Merge pull request #18 from yakhyo/feat-20251115

ref: Add comprehensive test suite and enhance model functionality
2025-12-30 00:52:25 +00:00 · 2025-11-15 21:32:10 +09:00
parent df673c4a3f fe3e70a352
commit 11363fe0a8
28 changed files with 2014 additions and 591 deletions
--- a/MODELS.md
+++ b/MODELS.md
@@ -113,13 +113,15 @@ embedding = recognizer.get_normalized_embedding(image, landmarks)

 Lightweight face recognition optimized for mobile devices.

-| Model Name      | Backbone        | Params | Size | Use Case           |
-|-----------------|-----------------|--------|------|--------------------|
-| `MNET_025`      | MobileNetV1 0.25| 0.2M   | 1MB  | Ultra-lightweight  |
-| `MNET_V2` ⭐    | MobileNetV2     | 1.0M   | 4MB  | **Mobile/Edge**    |
-| `MNET_V3_SMALL` | MobileNetV3-S   | 0.8M   | 3MB  | Mobile optimized   |
-| `MNET_V3_LARGE` | MobileNetV3-L   | 2.5M   | 10MB | Balanced mobile    |
+| Model Name      | Backbone        | Params | Size | LFW   | CALFW | CPLFW | AgeDB-30 | Use Case           |
+|-----------------|-----------------|--------|------|-------|-------|-------|----------|--------------------|
+| `MNET_025`      | MobileNetV1 0.25| 0.36M  | 1MB  | 98.76%| 92.02%| 82.37%| 90.02%   | Ultra-lightweight  |
+| `MNET_V2` ⭐    | MobileNetV2     | 2.29M  | 4MB  | 99.55%| 94.87%| 86.89%| 95.16%   | **Mobile/Edge**    |
+| `MNET_V3_SMALL` | MobileNetV3-S   | 1.25M  | 3MB  | 99.30%| 93.77%| 85.29%| 92.79%   | Mobile optimized   |
+| `MNET_V3_LARGE` | MobileNetV3-L   | 3.52M  | 10MB | 99.53%| 94.56%| 86.79%| 95.13%   | Balanced mobile    |

+**Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
+**Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
 **Note**: These models are lightweight alternatives to ArcFace for resource-constrained environments

 #### Usage
@@ -138,12 +140,14 @@ recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)

 Face recognition using angular softmax loss.

-| Model Name  | Backbone | Params | Size | Use Case              |
-|-------------|----------|--------|------|----------------------|
-| `SPHERE20`  | Sphere20 | 13.0M  | 50MB | Research/Comparison  |
-| `SPHERE36`  | Sphere36 | 24.2M  | 92MB | Research/Comparison  |
+| Model Name  | Backbone | Params | Size | LFW   | CALFW | CPLFW | AgeDB-30 | Use Case              |
+|-------------|----------|--------|------|-------|-------|-------|----------|----------------------|
+| `SPHERE20`  | Sphere20 | 24.5M  | 50MB | 99.67%| 95.61%| 88.75%| 96.58%   | Research/Comparison  |
+| `SPHERE36`  | Sphere36 | 34.6M  | 92MB | 99.72%| 95.64%| 89.92%| 96.83%   | Research/Comparison  |

-**Note**: SphereFace uses angular softmax loss, an earlier approach before ArcFace
+**Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
+**Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
+**Note**: SphereFace uses angular softmax loss, an earlier approach before ArcFace. These models provide good accuracy with moderate resource requirements.

 #### Usage

@@ -264,10 +268,10 @@ emotion, confidence = predictor.predict(image, landmarks)
 ### By Hardware

 #### Apple Silicon (M1/M2/M3/M4)
-**Recommended**: All models work well with CoreML acceleration
+**Recommended**: All models work well with ARM64 optimizations (automatically included)

 ```bash
-pip install uniface[silicon]
+pip install uniface
 ```

 **Recommended models**:
--- a/QUICKSTART.md
+++ b/QUICKSTART.md
@@ -7,8 +7,8 @@ Get up and running with UniFace in 5 minutes! This guide covers the most common
 ## Installation

 ```bash
-# macOS (Apple Silicon)
-pip install uniface[silicon]
+# macOS (Apple Silicon) - automatically includes ARM64 optimizations
+pip install uniface

 # Linux/Windows with NVIDIA GPU
 pip install uniface[gpu]
@@ -114,9 +114,9 @@ if faces1 and faces2:

    # Interpret result
    if similarity > 0.6:
-        print(f"✅ Same person (similarity: {similarity:.3f})")
+        print(f"Same person (similarity: {similarity:.3f})")
    else:
-        print(f"❌ Different people (similarity: {similarity:.3f})")
+        print(f"Different people (similarity: {similarity:.3f})")
 else:
    print("No faces detected")
 ```
@@ -264,31 +264,46 @@ print("Done!")

 Choose the right model for your use case:

+### Detection Models
+
 ```python
-from uniface import create_detector
+from uniface.detection import RetinaFace, SCRFD
 from uniface.constants import RetinaFaceWeights, SCRFDWeights

 # Fast detection (mobile/edge devices)
-detector = create_detector(
-    'retinaface',
+detector = RetinaFace(
    model_name=RetinaFaceWeights.MNET_025,
    conf_thresh=0.7
 )

 # Balanced (recommended)
-detector = create_detector(
-    'retinaface',
+detector = RetinaFace(
    model_name=RetinaFaceWeights.MNET_V2
 )

 # High accuracy (server/GPU)
-detector = create_detector(
-    'scrfd',
+detector = SCRFD(
    model_name=SCRFDWeights.SCRFD_10G_KPS,
    conf_thresh=0.5
 )
 ```

+### Recognition Models
+
+```python
+from uniface import ArcFace, MobileFace, SphereFace
+from uniface.constants import MobileFaceWeights, SphereFaceWeights
+
+# ArcFace (recommended for most use cases)
+recognizer = ArcFace()  # Best accuracy
+
+# MobileFace (lightweight for mobile/edge)
+recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)  # Fast, small size
+
+# SphereFace (angular margin approach)
+recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)  # Alternative method
+```
+
 ---

 ## Common Issues
@@ -316,20 +331,22 @@ print("Available providers:", ort.get_available_providers())

 ### 3. Slow Performance on Mac

-Make sure you installed with CoreML support:
+The standard installation includes ARM64 optimizations for Apple Silicon. If performance is slow, verify you're using the ARM64 build of Python:

 ```bash
-pip install uniface[silicon]
+python -c "import platform; print(platform.machine())"
+# Should show: arm64 (not x86_64)
 ```

 ### 4. Import Errors

 ```python
-# ✅ Correct imports
-from uniface import RetinaFace, ArcFace, Landmark106
-from uniface.detection import create_detector
+# Correct imports
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.landmark import Landmark106

-# ❌ Wrong imports
+# Wrong imports
 from uniface import retinaface  # Module, not class
 ```

--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@
 - **Face Recognition**: ArcFace, MobileFace, and SphereFace embeddings
 - **Attribute Analysis**: Age, gender, and emotion detection
 - **Face Alignment**: Precise alignment for downstream tasks
- **Hardware Acceleration**: CoreML (Apple Silicon), CUDA (NVIDIA), CPU fallback
+- **Hardware Acceleration**: ARM64 optimizations (Apple Silicon), CUDA (NVIDIA), CPU fallback
 - **Simple API**: Intuitive factory functions and clean interfaces
 - **Production-Ready**: Type hints, comprehensive logging, PEP8 compliant

@@ -39,27 +39,19 @@ pip install uniface

 #### macOS (Apple Silicon - M1/M2/M3/M4)

-For optimal performance with **CoreML acceleration** (3-5x faster):
+For Apple Silicon Macs, the standard installation automatically includes optimized ARM64 support:

 ```bash
-# Standard installation (CPU only)
 pip install uniface
-
-# With CoreML acceleration (recommended for M-series chips)
-pip install uniface[silicon]
 ```

-**Verify CoreML is available:**
-```python
-import onnxruntime as ort
-print(ort.get_available_providers())
-# Should show: ['CoreMLExecutionProvider', 'CPUExecutionProvider']
-```
+The base `onnxruntime` package (included with uniface) has native Apple Silicon support with ARM64 optimizations built-in since version 1.13+.

 #### Linux/Windows with NVIDIA GPU

+For CUDA acceleration on NVIDIA GPUs:
+
 ```bash
-# With CUDA acceleration
 pip install uniface[gpu]
 ```

@@ -172,28 +164,29 @@ print(f"{gender}, {age} years old")
 ### Factory Functions (Recommended)

 ```python
-from uniface import create_detector, create_recognizer, create_landmarker
+from uniface.detection import RetinaFace, SCRFD
+from uniface.recognition import ArcFace
+from uniface.landmark import Landmark106

 # Create detector with default settings
-detector = create_detector('retinaface')
+detector = RetinaFace()

 # Create with custom config
-detector = create_detector(
-    'scrfd',
+detector = SCRFD(
    model_name='scrfd_10g_kps',
    conf_thresh=0.8,
    input_size=(640, 640)
 )

 # Recognition and landmarks
-recognizer = create_recognizer('arcface')
-landmarker = create_landmarker('2d106det')
+recognizer = ArcFace()
+landmarker = Landmark106()
 ```

 ### Direct Model Instantiation

 ```python
-from uniface import RetinaFace, SCRFD, ArcFace, MobileFace
+from uniface import RetinaFace, SCRFD, ArcFace, MobileFace, SphereFace
 from uniface.constants import RetinaFaceWeights

 # Detection
@@ -206,6 +199,7 @@ detector = RetinaFace(
 # Recognition
 recognizer = ArcFace()  # Uses default weights
 recognizer = MobileFace()  # Lightweight alternative
+recognizer = SphereFace()  # Angular softmax alternative
 ```

 ### High-Level Detection API
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "uniface"
-version = "1.0.0"
+version = "1.1.0"
 description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection"
 readme = "README.md"
 license = { text = "MIT" }
@@ -21,7 +21,6 @@ requires-python = ">=3.10"
 [project.optional-dependencies]
 dev = ["pytest>=7.0.0"]
 gpu = ["onnxruntime-gpu>=1.16.0"]
-silicon = ["onnxruntime-silicon>=1.16.0"]

 [project.urls]
 Homepage = "https://github.com/yakhyo/uniface"
--- a/scripts/README.md
+++ b/scripts/README.md
@@ -1,18 +1,97 @@
-### `download_model.py`
+# Scripts

-# Download all models
+Collection of example scripts demonstrating UniFace functionality.
+
+## Available Scripts
+
+- `run_detection.py` - Face detection on images
+- `run_age_gender.py` - Age and gender prediction
+- `run_landmarks.py` - Facial landmark detection
+- `run_recognition.py` - Face recognition and embeddings
+- `run_face_search.py` - Face search and matching
+- `run_video_detection.py` - Video processing with face detection
+- `batch_process.py` - Batch processing of image folders
+- `download_model.py` - Download and manage models
+
+## Quick Start

 ```bash
-python scripts/download_model.py
+# Face detection
+python scripts/run_detection.py --image assets/test.jpg
+
+# Age and gender detection
+python scripts/run_age_gender.py --image assets/test.jpg
+
+# Webcam demo
+python scripts/run_age_gender.py --webcam
+
+# Batch processing
+python scripts/batch_process.py --input images/ --output results/
 ```

