint handler
 # Fully instrumented for debugging input structure and format.
 
-from typing import Dict, Any, Tuple
+from typing import Dict, Any, Tuple, Optional
 import os
 import io
 import base64
@@ -79,6 +79,25 @@ usage_to_weights_file = {
 usage = "General"
 resolution = (1024, 1024)
 half_precision = True
+SEGMENTATION_THRESHOLD = 0.05
+
+
+def extract_bbox_from_mask(mask: Image.Image, threshold: float = SEGMENTATION_THRESHOLD) -> Optional[Dict[str, int]]:
+    """Compute a bounding box for the non-zero region of the mask."""
+    mask_gray = mask.convert("L")
+    mask_array = np.array(mask_gray, dtype=np.float32) / 255.0
+    binary = mask_array > threshold
+    if not np.any(binary):
+        return None
+    ys, xs = np.where(binary)
+    x_min, x_max = xs.min(), xs.max()
+    y_min, y_max = ys.min(), ys.max()
+    return {
+        "x": int(x_min),
+        "y": int(y_min),
+        "width": int(x_max - x_min + 1),
+        "height": int(y_max - y_min + 1),
+    }
 
 # ======================================================
 # Endpoint Handler
@@ -156,12 +175,23 @@ class EndpointHandler:
 
         pred = preds[0].squeeze()
         pred_pil = transforms.ToPILImage()(pred)
+        mask_resized = pred_pil.resize(image.size)
+        mask_bbox = extract_bbox_from_mask(mask_resized)
 
         image_masked = refine_foreground(image, pred_pil)
-        image_masked.putalpha(pred_pil.resize(image.size))
+        image_masked.putalpha(mask_resized)
 
         buffer = io.BytesIO()
         image_masked.save(buffer, format="PNG")
         encoded_result = base64.b64encode(buffer.getvalue()).decode("utf-8")
-        return {"image_base64": encoded_result}
 
+        mask_buffer = io.BytesIO()
+        mask_resized.save(mask_buffer, format="PNG")
+        encoded_mask = base64.b64encode(mask_buffer.getvalue()).decode("utf-8")
+
+        return {
+            "image_base64": encoded_result,
+            "mask_base64": encoded_mask,
+            "mask_bbox": mask_bbox,
+            "mask_size": {"width": mask_resized.width, "height": mask_resized.height},
+        }