Update README.md

README.md

@@ -1,3 +1,35 @@
----
-license: mit
----
+---
+---
+license: apache-2.0
+tags:
+- image-segmentation
+- image-matting
+- background-removal
+- computer-vision
+- custom-architecture
+library_name: transformers
+pipeline_tag: image-segmentation
+---
+
+# MODNet – Fast Image Matting for Background Removal
+
+This repository provides a Hugging Face–compatible version of **MODNet (Mobile Object Detection Network)** for fast and high-quality foreground matting and background removal.
+
+The model is designed to produce **pixel-perfect alpha mattes**, handling fine details such as hair, fabric edges, and soft shadows, while remaining efficient enough for real-time CPU inference.
+
+---
+
+## 🔹 Model Details
+
+- **Architecture**: MODNet (custom architecture)
+- **Task**: Image matting / background removal
+- **Framework**: PyTorch
+- **Backbone**: MobileNetV2
+- **Input**: RGB image tensor `(B, 3, H, W)`
+- **Output**: `(semantic, detail, matte)` predictions
+
+This model uses a **custom architecture** and requires loading with:
+
+```python
+trust_remote_code=True
+---