-# Download just RESNET18
+## Import Examples

-```bash
-python scripts/download_model.py --model RESNET18
+The scripts use direct class imports for better developer experience:
+
+```python
+# Face Detection
+from uniface.detection import RetinaFace, SCRFD
+
+detector = RetinaFace()  # or SCRFD()
+faces = detector.detect(image)
+
+# Face Recognition
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+recognizer = ArcFace()  # or MobileFace(), SphereFace()
+embedding = recognizer.get_embedding(image, landmarks)
+
+# Age & Gender
+from uniface.attribute import AgeGender
+
+age_gender = AgeGender()
+gender, age = age_gender.predict(image, bbox)
+
+# Landmarks
+from uniface.landmark import Landmark106
+
+landmarker = Landmark106()
+landmarks = landmarker.get_landmarks(image, bbox)
 ```

-### `run_inference.py`
+## Available Classes
+
+**Detection:**
+- `RetinaFace` - High accuracy face detection
+- `SCRFD` - Fast face detection
+
+**Recognition:**
+- `ArcFace` - High accuracy face recognition
+- `MobileFace` - Lightweight face recognition
+- `SphereFace` - Alternative face recognition
+
+**Attributes:**
+- `AgeGender` - Age and gender prediction
+
+**Landmarks:**
+- `Landmark106` - 106-point facial landmarks
+
+## Common Options
+
+Most scripts support:
+- `--help` - Show usage information
+- `--verbose` - Enable detailed logging
+- `--detector` - Choose detector (retinaface, scrfd)
+- `--threshold` - Set confidence threshold
+
+## Testing
+
+Run basic functionality test:
 ```bash
-python scripts/run_inference.py --image assets/test.jpg --model MNET_V2 --iterations 10
-```
+python scripts/run_detection.py --image assets/test.jpg
+```
+
+For comprehensive testing, see the main project tests:
+```bash
+pytest tests/
+```
--- a/scripts/TESTING.md
+++ b/scripts/TESTING.md
@@ -1,389 +0,0 @@
-# Testing Scripts Guide
-
-Complete guide to testing all scripts in the `scripts/` directory.
-
---
-
-## 📁 Available Scripts
-
-1. **download_model.py** - Download and verify model weights
-2. **run_detection.py** - Face detection on images
-3. **run_recognition.py** - Face recognition (extract embeddings)
-4. **run_face_search.py** - Real-time face matching with webcam
-5. **sha256_generate.py** - Generate SHA256 checksums for models
-
---
-
-## Testing Each Script
-
-### 1. Test Model Download
-
-```bash
-# Download a specific model
-python scripts/download_model.py --model MNET_V2
-
-# Download all RetinaFace models (takes ~5 minutes, ~200MB)
-python scripts/download_model.py
-
-# Verify models are cached
-ls -lh ~/.uniface/models/
-```
-
-**Expected Output:**
-```
-📥 Downloading model: retinaface_mnet_v2
-2025-11-08 00:00:00 - INFO - Downloading model 'RetinaFaceWeights.MNET_V2' from https://...
-Downloading ~/.uniface/models/retinaface_mnet_v2.onnx: 100%|████| 3.5M/3.5M
-2025-11-08 00:00:05 - INFO - Successfully downloaded 'RetinaFaceWeights.MNET_V2'
-✅ All requested weights are ready and verified.
-```
-
---
-
-### 2. Test Face Detection
-
-```bash
-# Basic detection
-python scripts/run_detection.py --image assets/test.jpg
-
-# With custom settings
-python scripts/run_detection.py \
-    --image assets/test.jpg \
-    --method scrfd \
-    --threshold 0.7 \
-    --save_dir outputs
-
-# Benchmark mode (100 iterations)
-python scripts/run_detection.py \
-    --image assets/test.jpg \
-    --iterations 100
-```
-
-**Expected Output:**
-```
-Initializing detector: retinaface
-2025-11-08 00:00:00 - INFO - Initializing RetinaFace with model=RetinaFaceWeights.MNET_V2...
-2025-11-08 00:00:01 - INFO - CoreML acceleration enabled (Apple Silicon)
-✅ Output saved at: outputs/test_out.jpg
-[1/1] ⏱️ Inference time: 0.0234 seconds
-```
-
-**Verify Output:**
-```bash
-# Check output image was created
-ls -lh outputs/test_out.jpg
-
-# View the image (macOS)
-open outputs/test_out.jpg
-```
-
---
-
-### 3. Test Face Recognition (Embedding Extraction)
-
-```bash
-# Extract embeddings from an image
-python scripts/run_recognition.py --image assets/test.jpg
-
-# With different models
-python scripts/run_recognition.py \
-    --image assets/test.jpg \
-    --detector scrfd \
-    --recognizer mobileface
-```
-
-**Expected Output:**
-```
-Initializing detector: retinaface
-Initializing recognizer: arcface
-2025-11-08 00:00:00 - INFO - Successfully initialized face encoder from ~/.uniface/models/w600k_mbf.onnx
-Detected 1 face(s). Extracting embeddings for the first face...
-  - Embedding shape: (1, 512)
-  - L2 norm of unnormalized embedding: 64.2341
-  - L2 norm of normalized embedding: 1.0000
-```
-
---
-
-### 4. Test Real-Time Face Search (Webcam)
-
-**Prerequisites:**
- Webcam connected
- Reference image with a clear face
-
-```bash
-# Basic usage
-python scripts/run_face_search.py --image assets/test.jpg
-
-# With custom models
-python scripts/run_face_search.py \
-    --image assets/test.jpg \
-    --detector scrfd \
-    --recognizer arcface
-```
-
-**Expected Behavior:**
-1. Webcam window opens
-2. Faces are detected in real-time
-3. Green box = Match (similarity > 0.4)
-4. Red box = Unknown (similarity < 0.4)
-5. Press 'q' to quit
-
-**Expected Output:**
-```
-Initializing models...
-2025-11-08 00:00:00 - INFO - CoreML acceleration enabled (Apple Silicon)
-Extracting reference embedding...
-Webcam started. Press 'q' to quit.
-```
-
-**Troubleshooting:**
-```bash
-# If webcam doesn't open
-python -c "import cv2; cap = cv2.VideoCapture(0); print('Webcam OK' if cap.isOpened() else 'Webcam FAIL')"
-
-# If no faces detected
-# - Ensure good lighting
-# - Face should be frontal and clearly visible
-# - Try lowering threshold: edit script line 29, change 0.4 to 0.3
-```
-
---
-
-### 5. Test SHA256 Generator (For Developers)
-
-```bash
-# Generate checksum for a model file
-python scripts/sha256_generate.py ~/.uniface/models/retinaface_mnet_v2.onnx
-
-# Generate for all models
-for model in ~/.uniface/models/*.onnx; do
-    python scripts/sha256_generate.py "$model"
-done
-```
-
---
-
-## 🔍 Quick Verification Tests
-
-### Test 1: Imports Work
-
-```bash
-python -c "
-from uniface.detection import create_detector
-from uniface.recognition import create_recognizer
-print('✅ Imports successful')
-"
-```
-
-### Test 2: Models Download
-
-```bash
-python -c "
-from uniface import RetinaFace
-detector = RetinaFace()
-print('✅ Model downloaded and loaded')
-"
-```
-
-### Test 3: Detection Works
-
-```bash
-python -c "
-import cv2
-import numpy as np
-from uniface import RetinaFace
-
-detector = RetinaFace()
-image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-faces = detector.detect(image)
-print(f'✅ Detection works, found {len(faces)} faces')
-"
-```
-
-### Test 4: Recognition Works
-
-```bash
-python -c "
-import cv2
-import numpy as np
-from uniface import RetinaFace, ArcFace
-
-detector = RetinaFace()
-recognizer = ArcFace()
-image = cv2.imread('assets/test.jpg')
-faces = detector.detect(image)
-if faces:
-    landmarks = np.array(faces[0]['landmarks'])
-    embedding = recognizer.get_normalized_embedding(image, landmarks)
-    print(f'✅ Recognition works, embedding shape: {embedding.shape}')
-else:
-    print('⚠️ No faces detected in test image')
-"
-```
-
---
-
-## End-to-End Test Workflow
-
-Run this complete workflow to verify everything works:
-
-```bash
-#!/bin/bash
-# Save as test_all_scripts.sh
-
-echo "=== Testing UniFace Scripts ==="
-echo ""
-
-# Test 1: Download models
-echo "1️⃣ Testing model download..."
-python scripts/download_model.py --model MNET_V2
-if [ $? -eq 0 ]; then
-    echo "✅ Model download: PASS"
-else
-    echo "❌ Model download: FAIL"
-    exit 1
-fi
-echo ""
-
-# Test 2: Face detection
-echo "2️⃣ Testing face detection..."
-python scripts/run_detection.py --image assets/test.jpg --save_dir /tmp/uniface_test
-if [ $? -eq 0 ] && [ -f /tmp/uniface_test/test_out.jpg ]; then
-    echo "✅ Face detection: PASS"
-else
-    echo "❌ Face detection: FAIL"
-    exit 1
-fi
-echo ""
-
-# Test 3: Face recognition
-echo "3️⃣ Testing face recognition..."
-python scripts/run_recognition.py --image assets/test.jpg > /tmp/uniface_recognition.log
-if [ $? -eq 0 ] && grep -q "Embedding shape" /tmp/uniface_recognition.log; then
-    echo "✅ Face recognition: PASS"
-else
-    echo "❌ Face recognition: FAIL"
-    exit 1
-fi
-echo ""
-
-echo "=== All Tests Passed! 🎉 ==="
-```
-
-**Run the test suite:**
-```bash
-chmod +x test_all_scripts.sh
-./test_all_scripts.sh
-```
-
---
-
-## Performance Benchmarking
-
-### Benchmark Detection Speed
-
-```bash
-# Test different models
-for model in retinaface scrfd; do
-    echo "Testing $model..."
-    python scripts/run_detection.py \
-        --image assets/test.jpg \
-        --method $model \
-        --iterations 50
-done
-```
-
-### Benchmark Recognition Speed
-
-```bash
-# Test different recognizers
-for recognizer in arcface mobileface; do
-    echo "Testing $recognizer..."
-    time python scripts/run_recognition.py \
-        --image assets/test.jpg \
-        --recognizer $recognizer
-done
-```
-
---
-
-## 🐛 Common Issues
-
-### Issue: "No module named 'uniface'"
-
-```bash
-# Solution: Install in editable mode
-pip install -e .
-```
-
-### Issue: "Failed to load image"
-
-```bash
-# Check image exists
-ls -lh assets/test.jpg
-
-# Try with absolute path
-python scripts/run_detection.py --image $(pwd)/assets/test.jpg
-```
-
-### Issue: "No faces detected"
-
-```bash
-# Lower confidence threshold
-python scripts/run_detection.py \
-    --image assets/test.jpg \
-    --threshold 0.3
-```
-
-### Issue: Models downloading slowly
-
-```bash
-# Check internet connection
-curl -I https://github.com/yakhyo/uniface/releases
-
-# Or download manually
-wget https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv2.onnx \
-    -O ~/.uniface/models/retinaface_mnet_v2.onnx
-```
-
-### Issue: CoreML not available on Mac
-
-```bash
-# Install CoreML-enabled ONNX Runtime
-pip uninstall onnxruntime
-pip install onnxruntime-silicon
-
-# Verify
-python -c "import onnxruntime as ort; print(ort.get_available_providers())"
-# Should show: ['CoreMLExecutionProvider', 'CPUExecutionProvider']
-```
-
---
-
-## ✅ Script Status Summary
-
-| Script                | Status | API Updated | Tested |
-|-----------------------|--------|-------------|--------|
-| download_model.py     | ✅     | ✅          | ✅     |
-| run_detection.py      | ✅     | ✅          | ✅     |
-| run_recognition.py    | ✅     | ✅          | ✅     |
-| run_face_search.py    | ✅     | ✅          | ✅     |
-| sha256_generate.py    | ✅     | N/A         | ✅     |
-
-All scripts are updated and working with the new dict-based API! 🎉
-
---
-
-## 📝 Notes
-
- All scripts now use the factory functions (`create_detector`, `create_recognizer`)
- Scripts work with the new dict-based detection API
- Model download bug is fixed (enum vs string issue)
- CoreML acceleration is automatically detected on Apple Silicon
- All scripts include proper error handling
-
---
-
-Need help with a specific script? Check the main [README.md](../README.md) or [QUICKSTART.md](../QUICKSTART.md)!
-
--- a/scripts/batch_process.py
+++ b/scripts/batch_process.py
@@ -0,0 +1,157 @@
+"""Batch Image Processing Script"""
+
+import os
+import cv2
+import argparse
+from pathlib import Path
+from tqdm import tqdm
+
+from uniface import RetinaFace, SCRFD
+from uniface.visualization import draw_detections
+
+
+def get_image_files(input_dir: Path, extensions: tuple) -> list:
+    image_files = []
+    for ext in extensions:
+        image_files.extend(input_dir.glob(f"*.{ext}"))
+        image_files.extend(input_dir.glob(f"*.{ext.upper()}"))
+
+    return sorted(image_files)
+
+
+def process_single_image(detector, image_path: Path, output_dir: Path,
+                        vis_threshold: float, skip_existing: bool) -> dict:
+    output_path = output_dir / f"{image_path.stem}_detected{image_path.suffix}"
+
+    # Skip if already processed
+    if skip_existing and output_path.exists():
+        return {"status": "skipped", "faces": 0}
+
+    # Load image
+    image = cv2.imread(str(image_path))
+    if image is None:
+        return {"status": "error", "error": "Failed to load image"}
+
+    # Detect faces
+    try:
+        faces = detector.detect(image)
+    except Exception as e:
+        return {"status": "error", "error": str(e)}
+
+    # Draw detections
+    bboxes = [f['bbox'] for f in faces]
+    scores = [f['confidence'] for f in faces]
+    landmarks = [f['landmarks'] for f in faces]
+    draw_detections(image, bboxes, scores, landmarks, vis_threshold=vis_threshold)
+
+    # Add face count
+    cv2.putText(image, f"Faces: {len(faces)}", (10, 30),
+               cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+
+    # Save result
+    cv2.imwrite(str(output_path), image)
+
+    return {"status": "success", "faces": len(faces)}
+
+
+def batch_process(detector, input_dir: str, output_dir: str, extensions: tuple,
+                 vis_threshold: float, skip_existing: bool):
+    input_path = Path(input_dir)
+    output_path = Path(output_dir)
+
+    # Create output directory
+    output_path.mkdir(parents=True, exist_ok=True)
+
+    # Get image files
+    image_files = get_image_files(input_path, extensions)
+
+    if not image_files:
+        print(f"No image files found in '{input_dir}' with extensions {extensions}")
+        return
+
+    print(f"Input: {input_dir}")
+    print(f"Output: {output_dir}")
+    print(f"Found {len(image_files)} images\n")
+
+    # Process images
+    results = {
+        "success": 0,
+        "skipped": 0,
+        "error": 0,
+        "total_faces": 0
+    }
+
+    with tqdm(image_files, desc="Processing images", unit="img") as pbar:
+        for image_path in pbar:
+            result = process_single_image(
+                detector, image_path, output_path,
+                vis_threshold, skip_existing
+            )
+
+            if result["status"] == "success":
+                results["success"] += 1
+                results["total_faces"] += result["faces"]
+                pbar.set_postfix({"faces": result["faces"]})
+            elif result["status"] == "skipped":
+                results["skipped"] += 1
+            else:
+                results["error"] += 1
+                print(f"\nError processing {image_path.name}: {result.get('error', 'Unknown error')}")
+
+    # Print summary
+    print(f"\nBatch processing complete!")
+    print(f"   Total images: {len(image_files)}")
+    print(f"   Successfully processed: {results['success']}")
+    print(f"   Skipped: {results['skipped']}")
+    print(f"   Errors: {results['error']}")
+    print(f"   Total faces detected: {results['total_faces']}")
+    if results['success'] > 0:
+        print(f"   Average faces per image: {results['total_faces']/results['success']:.2f}")
+    print(f"\nResults saved to: {output_dir}")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Batch process images with face detection")
+    parser.add_argument("--input", type=str, required=True,
+                       help="Input directory containing images")
+    parser.add_argument("--output", type=str, required=True,
+                       help="Output directory for processed images")
+    parser.add_argument("--detector", type=str, default="retinaface",
+                       choices=['retinaface', 'scrfd'], help="Face detector to use")
+    parser.add_argument("--threshold", type=float, default=0.6,
+                       help="Confidence threshold for visualization")
+    parser.add_argument("--extensions", type=str, default="jpg,jpeg,png,bmp",
+                       help="Comma-separated list of image extensions")
+    parser.add_argument("--skip_existing", action="store_true",
+                       help="Skip files that already exist in output directory")
+    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
+
+    args = parser.parse_args()
+
+    # Check input directory exists
+    if not Path(args.input).exists():
+        print(f"Error: Input directory '{args.input}' does not exist")
+        return
+
+    if args.verbose:
+        from uniface import enable_logging
+        enable_logging()
+
+    # Parse extensions
+    extensions = tuple(ext.strip() for ext in args.extensions.split(','))
+
+    # Initialize detector
+    print(f"Initializing detector: {args.detector}")
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()
+    print("Detector initialized\n")
+
+    # Process batch
+    batch_process(detector, args.input, args.output, extensions,
+                 args.threshold, args.skip_existing)
+
+
+if __name__ == "__main__":
+    main()
--- a/scripts/download_model.py
+++ b/scripts/download_model.py
@@ -1,31 +1,77 @@
 import argparse
-from uniface.constants import RetinaFaceWeights
+from uniface.constants import (
+    RetinaFaceWeights, SphereFaceWeights, MobileFaceWeights, ArcFaceWeights,
+    SCRFDWeights, DDAMFNWeights, AgeGenderWeights, LandmarkWeights
+)
 from uniface.model_store import verify_model_weights


+# All available model types
+ALL_MODEL_TYPES = {
+    'retinaface': RetinaFaceWeights,
+    'sphereface': SphereFaceWeights,
+    'mobileface': MobileFaceWeights,
+    'arcface': ArcFaceWeights,
+    'scrfd': SCRFDWeights,
+    'ddamfn': DDAMFNWeights,
+    'agegender': AgeGenderWeights,
+    'landmark': LandmarkWeights,
+}
+
+
 def main():
-    parser = argparse.ArgumentParser(description="Download and verify RetinaFace model weights.")
+    parser = argparse.ArgumentParser(description="Download and verify model weights.")
+    parser.add_argument(
+        "--model-type",
+        type=str,
+        choices=list(ALL_MODEL_TYPES.keys()),
+        help="Model type to download (e.g. retinaface, arcface). If not specified, all models will be downloaded.",
+    )
    parser.add_argument(
        "--model",
        type=str,
-        choices=[m.name for m in RetinaFaceWeights],
-        help="Model to download (e.g. MNET_V2). If not specified, all models will be downloaded.",
+        help="Specific model to download (e.g. MNET_V2). For RetinaFace backward compatibility.",
    )
    args = parser.parse_args()

-    if args.model:
-        weight = RetinaFaceWeights[args.model]
-        print(f"📥 Downloading model: {weight.value}")
-        verify_model_weights(weight)  # Pass enum, not string
-    else:
-        print("📥 Downloading all models...")
-        for weight in RetinaFaceWeights:
-            verify_model_weights(weight)  # Pass enum, not string
+    if args.model and not args.model_type:
+        # Backward compatibility - assume RetinaFace
+        try:
+            weight = RetinaFaceWeights[args.model]
+            print(f"Downloading RetinaFace model: {weight.value}")
+            verify_model_weights(weight)
+            print("Model downloaded successfully.")
+        except KeyError:
+            print(f"Invalid RetinaFace model: {args.model}")
+            print(f"Available models: {[m.name for m in RetinaFaceWeights]}")
+        return

-    print("✅ All requested weights are ready and verified.")
+    if args.model_type:
+        # Download all models from specific type
+        model_enum = ALL_MODEL_TYPES[args.model_type]
+        print(f"Downloading all {args.model_type} models...")
+        for weight in model_enum:
+            print(f"Downloading: {weight.value}")
+            try:
+                verify_model_weights(weight)
+                print(f"Downloaded: {weight.value}")
+            except Exception as e:
+                print(f"Failed to download {weight.value}: {e}")
+    else:
+        # Download all models from all types
+        print("Downloading all models...")
+        for model_type, model_enum in ALL_MODEL_TYPES.items():
+            print(f"\nDownloading {model_type} models...")
+            for weight in model_enum:
+                print(f"Downloading: {weight.value}")
+                try:
+                    verify_model_weights(weight)
+                    print(f"Downloaded: {weight.value}")
+                except Exception as e:
+                    print(f"Failed to download {weight.value}: {e}")
+
+    print("\nDownload process completed.")


 if __name__ == "__main__":
    main()
-
-
--- a/scripts/run_age_gender.py
+++ b/scripts/run_age_gender.py
@@ -0,0 +1,163 @@
+"""Age and Gender Detection Demo Script"""
+
+import os
+import cv2
+import argparse
+from pathlib import Path
+
+from uniface import RetinaFace, SCRFD, AgeGender
+from uniface.visualization import draw_detections
+
+
+def process_image(detector, age_gender, image_path: str, save_dir: str = "outputs", vis_threshold: float = 0.6):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    print(f"Processing: {image_path}")
+
+    # Detect faces
+    faces = detector.detect(image)
+    print(f"  Detected {len(faces)} face(s)")
+
+    if not faces:
+        print("  No faces detected")
+        return
+
+    # Draw detections
+    bboxes = [f['bbox'] for f in faces]
+    scores = [f['confidence'] for f in faces]
+    landmarks = [f['landmarks'] for f in faces]
+    draw_detections(image, bboxes, scores, landmarks, vis_threshold=vis_threshold)
+
+    # Predict and draw age/gender for each face
+    for i, face in enumerate(faces):
+        gender, age = age_gender.predict(image, face['bbox'])
+        print(f"  Face {i+1}: {gender}, {age} years old")
+
+        # Draw age and gender text
+        bbox = face['bbox']
+        x1, y1 = int(bbox[0]), int(bbox[1])
+        text = f"{gender}, {age}y"
+
+        # Background rectangle for text
+        (text_width, text_height), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+        cv2.rectangle(image, (x1, y1 - text_height - 10),
+                    (x1 + text_width + 10, y1), (0, 255, 0), -1)
+        cv2.putText(image, text, (x1 + 5, y1 - 5),
+                   cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
+
+    # Save result
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f"{Path(image_path).stem}_age_gender.jpg")
+    cv2.imwrite(output_path, image)
+    print(f"Output saved: {output_path}")
+
+
+def run_webcam(detector, age_gender, vis_threshold: float = 0.6):
+    cap = cv2.VideoCapture(0)
+
+    if not cap.isOpened():
+        print("Cannot open webcam")
+        return
+
+    print("Webcam opened")
+    print("Press 'q' to quit\n")
+
+    frame_count = 0
+
+    try:
+        while True:
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            frame_count += 1
+
+            # Detect faces
+            faces = detector.detect(frame)
+
+            # Draw detections
+            bboxes = [f['bbox'] for f in faces]
+            scores = [f['confidence'] for f in faces]
+            landmarks = [f['landmarks'] for f in faces]
+            draw_detections(frame, bboxes, scores, landmarks, vis_threshold=vis_threshold)
+
+            # Predict and draw age/gender for each face
+            for face in faces:
+                gender, age = age_gender.predict(frame, face['bbox'])
+
+                # Draw age and gender text
+                bbox = face['bbox']
+                x1, y1 = int(bbox[0]), int(bbox[1])
+                text = f"{gender}, {age}y"
+
+                # Background rectangle for text
+                (text_width, text_height), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+                cv2.rectangle(frame, (x1, y1 - text_height - 10),
+                            (x1 + text_width + 10, y1), (0, 255, 0), -1)
+                cv2.putText(frame, text, (x1 + 5, y1 - 5),
+                           cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
+
+            # Add info
+            cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
+                       cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+            cv2.putText(frame, "Press 'q' to quit", (10, frame.shape[0] - 10),
+                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
+
+            cv2.imshow("Age & Gender Detection", frame)
+
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                break
+
+    except KeyboardInterrupt:
+        print("\nInterrupted")
+    finally:
+        cap.release()
+        cv2.destroyAllWindows()
+        print(f"\nProcessed {frame_count} frames")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run age and gender detection")
+    parser.add_argument("--image", type=str, help="Path to input image")
+    parser.add_argument("--webcam", action="store_true", help="Use webcam instead of image")
+    parser.add_argument("--detector", type=str, default="retinaface",
+                       choices=['retinaface', 'scrfd'], help="Face detector to use")
+    parser.add_argument("--threshold", type=float, default=0.6,
+                       help="Confidence threshold for visualization")
+    parser.add_argument("--save_dir", type=str, default="outputs",
+                       help="Directory to save output images")
+    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
+
+    args = parser.parse_args()
+
+    # Validate input
+    if not args.image and not args.webcam:
+        parser.error("Either --image or --webcam must be specified")
+
+    if args.verbose:
+        from uniface import enable_logging
+        enable_logging()
+
+    # Initialize models
+    print(f"Initializing detector: {args.detector}")
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()
+
+    print("Initializing age/gender model...")
+    age_gender = AgeGender()
+    print("Models initialized\n")
+
+    # Process
+    if args.webcam:
+        run_webcam(detector, age_gender, args.threshold)
+    else:
+        process_image(detector, age_gender, args.image, args.save_dir, args.threshold)
+
+
+if __name__ == "__main__":
+    main()
--- a/scripts/run_detection.py
+++ b/scripts/run_detection.py
@@ -4,24 +4,14 @@ import time
 import argparse
 import numpy as np

-# UPDATED: Use the factory function and import from the new location
-from uniface.detection import create_detector
+from uniface.detection import RetinaFace, SCRFD
 from uniface.visualization import draw_detections


 def run_inference(detector, image_path: str, vis_threshold: float = 0.6, save_dir: str = "outputs"):
-    """
-    Run face detection on a single image.
-
-    Args:
-        detector: Initialized face detector.
-        image_path (str): Path to input image.
-        vis_threshold (float): Threshold for drawing detections.
-        save_dir (str): Directory to save output image.
-    """
    image = cv2.imread(image_path)
    if image is None:
-        print(f"❌ Error: Failed to load image from '{image_path}'")
+        print(f"Error: Failed to load image from '{image_path}'")
        return

    # 1. Get the list of face dictionaries from the detector
@@ -40,7 +30,7 @@ def run_inference(detector, image_path: str, vis_threshold: float = 0.6, save_di
    os.makedirs(save_dir, exist_ok=True)
    output_path = os.path.join(save_dir, f"{os.path.splitext(os.path.basename(image_path))[0]}_out.jpg")
    cv2.imwrite(output_path, image)
-    print(f"✅ Output saved at: {output_path}")
+    print(f"Output saved at: {output_path}")


 def main():
@@ -65,14 +55,17 @@ def main():
        enable_logging()

    print(f"Initializing detector: {args.method}")
-    detector = create_detector(method=args.method)
+    if args.method == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()

    avg_time = 0
    for i in range(args.iterations):
        start = time.time()
        run_inference(detector, args.image, args.threshold, args.save_dir)
        elapsed = time.time() - start
-        print(f"[{i + 1}/{args.iterations}] ⏱️ Inference time: {elapsed:.4f} seconds")
+        print(f"[{i + 1}/{args.iterations}] Inference time: {elapsed:.4f} seconds")
        if i >= 0:  # Avoid counting the first run if it includes model loading time
            avg_time += elapsed

@@ -80,7 +73,7 @@ def main():
        # Adjust average calculation to exclude potential first-run overhead
        effective_iterations = max(1, args.iterations)
        print(
-            f"\n🔥 Average inference time over {effective_iterations} runs: {avg_time / effective_iterations:.4f} seconds")
+            f"\nAverage inference time over {effective_iterations} runs: {avg_time / effective_iterations:.4f} seconds")


 if __name__ == "__main__":
--- a/scripts/run_face_search.py
+++ b/scripts/run_face_search.py
@@ -3,14 +3,12 @@ import argparse
 import cv2
 import numpy as np

-# Use the new high-level factory functions
-from uniface.detection import create_detector
+from uniface.detection import RetinaFace, SCRFD
 from uniface.face_utils import compute_similarity
-from uniface.recognition import create_recognizer
+from uniface.recognition import ArcFace, MobileFace, SphereFace


 def extract_reference_embedding(detector, recognizer, image_path: str) -> np.ndarray:
-    """Extracts a normalized embedding from the first face found in an image."""
    image = cv2.imread(image_path)
    if image is None:
        raise RuntimeError(f"Failed to load image: {image_path}")
@@ -28,7 +26,6 @@ def extract_reference_embedding(detector, recognizer, image_path: str) -> np.nda


 def run_video(detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
-    """Run real-time face recognition from a webcam feed."""
    cap = cv2.VideoCapture(0)
    if not cap.isOpened():
        raise RuntimeError("Webcam could not be opened.")
@@ -91,8 +88,17 @@ def main():
        enable_logging()

    print("Initializing models...")
-    detector = create_detector(method=args.detector)
-    recognizer = create_recognizer(method=args.recognizer)
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()
+
+    if args.recognizer == 'arcface':
+        recognizer = ArcFace()
+    elif args.recognizer == 'mobileface':
+        recognizer = MobileFace()
+    else:
+        recognizer = SphereFace()

    print("Extracting reference embedding...")
    ref_embedding = extract_reference_embedding(detector, recognizer, args.image)
--- a/scripts/run_landmarks.py
+++ b/scripts/run_landmarks.py
@@ -0,0 +1,149 @@
+"""Facial Landmark Detection Demo Script"""
+
+import os
+import cv2
+import argparse
+from pathlib import Path
+
+from uniface import RetinaFace, SCRFD, Landmark106
+
+
+def process_image(detector, landmarker, image_path: str, save_dir: str = "outputs"):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    print(f"Processing: {image_path}")
+
+    # Detect faces
+    faces = detector.detect(image)
+    print(f"  Detected {len(faces)} face(s)")
+
+    if not faces:
+        print("  No faces detected")
+        return
+
+    # Process each face
+    for i, face in enumerate(faces):
+        # Draw bounding box
+        bbox = face['bbox']
+        x1, y1, x2, y2 = map(int, bbox)
+        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        # Get and draw 106 landmarks
+        landmarks = landmarker.get_landmarks(image, bbox)
+        print(f"  Face {i+1}: Extracted {len(landmarks)} landmarks")
+
+        for x, y in landmarks.astype(int):
+            cv2.circle(image, (x, y), 1, (0, 255, 0), -1)
+
+        # Add face count
+        cv2.putText(image, f"Face {i+1}", (x1, y1 - 10),
+                   cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+
+    # Add total count
+    cv2.putText(image, f"Faces: {len(faces)}", (10, 30),
+               cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+
+    # Save result
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f"{Path(image_path).stem}_landmarks.jpg")
+    cv2.imwrite(output_path, image)
+    print(f"Output saved: {output_path}")
+
+
+def run_webcam(detector, landmarker):
+    cap = cv2.VideoCapture(0)
+
+    if not cap.isOpened():
+        print("Cannot open webcam")
+        return
+
+    print("Webcam opened")
+    print("Press 'q' to quit\n")
+
+    frame_count = 0
+
+    try:
+        while True:
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            frame_count += 1
+
+            # Detect faces
+            faces = detector.detect(frame)
+
+            # Process each face
+            for face in faces:
+                # Draw bounding box
+                bbox = face['bbox']
+                x1, y1, x2, y2 = map(int, bbox)
+                cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+                # Get and draw 106 landmarks
+                landmarks = landmarker.get_landmarks(frame, bbox)
+                for x, y in landmarks.astype(int):
+                    cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
+
+            # Add info
+            cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
+                       cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+            cv2.putText(frame, "Press 'q' to quit", (10, frame.shape[0] - 10),
+                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
+
+            cv2.imshow("106-Point Landmarks", frame)
+
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                break
+
+    except KeyboardInterrupt:
+        print("\nInterrupted")
+    finally:
+        cap.release()
+        cv2.destroyAllWindows()
+        print(f"\nProcessed {frame_count} frames")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run facial landmark detection")
+    parser.add_argument("--image", type=str, help="Path to input image")
+    parser.add_argument("--webcam", action="store_true", help="Use webcam instead of image")
+    parser.add_argument("--detector", type=str, default="retinaface",
+                       choices=['retinaface', 'scrfd'], help="Face detector to use")
+    parser.add_argument("--save_dir", type=str, default="outputs",
+                       help="Directory to save output images")
+    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
+
+    args = parser.parse_args()
+
+    # Validate input
+    if not args.image and not args.webcam:
+        parser.error("Either --image or --webcam must be specified")
+
+    if args.verbose:
+        from uniface import enable_logging
+        enable_logging()
+
+    # Initialize models
+    print(f"Initializing detector: {args.detector}")
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()
+
+    print("Initializing landmark detector...")
+    landmarker = Landmark106()
+    print("Models initialized\n")
+
+    # Process
+    if args.webcam:
+        run_webcam(detector, landmarker)
+    else:
+        process_image(detector, landmarker, args.image, args.save_dir)
+
+
+if __name__ == "__main__":
+    main()
--- a/scripts/run_recognition.py
+++ b/scripts/run_recognition.py
@@ -2,20 +2,12 @@ import cv2
 import argparse
 import numpy as np

-# Use the new high-level factory functions for consistency
-from uniface.detection import create_detector
-from uniface.recognition import create_recognizer
+from uniface.detection import RetinaFace, SCRFD
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+from uniface.face_utils import compute_similarity


 def run_inference(detector, recognizer, image_path: str):
-    """
-    Detect faces and extract embeddings from a single image.
-
-    Args:
-        detector: Initialized face detector.
-        recognizer: Initialized face recognition model.
-        image_path (str): Path to the input image.
-    """
    image = cv2.imread(image_path)
    if image is None:
        print(f"Error: Failed to load image from '{image_path}'")
@@ -43,9 +35,47 @@ def run_inference(detector, recognizer, image_path: str):
    print(f"  - L2 norm of normalized embedding: {np.linalg.norm(norm_embedding):.4f}")


+def compare_faces(detector, recognizer, image1_path: str, image2_path: str, threshold: float = 0.35):
+
+    # Load images
+    img1 = cv2.imread(image1_path)
+    img2 = cv2.imread(image2_path)
+
+    if img1 is None or img2 is None:
+        print(f"Error: Failed to load images")
+        return
+
+    # Detect faces
+    faces1 = detector.detect(img1)
+    faces2 = detector.detect(img2)
+
+    if not faces1 or not faces2:
+        print("Error: No faces detected in one or both images")
+        return
+
+    # Get landmarks for first face in each image
+    landmarks1 = np.array(faces1[0]['landmarks'])
+    landmarks2 = np.array(faces2[0]['landmarks'])
+
+    # Get normalized embeddings
+    embedding1 = recognizer.get_normalized_embedding(img1, landmarks1)
+    embedding2 = recognizer.get_normalized_embedding(img2, landmarks2)
+
+    # Compute similarity
+    similarity = compute_similarity(embedding1, embedding2, normalized=True)
+    is_match = similarity > threshold
+
+    print(f"Similarity: {similarity:.4f}")
+    print(f"Result: {'Same person' if is_match else 'Different person'}")
+    print(f"Threshold: {threshold}")
+
+
 def main():
-    parser = argparse.ArgumentParser(description="Extract face embeddings from a single image.")
-    parser.add_argument("--image", type=str, required=True, help="Path to the input image.")
+    parser = argparse.ArgumentParser(description="Face recognition and comparison.")
+    parser.add_argument("--image", type=str, help="Path to single image for embedding extraction.")
+    parser.add_argument("--image1", type=str, help="Path to first image for comparison.")
+    parser.add_argument("--image2", type=str, help="Path to second image for comparison.")
+    parser.add_argument("--threshold", type=float, default=0.35, help="Similarity threshold for face matching.")
    parser.add_argument(
        "--detector",
        type=str,
@@ -69,12 +99,29 @@ def main():
        enable_logging()

    print(f"Initializing detector: {args.detector}")
-    detector = create_detector(method=args.detector)
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()

    print(f"Initializing recognizer: {args.recognizer}")
-    recognizer = create_recognizer(method=args.recognizer)
+    if args.recognizer == 'arcface':
+        recognizer = ArcFace()
+    elif args.recognizer == 'mobileface':
+        recognizer = MobileFace()
+    else:
+        recognizer = SphereFace()

-    run_inference(detector, recognizer, args.image)
+    if args.image1 and args.image2:
+        # Face comparison mode
+        print(f"Comparing faces: {args.image1} vs {args.image2}")
+        compare_faces(detector, recognizer, args.image1, args.image2, args.threshold)
+    elif args.image:
+        # Single image embedding extraction mode
+        run_inference(detector, recognizer, args.image)
+    else:
+        print("Error: Provide either --image for single image processing or --image1 and --image2 for comparison")
+        parser.print_help()


 if __name__ == "__main__":
--- a/scripts/run_video_detection.py
+++ b/scripts/run_video_detection.py
@@ -0,0 +1,142 @@
+"""Video Face Detection Script"""
+
+import cv2
+import argparse
+from pathlib import Path
+from tqdm import tqdm
+
+from uniface import RetinaFace, SCRFD
+from uniface.visualization import draw_detections
+
+
+def process_video(detector, input_path: str, output_path: str, vis_threshold: float = 0.6,
+                 fps: int = None, show_preview: bool = False):
+    # Open input video
+    cap = cv2.VideoCapture(input_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{input_path}'")
+        return
+
+    # Get video properties
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    source_fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+    output_fps = fps if fps is not None else source_fps
+
+    print(f"📹 Input: {input_path}")
+    print(f"   Resolution: {width}x{height}")
+    print(f"   FPS: {source_fps:.2f}")
+    print(f"   Total frames: {total_frames}")
+    print(f"\n📹 Output: {output_path}")
+    print(f"   FPS: {output_fps:.2f}\n")
+
+    # Initialize video writer
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, output_fps, (width, height))
+
+    if not out.isOpened():
+        print(f"Error: Cannot create output video '{output_path}'")
+        cap.release()
+        return
+
+    # Process frames
+    frame_count = 0
+    total_faces = 0
+
+    try:
+        with tqdm(total=total_frames, desc="Processing", unit="frames") as pbar:
+            while True:
+                ret, frame = cap.read()
+                if not ret:
+                    break
+
+                frame_count += 1
+
+                # Detect faces
+                faces = detector.detect(frame)
+                total_faces += len(faces)
+
+                # Draw detections
+                bboxes = [f['bbox'] for f in faces]
+                scores = [f['confidence'] for f in faces]
+                landmarks = [f['landmarks'] for f in faces]
+                draw_detections(frame, bboxes, scores, landmarks, vis_threshold=vis_threshold)
+
+                # Add frame info
+                cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
+                           cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+
+                # Write frame
+                out.write(frame)
+
+                # Show preview if requested
+                if show_preview:
+                    cv2.imshow("Processing Video - Press 'q' to cancel", frame)
+                    if cv2.waitKey(1) & 0xFF == ord('q'):
+                        print("\nProcessing cancelled by user")
+                        break
+
+                pbar.update(1)
+
+    except KeyboardInterrupt:
+        print("\nProcessing interrupted")
+    finally:
+        cap.release()
+        out.release()
+        if show_preview:
+            cv2.destroyAllWindows()
+
+    # Summary
+    print(f"\nProcessing complete!")
+    print(f"   Processed: {frame_count} frames")
+    print(f"   Total faces detected: {total_faces}")
+    print(f"   Average faces per frame: {total_faces/frame_count:.2f}" if frame_count > 0 else "")
+    print(f"   Output saved: {output_path}")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Process video with face detection")
+    parser.add_argument("--input", type=str, required=True, help="Path to input video")
+    parser.add_argument("--output", type=str, required=True, help="Path to output video")
+    parser.add_argument("--detector", type=str, default="retinaface",
+                       choices=['retinaface', 'scrfd'], help="Face detector to use")
+    parser.add_argument("--threshold", type=float, default=0.6,
+                       help="Confidence threshold for visualization")
+    parser.add_argument("--fps", type=int, default=None,
+                       help="Output FPS (default: same as input)")
+    parser.add_argument("--preview", action="store_true",
+                       help="Show live preview during processing")
+    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
+
+    args = parser.parse_args()
+
+    # Check input exists
+    if not Path(args.input).exists():
+        print(f"Error: Input file '{args.input}' does not exist")
+        return
+
+    # Create output directory if needed
+    output_dir = Path(args.output).parent
+    if output_dir != Path('.'):
+        output_dir.mkdir(parents=True, exist_ok=True)
+
+    if args.verbose:
+        from uniface import enable_logging
+        enable_logging()
+
+    # Initialize detector
+    print(f"Initializing detector: {args.detector}")
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    else:
+        detector = SCRFD()
+    print("Detector initialized\n")
+
+    # Process video
+    process_video(detector, args.input, args.output, args.threshold, args.fps, args.preview)
+
+
+if __name__ == "__main__":
+    main()
--- a/tests/test_age_gender.py
+++ b/tests/test_age_gender.py
@@ -0,0 +1,116 @@
+import numpy as np
+import pytest
+
+from uniface.attribute import AgeGender
+
+
+@pytest.fixture
+def age_gender_model():
+    return AgeGender()
+
+
+@pytest.fixture
+def mock_image():
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_bbox():
+    return [100, 100, 300, 300]
+
+
+def test_model_initialization(age_gender_model):
+    assert age_gender_model is not None, "AgeGender model initialization failed."
+
+
+def test_prediction_output_format(age_gender_model, mock_image, mock_bbox):
+    gender, age = age_gender_model.predict(mock_image, mock_bbox)
+    assert isinstance(gender, str), f"Gender should be string, got {type(gender)}"
+    assert isinstance(age, int), f"Age should be int, got {type(age)}"
+
+
+def test_gender_values(age_gender_model, mock_image, mock_bbox):
+    gender, age = age_gender_model.predict(mock_image, mock_bbox)
+    assert gender in ['Male', 'Female'], f"Gender should be 'Male' or 'Female', got '{gender}'"
+
+
+def test_age_range(age_gender_model, mock_image, mock_bbox):
+    gender, age = age_gender_model.predict(mock_image, mock_bbox)
+    assert 0 <= age <= 120, f"Age should be between 0 and 120, got {age}"
+
+
+def test_different_bbox_sizes(age_gender_model, mock_image):
+    test_bboxes = [
+        [50, 50, 150, 150],
+        [100, 100, 300, 300],
+        [50, 50, 400, 400],
+    ]
+
+    for bbox in test_bboxes:
+        gender, age = age_gender_model.predict(mock_image, bbox)
+        assert gender in ['Male', 'Female'], f"Failed for bbox {bbox}"
+        assert 0 <= age <= 120, f"Age out of range for bbox {bbox}"
+
+
+def test_different_image_sizes(age_gender_model, mock_bbox):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        gender, age = age_gender_model.predict(mock_image, mock_bbox)
+        assert gender in ['Male', 'Female'], f"Failed for image size {size}"
+        assert 0 <= age <= 120, f"Age out of range for image size {size}"
+
+
+def test_consistency(age_gender_model, mock_image, mock_bbox):
+    gender1, age1 = age_gender_model.predict(mock_image, mock_bbox)
+    gender2, age2 = age_gender_model.predict(mock_image, mock_bbox)
+
+    assert gender1 == gender2, "Same input should produce same gender prediction"
+    assert age1 == age2, "Same input should produce same age prediction"
+
+
+def test_bbox_list_format(age_gender_model, mock_image):
+    bbox_list = [100, 100, 300, 300]
+    gender, age = age_gender_model.predict(mock_image, bbox_list)
+    assert gender in ['Male', 'Female'], "Should work with bbox as list"
+    assert 0 <= age <= 120, "Age should be in valid range"
+
+
+def test_bbox_array_format(age_gender_model, mock_image):
+    bbox_array = np.array([100, 100, 300, 300])
+    gender, age = age_gender_model.predict(mock_image, bbox_array)
+    assert gender in ['Male', 'Female'], "Should work with bbox as numpy array"
+    assert 0 <= age <= 120, "Age should be in valid range"
+
+
+def test_multiple_predictions(age_gender_model, mock_image):
+    bboxes = [
+        [50, 50, 150, 150],
+        [200, 200, 350, 350],
+        [400, 400, 550, 550],
+    ]
+
+    results = []
+    for bbox in bboxes:
+        gender, age = age_gender_model.predict(mock_image, bbox)
+        results.append((gender, age))
+
+    assert len(results) == 3, "Should have 3 predictions"
+    for gender, age in results:
+        assert gender in ['Male', 'Female']
+        assert 0 <= age <= 120
+
+
+def test_age_is_positive(age_gender_model, mock_image, mock_bbox):
+    for _ in range(5):
+        gender, age = age_gender_model.predict(mock_image, mock_bbox)
+        assert age >= 0, f"Age should be non-negative, got {age}"
+
+
+def test_output_format_for_visualization(age_gender_model, mock_image, mock_bbox):
+    gender, age = age_gender_model.predict(mock_image, mock_bbox)
+    text = f"{gender}, {age}y"
+    assert isinstance(text, str), "Should be able to format as string"
+    assert "Male" in text or "Female" in text, "Text should contain gender"
+    assert "y" in text, "Text should contain 'y' for years"
--- a/tests/test_factory.py
+++ b/tests/test_factory.py
@@ -0,0 +1,278 @@
+import numpy as np
+import pytest
+
+from uniface import (
+    create_detector,
+    create_landmarker,
+    create_recognizer,
+    detect_faces,
+    list_available_detectors,
+)
+from uniface.constants import RetinaFaceWeights, SCRFDWeights
+
+
+# create_detector tests
+def test_create_detector_retinaface():
+    """
+    Test creating a RetinaFace detector using factory function.
+    """
+    detector = create_detector('retinaface')
+    assert detector is not None, "Failed to create RetinaFace detector"
+
+
+def test_create_detector_scrfd():
+    """
+    Test creating a SCRFD detector using factory function.
+    """
+    detector = create_detector('scrfd')
+    assert detector is not None, "Failed to create SCRFD detector"
+
+
+def test_create_detector_with_config():
+    """
+    Test creating detector with custom configuration.
+    """
+    detector = create_detector(
+        'retinaface',
+        model_name=RetinaFaceWeights.MNET_V2,
+        conf_thresh=0.8,
+        nms_thresh=0.3
+    )
+    assert detector is not None, "Failed to create detector with custom config"
+
+
+def test_create_detector_invalid_method():
+    """
+    Test that invalid detector method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_detector('invalid_method')
+
+
+def test_create_detector_scrfd_with_model():
+    """
+    Test creating SCRFD detector with specific model.
+    """
+    detector = create_detector(
+        'scrfd',
+        model_name=SCRFDWeights.SCRFD_10G_KPS,
+        conf_thresh=0.5
+    )
+    assert detector is not None, "Failed to create SCRFD with specific model"
+
+
+# create_recognizer tests
+def test_create_recognizer_arcface():
+    """
+    Test creating an ArcFace recognizer using factory function.
+    """
+    recognizer = create_recognizer('arcface')
+    assert recognizer is not None, "Failed to create ArcFace recognizer"
+
+
+def test_create_recognizer_mobileface():
+    """
+    Test creating a MobileFace recognizer using factory function.
+    """
+    recognizer = create_recognizer('mobileface')
+    assert recognizer is not None, "Failed to create MobileFace recognizer"
+
+
+def test_create_recognizer_sphereface():
+    """
+    Test creating a SphereFace recognizer using factory function.
+    """
+    recognizer = create_recognizer('sphereface')
+    assert recognizer is not None, "Failed to create SphereFace recognizer"
+
+
+def test_create_recognizer_invalid_method():
+    """
+    Test that invalid recognizer method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_recognizer('invalid_method')
+
+
+# create_landmarker tests
+def test_create_landmarker():
+    """
+    Test creating a Landmark106 detector using factory function.
+    """
+    landmarker = create_landmarker('2d106det')
+    assert landmarker is not None, "Failed to create Landmark106 detector"
+
+
+def test_create_landmarker_default():
+    """
+    Test creating landmarker with default parameters.
+    """
+    landmarker = create_landmarker()
+    assert landmarker is not None, "Failed to create default landmarker"
+
+
+def test_create_landmarker_invalid_method():
+    """
+    Test that invalid landmarker method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_landmarker('invalid_method')
+
+
+# detect_faces tests
+def test_detect_faces_retinaface():
+    """
+    Test high-level detect_faces function with RetinaFace.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image, method='retinaface')
+
+    assert isinstance(faces, list), "detect_faces should return a list"
+
+
+def test_detect_faces_scrfd():
+    """
+    Test high-level detect_faces function with SCRFD.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image, method='scrfd')
+
+    assert isinstance(faces, list), "detect_faces should return a list"
+
+
+def test_detect_faces_with_threshold():
+    """
+    Test detect_faces with custom confidence threshold.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image, method='retinaface', conf_thresh=0.8)
+
+    assert isinstance(faces, list), "detect_faces should return a list"
+
+    # All detections should respect threshold
+    for face in faces:
+        assert face['confidence'] >= 0.8, "All detections should meet confidence threshold"
+
+
+def test_detect_faces_default_method():
+    """
+    Test detect_faces with default method (should use retinaface).
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image)  # No method specified
+
+    assert isinstance(faces, list), "detect_faces should return a list with default method"
+
+
+def test_detect_faces_empty_image():
+    """
+    Test detect_faces on a blank image.
+    """
+    empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(empty_image, method='retinaface')
+
+    assert isinstance(faces, list), "Should return a list even for empty image"
+    assert len(faces) == 0, "Should detect no faces in blank image"
+
+
+# list_available_detectors tests
+def test_list_available_detectors():
+    """
+    Test that list_available_detectors returns a dictionary.
+    """
+    detectors = list_available_detectors()
+
+    assert isinstance(detectors, dict), "Should return a dictionary of detectors"
+    assert len(detectors) > 0, "Should have at least one detector available"
+
+
+def test_list_available_detectors_contents():
+    """
+    Test that list includes known detectors.
+    """
+    detectors = list_available_detectors()
+
+    # Should include at least these detectors
+    assert 'retinaface' in detectors, "Should include 'retinaface'"
+    assert 'scrfd' in detectors, "Should include 'scrfd'"
+
+
+# Integration tests
+def test_detector_inference_from_factory():
+    """
+    Test that detector created from factory can perform inference.
+    """
+    detector = create_detector('retinaface')
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    faces = detector.detect(mock_image)
+    assert isinstance(faces, list), "Detector should return list of faces"
+
+
+def test_recognizer_inference_from_factory():
+    """
+    Test that recognizer created from factory can perform inference.
+    """
+    recognizer = create_recognizer('arcface')
+    mock_image = np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
+
+    embedding = recognizer.get_embedding(mock_image)
+    assert embedding is not None, "Recognizer should return embedding"
+    assert embedding.shape[1] == 512, "Should return 512-dimensional embedding"
+
+
+def test_landmarker_inference_from_factory():
+    """
+    Test that landmarker created from factory can perform inference.
+    """
+    landmarker = create_landmarker('2d106det')
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    mock_bbox = [100, 100, 300, 300]
+
+    landmarks = landmarker.get_landmarks(mock_image, mock_bbox)
+    assert landmarks is not None, "Landmarker should return landmarks"
+    assert landmarks.shape == (106, 2), "Should return 106 landmarks"
+
+
+def test_multiple_detector_creation():
+    """
+    Test that multiple detectors can be created independently.
+    """
+    detector1 = create_detector('retinaface')
+    detector2 = create_detector('scrfd')
+
+    assert detector1 is not None
+    assert detector2 is not None
+    assert detector1 is not detector2, "Should create separate instances"
+
+
+def test_detector_with_different_configs():
+    """
+    Test creating multiple detectors with different configurations.
+    """
+    detector_high_thresh = create_detector('retinaface', conf_thresh=0.9)
+    detector_low_thresh = create_detector('retinaface', conf_thresh=0.3)
+
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    faces_high = detector_high_thresh.detect(mock_image)
+    faces_low = detector_low_thresh.detect(mock_image)
+
+    # Both should work
+    assert isinstance(faces_high, list)
+    assert isinstance(faces_low, list)
+
+
+def test_factory_returns_correct_types():
+    """
+    Test that factory functions return instances of the correct types.
+    """
+    from uniface import RetinaFace, ArcFace, Landmark106
+
+    detector = create_detector('retinaface')
+    recognizer = create_recognizer('arcface')
+    landmarker = create_landmarker('2d106det')
+
+    assert isinstance(detector, RetinaFace), "Should return RetinaFace instance"
+    assert isinstance(recognizer, ArcFace), "Should return ArcFace instance"
+    assert isinstance(landmarker, Landmark106), "Should return Landmark106 instance"
--- a/tests/test_landmark.py
+++ b/tests/test_landmark.py
@@ -0,0 +1,107 @@
+import numpy as np
+import pytest
+
+from uniface.landmark import Landmark106
+
+
+@pytest.fixture
+def landmark_model():
+    return Landmark106()
+
+
+@pytest.fixture
+def mock_image():
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_bbox():
+    return [100, 100, 300, 300]
+
+
+def test_model_initialization(landmark_model):
+    assert landmark_model is not None, "Landmark106 model initialization failed."
+
+
+def test_landmark_detection(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+    assert landmarks.shape == (106, 2), f"Expected shape (106, 2), got {landmarks.shape}"
+
+
+def test_landmark_dtype(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+    assert landmarks.dtype == np.float32, f"Expected float32, got {landmarks.dtype}"
+
+
+def test_landmark_coordinates_within_image(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    x_coords = landmarks[:, 0]
+    y_coords = landmarks[:, 1]
+
+    x1, y1, x2, y2 = mock_bbox
+    margin = 50
+
+    x_in_bounds = np.sum((x_coords >= x1 - margin) & (x_coords <= x2 + margin))
+    y_in_bounds = np.sum((y_coords >= y1 - margin) & (y_coords <= y2 + margin))
+
+    assert x_in_bounds >= 95, f"Only {x_in_bounds}/106 x-coordinates within bounds"
+    assert y_in_bounds >= 95, f"Only {y_in_bounds}/106 y-coordinates within bounds"
+
+
+def test_different_bbox_sizes(landmark_model, mock_image):
+    test_bboxes = [
+        [50, 50, 150, 150],
+        [100, 100, 300, 300],
+        [50, 50, 400, 400],
+    ]
+
+    for bbox in test_bboxes:
+        landmarks = landmark_model.get_landmarks(mock_image, bbox)
+        assert landmarks.shape == (106, 2), f"Failed for bbox {bbox}"
+
+
+def test_landmark_array_format(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+    landmarks_int = landmarks.astype(int)
+
+    assert landmarks_int.shape == (106, 2), "Integer conversion should preserve shape"
+    assert landmarks_int.dtype in [np.int32, np.int64], "Should convert to integer type"
+
+
+def test_consistency(landmark_model, mock_image, mock_bbox):
+    landmarks1 = landmark_model.get_landmarks(mock_image, mock_bbox)
+    landmarks2 = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    assert np.allclose(landmarks1, landmarks2), "Same input should produce same landmarks"
+
+
+def test_different_image_sizes(landmark_model, mock_bbox):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+        assert landmarks.shape == (106, 2), f"Failed for image size {size}"
+
+
+def test_bbox_list_format(landmark_model, mock_image):
+    bbox_list = [100, 100, 300, 300]
+    landmarks = landmark_model.get_landmarks(mock_image, bbox_list)
+    assert landmarks.shape == (106, 2), "Should work with bbox as list"
+
+
+def test_bbox_array_format(landmark_model, mock_image):
+    bbox_array = np.array([100, 100, 300, 300])
+    landmarks = landmark_model.get_landmarks(mock_image, bbox_array)
+    assert landmarks.shape == (106, 2), "Should work with bbox as numpy array"
+
+
+def test_landmark_distribution(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    x_variance = np.var(landmarks[:, 0])
+    y_variance = np.var(landmarks[:, 1])
+
+    assert x_variance > 0, "Landmarks should have variation in x-coordinates"
+    assert y_variance > 0, "Landmarks should have variation in y-coordinates"
--- a/tests/test_recognition.py
+++ b/tests/test_recognition.py
@@ -0,0 +1,211 @@
+import numpy as np
+import pytest
+
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+
+@pytest.fixture
+def arcface_model():
+    """
+    Fixture to initialize the ArcFace model for testing.
+    """
+    return ArcFace()
+
+
+@pytest.fixture
+def mobileface_model():
+    """
+    Fixture to initialize the MobileFace model for testing.
+    """
+    return MobileFace()
+
+
+@pytest.fixture
+def sphereface_model():
+    """
+    Fixture to initialize the SphereFace model for testing.
+    """
+    return SphereFace()
+
+
+@pytest.fixture
+def mock_aligned_face():
+    """
+    Create a mock 112x112 aligned face image.
+    """
+    return np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_landmarks():
+    """
+    Create mock 5-point facial landmarks.
+    """
+    return np.array([
+        [38.2946, 51.6963],
+        [73.5318, 51.5014],
+        [56.0252, 71.7366],
+        [41.5493, 92.3655],
+        [70.7299, 92.2041]
+    ], dtype=np.float32)
+
+
+# ArcFace Tests
+def test_arcface_initialization(arcface_model):
+    """
+    Test that the ArcFace model initializes correctly.
+    """
+    assert arcface_model is not None, "ArcFace model initialization failed."
+
+
+def test_arcface_embedding_shape(arcface_model, mock_aligned_face):
+    """
+    Test that ArcFace produces embeddings with the correct shape.
+    """
+    embedding = arcface_model.get_embedding(mock_aligned_face)
+
+    # ArcFace typically produces 512-dimensional embeddings
+    assert embedding.shape[1] == 512, f"Expected 512-dim embedding, got {embedding.shape[1]}"
+    assert embedding.shape[0] == 1, "Embedding should have batch dimension of 1"
+
+
+def test_arcface_normalized_embedding(arcface_model, mock_landmarks):
+    """
+    Test that normalized embeddings have unit length.
+    """
+    # Create a larger mock image for alignment
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = arcface_model.get_normalized_embedding(mock_image, mock_landmarks)
+
+    # Check that embedding is normalized (L2 norm ≈ 1.0)
+    norm = np.linalg.norm(embedding)
+    assert np.isclose(norm, 1.0, atol=1e-5), f"Normalized embedding should have norm 1.0, got {norm}"
+
+
+def test_arcface_embedding_dtype(arcface_model, mock_aligned_face):
+    """
+    Test that embeddings have the correct data type.
+    """
+    embedding = arcface_model.get_embedding(mock_aligned_face)
+    assert embedding.dtype == np.float32, f"Expected float32, got {embedding.dtype}"
+
+
+def test_arcface_consistency(arcface_model, mock_aligned_face):
+    """
+    Test that the same input produces the same embedding.
+    """
+    embedding1 = arcface_model.get_embedding(mock_aligned_face)
+    embedding2 = arcface_model.get_embedding(mock_aligned_face)
+
+    assert np.allclose(embedding1, embedding2), "Same input should produce same embedding"
+
+
+# MobileFace Tests
+def test_mobileface_initialization(mobileface_model):
+    """
+    Test that the MobileFace model initializes correctly.
+    """
+    assert mobileface_model is not None, "MobileFace model initialization failed."
+
+
+def test_mobileface_embedding_shape(mobileface_model, mock_aligned_face):
+    """
+    Test that MobileFace produces embeddings with the correct shape.
+    """
+    embedding = mobileface_model.get_embedding(mock_aligned_face)
+
+    # MobileFace typically produces 512-dimensional embeddings
+    assert embedding.shape[1] == 512, f"Expected 512-dim embedding, got {embedding.shape[1]}"
+    assert embedding.shape[0] == 1, "Embedding should have batch dimension of 1"
+
+
+def test_mobileface_normalized_embedding(mobileface_model, mock_landmarks):
+    """
+    Test that MobileFace normalized embeddings have unit length.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = mobileface_model.get_normalized_embedding(mock_image, mock_landmarks)
+
+    norm = np.linalg.norm(embedding)
+    assert np.isclose(norm, 1.0, atol=1e-5), f"Normalized embedding should have norm 1.0, got {norm}"
+
+
+# SphereFace Tests
+def test_sphereface_initialization(sphereface_model):
+    """
+    Test that the SphereFace model initializes correctly.
+    """
+    assert sphereface_model is not None, "SphereFace model initialization failed."
+
+
+def test_sphereface_embedding_shape(sphereface_model, mock_aligned_face):
+    """
+    Test that SphereFace produces embeddings with the correct shape.
+    """
+    embedding = sphereface_model.get_embedding(mock_aligned_face)
+
+    # SphereFace typically produces 512-dimensional embeddings
+    assert embedding.shape[1] == 512, f"Expected 512-dim embedding, got {embedding.shape[1]}"
+    assert embedding.shape[0] == 1, "Embedding should have batch dimension of 1"
+
+
+def test_sphereface_normalized_embedding(sphereface_model, mock_landmarks):
+    """
+    Test that SphereFace normalized embeddings have unit length.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = sphereface_model.get_normalized_embedding(mock_image, mock_landmarks)
+
+    norm = np.linalg.norm(embedding)
+    assert np.isclose(norm, 1.0, atol=1e-5), f"Normalized embedding should have norm 1.0, got {norm}"
+
+
+# Cross-model comparison tests
+def test_different_models_different_embeddings(arcface_model, mobileface_model, mock_aligned_face):
+    """
+    Test that different models produce different embeddings for the same input.
+    """
+    arcface_emb = arcface_model.get_embedding(mock_aligned_face)
+    mobileface_emb = mobileface_model.get_embedding(mock_aligned_face)
+
+    # Embeddings should be different (with high probability for random input)
+    # We check that they're not identical
+    assert not np.allclose(arcface_emb, mobileface_emb), \
+        "Different models should produce different embeddings"
+
+
+def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
+    """
+    Test computing similarity between embeddings.
+    """
+    # Get two embeddings
+    emb1 = arcface_model.get_embedding(mock_aligned_face)
+
+    # Create a slightly different image
+    mock_aligned_face2 = mock_aligned_face.copy()
+    mock_aligned_face2[:10, :10] = 0  # Modify a small region
+    emb2 = arcface_model.get_embedding(mock_aligned_face2)
+
+    # Compute cosine similarity
+    from uniface import compute_similarity
+    similarity = compute_similarity(emb1, emb2)
+
+    # Similarity should be between -1 and 1
+    assert -1.0 <= similarity <= 1.0, f"Similarity should be in [-1, 1], got {similarity}"
+
+
+def test_same_face_high_similarity(arcface_model, mock_aligned_face):
+    """
+    Test that the same face produces high similarity.
+    """
+    emb1 = arcface_model.get_embedding(mock_aligned_face)
+    emb2 = arcface_model.get_embedding(mock_aligned_face)
+
+    from uniface import compute_similarity
+    similarity = compute_similarity(emb1, emb2)
+
+    # Same image should have similarity close to 1.0
+    assert similarity > 0.99, f"Same face should have similarity > 0.99, got {similarity}"
--- a/tests/test_retinaface.py
+++ b/tests/test_retinaface.py
@@ -7,9 +7,6 @@ from uniface.detection import RetinaFace

@pytest.fixture
 def retinaface_model():
-    """
-    Fixture to initialize the RetinaFace model for testing.
-    """
    return RetinaFace(
        model_name=RetinaFaceWeights.MNET_V2,
        conf_thresh=0.5,
@@ -20,67 +17,39 @@ def retinaface_model():


 def test_model_initialization(retinaface_model):
-    """
-    Test that the RetinaFace model initializes correctly.
-    """
    assert retinaface_model is not None, "Model initialization failed."


 def test_inference_on_640x640_image(retinaface_model):
-    """
-    Test inference on a 640x640 BGR image.
-    """
-    # Generate a mock 640x640 BGR image
    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-
-    # Run inference - returns list of dictionaries
    faces = retinaface_model.detect(mock_image)

-    # Check output type
    assert isinstance(faces, list), "Detections should be a list."

-    # Check that each face has the expected structure
    for face in faces:
        assert isinstance(face, dict), "Each detection should be a dictionary."
        assert "bbox" in face, "Each detection should have a 'bbox' key."
        assert "confidence" in face, "Each detection should have a 'confidence' key."
        assert "landmarks" in face, "Each detection should have a 'landmarks' key."

-        # Check bbox format
        bbox = face["bbox"]
        assert len(bbox) == 4, "BBox should have 4 values (x1, y1, x2, y2)."

-        # Check landmarks format
        landmarks = face["landmarks"]
        assert len(landmarks) == 5, "Should have 5 landmark points."
        assert all(len(pt) == 2 for pt in landmarks), "Each landmark should be (x, y)."


 def test_confidence_threshold(retinaface_model):
-    """
-    Test that detections respect the confidence threshold.
-    """
-    # Generate a mock 640x640 BGR image
    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-
-    # Run inference
    faces = retinaface_model.detect(mock_image)

-    # Ensure all detections have confidence scores above the threshold
    for face in faces:
        confidence = face["confidence"]
        assert confidence >= 0.5, f"Detection has confidence {confidence} below threshold 0.5"


 def test_no_faces_detected(retinaface_model):
-    """
-    Test inference on an image without detectable faces.
-    """
-    # Generate an empty (black) 640x640 image
    empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
-
-    # Run inference
    faces = retinaface_model.detect(empty_image)
-
-    # Ensure no detections are found
    assert len(faces) == 0, "Should detect no faces in a blank image."
--- a/tests/test_scrfd.py
+++ b/tests/test_scrfd.py
@@ -0,0 +1,71 @@
+import numpy as np
+import pytest
+
+from uniface.constants import SCRFDWeights
+from uniface.detection import SCRFD
+
+
+@pytest.fixture
+def scrfd_model():
+    return SCRFD(
+        model_name=SCRFDWeights.SCRFD_500M_KPS,
+        conf_thresh=0.5,
+        nms_thresh=0.4,
+    )
+
+
+def test_model_initialization(scrfd_model):
+    assert scrfd_model is not None, "Model initialization failed."
+
+
+def test_inference_on_640x640_image(scrfd_model):
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = scrfd_model.detect(mock_image)
+
+    assert isinstance(faces, list), "Detections should be a list."
+
+    for face in faces:
+        assert isinstance(face, dict), "Each detection should be a dictionary."
+        assert "bbox" in face, "Each detection should have a 'bbox' key."
+        assert "confidence" in face, "Each detection should have a 'confidence' key."
+        assert "landmarks" in face, "Each detection should have a 'landmarks' key."
+
+        bbox = face["bbox"]
+        assert len(bbox) == 4, "BBox should have 4 values (x1, y1, x2, y2)."
+
+        landmarks = face["landmarks"]
+        assert len(landmarks) == 5, "Should have 5 landmark points."
+        assert all(len(pt) == 2 for pt in landmarks), "Each landmark should be (x, y)."
+
+
+def test_confidence_threshold(scrfd_model):
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = scrfd_model.detect(mock_image)
+
+    for face in faces:
+        confidence = face["confidence"]
+        assert confidence >= 0.5, f"Detection has confidence {confidence} below threshold 0.5"
+
+
+def test_no_faces_detected(scrfd_model):
+    empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
+    faces = scrfd_model.detect(empty_image)
+    assert len(faces) == 0, "Should detect no faces in a blank image."
+
+
+def test_different_input_sizes(scrfd_model):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        faces = scrfd_model.detect(mock_image)
+        assert isinstance(faces, list), f"Should return list for size {size}"
+
+
+def test_scrfd_10g_model():
+    model = SCRFD(model_name=SCRFDWeights.SCRFD_10G_KPS, conf_thresh=0.5)
+    assert model is not None, "SCRFD 10G model initialization failed."
+
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = model.detect(mock_image)
+    assert isinstance(faces, list), "SCRFD 10G should return list of detections."
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -0,0 +1,247 @@
+import numpy as np
+import pytest
+
+from uniface import compute_similarity, face_alignment
+
+
+@pytest.fixture
+def mock_image():
+    """
+    Create a mock 640x640 BGR image.
+    """
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_landmarks():
+    """
+    Create mock 5-point facial landmarks.
+    Standard positions for a face roughly centered at (112/2, 112/2).
+    """
+    return np.array([
+        [38.2946, 51.6963],  # Left eye
+        [73.5318, 51.5014],  # Right eye
+        [56.0252, 71.7366],  # Nose
+        [41.5493, 92.3655],  # Left mouth corner
+        [70.7299, 92.2041]   # Right mouth corner
+    ], dtype=np.float32)
+
+
+# compute_similarity tests
+def test_compute_similarity_same_embedding():
+    """
+    Test that similarity of an embedding with itself is 1.0.
+    """
+    embedding = np.random.randn(1, 512).astype(np.float32)
+    embedding = embedding / np.linalg.norm(embedding)  # Normalize
+
+    similarity = compute_similarity(embedding, embedding)
+    assert np.isclose(similarity, 1.0, atol=1e-5), f"Self-similarity should be 1.0, got {similarity}"
+
+
+def test_compute_similarity_range():
+    """
+    Test that similarity is always in the range [-1, 1].
+    """
+    # Test with multiple random embeddings
+    for _ in range(10):
+        emb1 = np.random.randn(1, 512).astype(np.float32)
+        emb2 = np.random.randn(1, 512).astype(np.float32)
+
+        # Normalize
+        emb1 = emb1 / np.linalg.norm(emb1)
+        emb2 = emb2 / np.linalg.norm(emb2)
+
+        similarity = compute_similarity(emb1, emb2)
+        assert -1.0 <= similarity <= 1.0, f"Similarity should be in [-1, 1], got {similarity}"
+
+
+def test_compute_similarity_orthogonal():
+    """
+    Test that orthogonal embeddings have similarity close to 0.
+    """
+    # Create orthogonal embeddings
+    emb1 = np.zeros((1, 512), dtype=np.float32)
+    emb1[0, 0] = 1.0  # [1, 0, 0, ..., 0]
+
+    emb2 = np.zeros((1, 512), dtype=np.float32)
+    emb2[0, 1] = 1.0  # [0, 1, 0, ..., 0]
+
+    similarity = compute_similarity(emb1, emb2)
+    assert np.isclose(similarity, 0.0, atol=1e-5), f"Orthogonal embeddings should have similarity 0.0, got {similarity}"
+
+
+def test_compute_similarity_opposite():
+    """
+    Test that opposite embeddings have similarity close to -1.
+    """
+    emb1 = np.ones((1, 512), dtype=np.float32)
+    emb1 = emb1 / np.linalg.norm(emb1)
+
+    emb2 = -emb1  # Opposite direction
+
+    similarity = compute_similarity(emb1, emb2)
+    assert np.isclose(similarity, -1.0, atol=1e-5), f"Opposite embeddings should have similarity -1.0, got {similarity}"
+
+
+def test_compute_similarity_symmetry():
+    """
+    Test that similarity(A, B) == similarity(B, A).
+    """
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    sim_12 = compute_similarity(emb1, emb2)
+    sim_21 = compute_similarity(emb2, emb1)
+
+    assert np.isclose(sim_12, sim_21), "Similarity should be symmetric"
+
+
+def test_compute_similarity_dtype():
+    """
+    Test that compute_similarity returns a float.
+    """
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    similarity = compute_similarity(emb1, emb2)
+    assert isinstance(similarity, (float, np.floating)), f"Similarity should be float, got {type(similarity)}"
+
+
+# face_alignment tests
+def test_face_alignment_output_shape(mock_image, mock_landmarks):
+    """
+    Test that face_alignment produces output with the correct shape.
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert aligned.shape == (112, 112, 3), f"Expected shape (112, 112, 3), got {aligned.shape}"
+
+
+def test_face_alignment_dtype(mock_image, mock_landmarks):
+    """
+    Test that aligned face has the correct data type.
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert aligned.dtype == np.uint8, f"Expected uint8, got {aligned.dtype}"
+
+
+def test_face_alignment_different_sizes(mock_image, mock_landmarks):
+    """
+    Test face alignment with different output sizes.
+    """
+    # Only test sizes that are multiples of 112 or 128 as required by the function
+    test_sizes = [(112, 112), (128, 128), (224, 224)]
+
+    for size in test_sizes:
+        aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=size)
+        assert aligned.shape == (*size, 3), f"Failed for size {size}"
+
+
+def test_face_alignment_consistency(mock_image, mock_landmarks):
+    """
+    Test that the same input produces the same aligned face.
+    """
+    aligned1, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+    aligned2, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert np.allclose(aligned1, aligned2), "Same input should produce same aligned face"
+
+
+def test_face_alignment_landmarks_as_list(mock_image):
+    """
+    Test that landmarks can be passed as a list of lists (converted to array).
+    """
+    landmarks_list = [
+        [38.2946, 51.6963],
+        [73.5318, 51.5014],
+        [56.0252, 71.7366],
+        [41.5493, 92.3655],
+        [70.7299, 92.2041]
+    ]
+
+    # Convert list to numpy array before passing to face_alignment
+    landmarks_array = np.array(landmarks_list, dtype=np.float32)
+    aligned, _ = face_alignment(mock_image, landmarks_array, image_size=(112, 112))
+    assert aligned.shape == (112, 112, 3), "Should work with landmarks as array"
+
+
+def test_face_alignment_value_range(mock_image, mock_landmarks):
+    """
+    Test that aligned face pixel values are in valid range [0, 255].
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert np.all(aligned >= 0), "Pixel values should be >= 0"
+    assert np.all(aligned <= 255), "Pixel values should be <= 255"
+
+
+def test_face_alignment_not_all_zeros(mock_image, mock_landmarks):
+    """
+    Test that aligned face is not all zeros (actual transformation occurred).
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    # At least some pixels should be non-zero
+    assert np.any(aligned > 0), "Aligned face should have some non-zero pixels"
+
+
+def test_face_alignment_from_different_positions(mock_image):
+    """
+    Test alignment with landmarks at different positions in the image.
+    """
+    # Landmarks at different positions
+    positions = [
+        np.array([[100, 100], [150, 100], [125, 130], [110, 150], [140, 150]], dtype=np.float32),
+        np.array([[300, 200], [350, 200], [325, 230], [310, 250], [340, 250]], dtype=np.float32),
+        np.array([[500, 400], [550, 400], [525, 430], [510, 450], [540, 450]], dtype=np.float32),
+    ]
+
+    for landmarks in positions:
+        aligned, _ = face_alignment(mock_image, landmarks, image_size=(112, 112))
+        assert aligned.shape == (112, 112, 3), f"Failed for landmarks at {landmarks[0]}"
+
+
+def test_face_alignment_landmark_count(mock_image):
+    """
+    Test that face_alignment works specifically with 5-point landmarks.
+    """
+    # Standard 5-point landmarks
+    landmarks_5pt = np.array([
+        [38.2946, 51.6963],
+        [73.5318, 51.5014],
+        [56.0252, 71.7366],
+        [41.5493, 92.3655],
+        [70.7299, 92.2041]
+    ], dtype=np.float32)
+
+    aligned, _ = face_alignment(mock_image, landmarks_5pt, image_size=(112, 112))
+    assert aligned.shape == (112, 112, 3), "Should work with 5-point landmarks"
+
+
+def test_compute_similarity_with_recognition_embeddings():
+    """
+    Test compute_similarity with realistic embedding dimensions.
+    """
+    # Simulate ArcFace/MobileFace/SphereFace embeddings (512-dim)
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize (as done in get_normalized_embedding)
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    similarity = compute_similarity(emb1, emb2)
+
+    # Should be a valid similarity score
+    assert -1.0 <= similarity <= 1.0
+    assert isinstance(similarity, (float, np.floating))
--- a/uniface/init.py
+++ b/uniface/init.py
@@ -13,7 +13,7 @@

 __license__ = "MIT"
 __author__ = "Yakhyokhuja Valikhujaev"
-__version__ = "1.0.0"
+__version__ = "1.1.0"


 from uniface.face_utils import compute_similarity, face_alignment
--- a/uniface/constants.py
+++ b/uniface/constants.py
@@ -29,7 +29,7 @@ class ArcFaceWeights(str, Enum):
    Pretrained weights from ArcFace model (insightface).
    https://github.com/deepinsight/insightface
    """
-    MNET = "arcface_mnet"
+    MNET   = "arcface_mnet"
    RESNET = "arcface_resnet"

 class RetinaFaceWeights(str, Enum):
@@ -84,42 +84,42 @@ class LandmarkWeights(str, Enum):
 MODEL_URLS: Dict[Enum, str] = {

    # RetinaFace
-    RetinaFaceWeights.MNET_025: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv1_0.25.onnx',
-    RetinaFaceWeights.MNET_050: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv1_0.50.onnx',
-    RetinaFaceWeights.MNET_V1:  'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv1.onnx',
-    RetinaFaceWeights.MNET_V2:  'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv2.onnx',
-    RetinaFaceWeights.RESNET18: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_r18.onnx',
-    RetinaFaceWeights.RESNET34: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_r34.onnx',
+    RetinaFaceWeights.MNET_025: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.25.onnx',
+    RetinaFaceWeights.MNET_050: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.50.onnx',
+    RetinaFaceWeights.MNET_V1:  'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1.onnx',
+    RetinaFaceWeights.MNET_V2:  'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv2.onnx',
+    RetinaFaceWeights.RESNET18: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r18.onnx',
+    RetinaFaceWeights.RESNET34: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r34.onnx',

    # MobileFace
-    MobileFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    MobileFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    MobileFaceWeights.MNET_V3_SMALL: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    MobileFaceWeights.MNET_V3_LARGE: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
+    MobileFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv1_0.25.onnx',
+    MobileFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv2.onnx',
+    MobileFaceWeights.MNET_V3_SMALL: 'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv3_small.onnx',
+    MobileFaceWeights.MNET_V3_LARGE: 'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv3_large.onnx',

    # SphereFace
-    SphereFaceWeights.SPHERE20: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    SphereFaceWeights.SPHERE36: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
+    SphereFaceWeights.SPHERE20: 'https://github.com/yakhyo/uniface/releases/download/weights/sphere20.onnx',
+    SphereFaceWeights.SPHERE36: 'https://github.com/yakhyo/uniface/releases/download/weights/sphere36.onnx',


    # ArcFace
-    ArcFaceWeights.MNET:   'https://github.com/yakhyo/uniface/releases/download/v0.1.2/w600k_mbf.onnx',
-    ArcFaceWeights.RESNET: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/w600k_r50.onnx',
+    ArcFaceWeights.MNET:   'https://github.com/yakhyo/uniface/releases/download/weights/w600k_mbf.onnx',
+    ArcFaceWeights.RESNET: 'https://github.com/yakhyo/uniface/releases/download/weights/w600k_r50.onnx',

    # SCRFD
-    SCRFDWeights.SCRFD_10G_KPS:  'https://github.com/yakhyo/uniface/releases/download/v0.1.2/scrfd_10g_kps.onnx',
-    SCRFDWeights.SCRFD_500M_KPS: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/scrfd_500m_kps.onnx',
+    SCRFDWeights.SCRFD_10G_KPS:  'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_10g_kps.onnx',
+    SCRFDWeights.SCRFD_500M_KPS: 'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_500m_kps.onnx',


    # DDAFM
-    DDAMFNWeights.AFFECNET7: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/affecnet7.script',
-    DDAMFNWeights.AFFECNET8: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/affecnet8.script',
+    DDAMFNWeights.AFFECNET7: 'https://github.com/yakhyo/uniface/releases/download/weights/affecnet7.script',
+    DDAMFNWeights.AFFECNET8: 'https://github.com/yakhyo/uniface/releases/download/weights/affecnet8.script',

    # AgeGender
-    AgeGenderWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/genderage.onnx',
+    AgeGenderWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/weights/genderage.onnx',

    # Landmarks
-    LandmarkWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/2d106det.onnx',
+    LandmarkWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/weights/2d106det.onnx',
 }

 MODEL_SHA256: Dict[Enum, str] = {
@@ -132,14 +132,14 @@ MODEL_SHA256: Dict[Enum, str] = {
    RetinaFaceWeights.RESNET34: 'bd0263dc2a465d32859555cb1741f2d98991eb0053696e8ee33fec583d30e630',

    # MobileFace
-    MobileFaceWeights.MNET_025:      '#',
-    MobileFaceWeights.MNET_V2:       '#',
-    MobileFaceWeights.MNET_V3_SMALL: '#',
-    MobileFaceWeights.MNET_V3_LARGE: '#',
+    MobileFaceWeights.MNET_025:      'eeda7d23d9c2b40cf77fa8da8e895b5697465192648852216074679657f8ee8b',
+    MobileFaceWeights.MNET_V2:       '38b148284dd48cc898d5d4453104252fbdcbacc105fe3f0b80e78954d9d20d89',
+    MobileFaceWeights.MNET_V3_SMALL: 'd4acafa1039a82957aa8a9a1dac278a401c353a749c39df43de0e29cc1c127c3',
+    MobileFaceWeights.MNET_V3_LARGE: '0e48f8e11f070211716d03e5c65a3db35a5e917cfb5bc30552358629775a142a',

    # SphereFace
-    SphereFaceWeights.SPHERE20: '#',
-    SphereFaceWeights.SPHERE36: '#',
+    SphereFaceWeights.SPHERE20: 'c02878cf658eb1861f580b7e7144b0d27cc29c440bcaa6a99d466d2854f14c9d',
+    SphereFaceWeights.SPHERE36: '13b3890cd5d7dec2b63f7c36fd7ce07403e5a0bbb701d9647c0289e6cbe7bb20',


    # ArcFace
--- a/uniface/detection/retinaface.py
+++ b/uniface/detection/retinaface.py
@@ -287,15 +287,15 @@ if __name__ == "__main__":
    cap = cv2.VideoCapture(0)

    if not cap.isOpened():
-        print("❌ Failed to open webcam.")
+        print("Failed to open webcam.")
        exit()

-    print("📷 Webcam started. Press 'q' to exit.")
+    print("Webcam started. Press 'q' to exit.")

    while True:
        ret, frame = cap.read()
        if not ret:
-            print("❌ Failed to read frame.")
+            print("Failed to read frame.")
            break

        # Get face detections as list of dictionaries
--- a/uniface/detection/scrfd.py
+++ b/uniface/detection/scrfd.py
@@ -280,15 +280,15 @@ if __name__ == "__main__":
    cap = cv2.VideoCapture(0)

    if not cap.isOpened():
-        print("❌ Failed to open webcam.")
+        print("Failed to open webcam.")
        exit()

-    print("📷 Webcam started. Press 'q' to exit.")
+    print("Webcam started. Press 'q' to exit.")

    while True:
        ret, frame = cap.read()
        if not ret:
-            print("❌ Failed to read frame.")
+            print("Failed to read frame.")
            break

        # Get face detections as list of dictionaries
--- a/uniface/face_utils.py
+++ b/uniface/face_utils.py
@@ -5,7 +5,7 @@
 import cv2
 import numpy as np
 from skimage.transform import SimilarityTransform
-from typing import Tuple
+from typing import Tuple, Union


 __all__ = ["face_alignment", "compute_similarity", "bbox_center_alignment", "transform_points_2d"]
@@ -24,13 +24,14 @@ reference_alignment: np.ndarray = np.array(
 )


-def estimate_norm(landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarray, np.ndarray]:
+def estimate_norm(landmark: np.ndarray, image_size: Union[int, Tuple[int, int]] = 112) -> Tuple[np.ndarray, np.ndarray]:
    """
    Estimate the normalization transformation matrix for facial landmarks.

    Args:
        landmark (np.ndarray): Array of shape (5, 2) representing the coordinates of the facial landmarks.
-        image_size (int, optional): The size of the output image. Default is 112.
+        image_size (Union[int, Tuple[int, int]], optional): The size of the output image.
+            Can be an integer (for square images) or a tuple (width, height). Default is 112.

    Returns:
        np.ndarray: The 2x3 transformation matrix for aligning the landmarks.
@@ -41,13 +42,20 @@ def estimate_norm(landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarr
                        or if image_size is not a multiple of 112 or 128.
    """
    assert landmark.shape == (5, 2), "Landmark array must have shape (5, 2)."
-    assert image_size % 112 == 0 or image_size % 128 == 0, "Image size must be a multiple of 112 or 128."

-    if image_size % 112 == 0:
-        ratio = float(image_size) / 112.0
+    # Handle both int and tuple inputs
+    if isinstance(image_size, tuple):
+        size = image_size[0]  # Use width for ratio calculation
+    else:
+        size = image_size
+
+    assert size % 112 == 0 or size % 128 == 0, "Image size must be a multiple of 112 or 128."
+
+    if size % 112 == 0:
+        ratio = float(size) / 112.0
        diff_x = 0.0
    else:
-        ratio = float(image_size) / 128.0
+        ratio = float(size) / 128.0
        diff_x = 8.0 * ratio

    # Adjust reference alignment based on ratio and diff_x
@@ -64,14 +72,15 @@ def estimate_norm(landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarr
    return matrix, inverse_matrix


-def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarray, np.ndarray]:
+def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: Union[int, Tuple[int, int]] = 112) -> Tuple[np.ndarray, np.ndarray]:
    """
    Align the face in the input image based on the given facial landmarks.

    Args:
        image (np.ndarray): Input image as a NumPy array.
        landmark (np.ndarray): Array of shape (5, 2) representing the coordinates of the facial landmarks.
-        image_size (int, optional): The size of the aligned output image. Default is 112.
+        image_size (Union[int, Tuple[int, int]], optional): The size of the aligned output image.
+            Can be an integer (for square images) or a tuple (width, height). Default is 112.

    Returns:
        np.ndarray: The aligned face as a NumPy array.
@@ -80,8 +89,14 @@ def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: int = 11
    # Get the transformation matrix
    M, M_inv = estimate_norm(landmark, image_size)

+    # Handle both int and tuple for warpAffine output size
+    if isinstance(image_size, int):
+        output_size = (image_size, image_size)
+    else:
+        output_size = image_size
+
    # Warp the input image to align the face
-    warped = cv2.warpAffine(image, M, (image_size, image_size), borderValue=0.0)
+    warped = cv2.warpAffine(image, M, output_size, borderValue=0.0)

    return warped, M_inv

--- a/uniface/landmark/models.py
+++ b/uniface/landmark/models.py
@@ -157,15 +157,13 @@ class Landmark106(BaseLandmarker):



-# TODO: For testing purposes only, remote later
+# Testing code
 if __name__ == "__main__":
-    # UPDATED: Use the high-level factory functions
-    from uniface.detection import create_detector
-    from uniface.landmark import create_landmarker
+    from uniface.detection import RetinaFace
+    from uniface.landmark import Landmark106

-    # 1. Create the detector and landmarker using the new API
-    face_detector = create_detector('retinaface')
-    landmarker = create_landmarker() # Uses the default '2d106det' method
+    face_detector = RetinaFace()
+    landmarker = Landmark106()

    cap = cv2.VideoCapture(0)
    if not cap.isOpened():
--- a/uniface/recognition/base.py
+++ b/uniface/recognition/base.py
@@ -109,19 +109,23 @@ class BaseRecognizer(ABC):

        return blob

-    def get_embedding(self, image: np.ndarray, landmarks: np.ndarray) -> np.ndarray:
+    def get_embedding(self, image: np.ndarray, landmarks: np.ndarray = None) -> np.ndarray:
        """
        Extracts face embedding from an image.

        Args:
-            image: Input face image (BGR format).
-            landmarks: Facial landmarks (5 points for alignment).
+            image: Input face image (BGR format). If already aligned (112x112), landmarks can be None.
+            landmarks: Facial landmarks (5 points for alignment). Optional if image is already aligned.

        Returns:
            Face embedding vector (typically 512-dimensional).
        """
-        # Align face using landmarks
-        aligned_face, _ = face_alignment(image, landmarks)
+        # If landmarks are provided, align the face first
+        if landmarks is not None:
+            aligned_face, _ = face_alignment(image, landmarks, image_size=self.input_size)
+        else:
+            # Assume image is already aligned
+            aligned_face = image

        # Generate embedding from aligned face
        face_blob = self.preprocess(aligned_face)