Update README.md

README.md

@@ -16,22 +16,93 @@ Custom trained models for the soon to be released **Forbidden Vision** ComfyUI c
 </div>
 
 ---
+# Forbidden Vision Face Models
 
-Custom-trained models for high-performance face detection, landmark estimation, and segmentation across realistic, anime, and NSFW content.
+Custom-trained models for face detection, landmark estimation, and segmentation across realistic, anime, and NSFW content.
+
+Part of the [ComfyUI Forbidden Vision](https://github.com/luxdelux7/ComfyUI-Forbidden-Vision) node pack.
+
+## Models
+
+| Model | Purpose | Architecture |
+|-------|---------|--------------|
+| **Face Detection** | Locate faces in images | YOLOv11-small |
+| **Landmark Detection** | Facial orientation & alignment | MobileNetV4-Conv-Small |
+| **Segmentation** | Precise face masks | GhostNetV2-100 |
+
+## What Makes These Different?
+
+**Trained on what you actually generate.**
 
-🎯 What Makes These Different?
-Trained on what you actually generate.
 Unlike general-purpose face models trained only on real photographs, these models were specifically trained on:
 
-Diffusion outputs from CivitAI (realistic and anime styles)
-Danbooru anime dataset
-Real photography for ground truth accuracy
-NSFW content without artificial restrictions
+- **Diffusion outputs** from CivitAI (realistic and anime styles)
+- **Danbooru** anime dataset
+- **Real photography** for ground truth accuracy
+- **NSFW content** without artificial restrictions
 
 This mixed training approach ensures reliable performance across:
+- ✓ Both realistic and anime art styles
+- ✓ Difficult angles, occlusions, and expressions  
+- ✓ Low-quality generations and artifacts
+- ✓ SFW and NSFW content equally
+- ✓ Edge cases that break traditional face detectors
+
+## Model Details
+
+### Face Detection (YOLOv11-Small)
+
+Primary face detection and bounding box localization.
+
+**Training Data:**
+- 50k+ images from CivitAI diffusion outputs (SDXL, SD1.5, Pony)
+- 30k+ Danbooru anime images
+- 20k+ real photographs
+
+**Features:**
+- Handles extreme angles and rotations
+- Detects partially occluded faces
+- Works with artistic distortions and stylization
+- Reliable on both photorealistic and anime styles
+
+### Landmark Detection (MobileNetV4-Conv-Small)
+
+Facial orientation and alignment estimation with 68-point landmark regression.
+
+**Training Data:**
+- 40k+ annotated faces from mixed sources
+- Manual annotation for anime/artistic styles
+- Augmented with rotation and perspective transforms
+
+**Features:**
+- Fast orientation detection for auto-rotation
+- Works on both realistic and anime faces
+- Handles partial occlusions and unusual expressions
+
+### Segmentation (GhostNetV2-100)
+
+Precise face mask generation including hair and complex boundaries.
+
+**Training Data:**
+- 35k+ faces with pixel-accurate mask annotations
+- Mixed realistic, anime, and artistic styles
+- Includes hair, accessories, and complex boundaries
+
+**Features:**
+- Pixel-accurate boundaries including hair
+- Handles complex occlusions (hands, objects)
+- Works with artistic styles and effects
+- Smooth mask edges for seamless blending
+
+## Usage
+
+These models are automatically downloaded and used by the **Fixer** node in ComfyUI Forbidden Vision.
+
+## License
+
+GNU General Public License v3.0
+
+## Contact
 
-✓ Both realistic and anime art styles
-✓ Difficult angles, occlusions, and expressions
-✓ Low-quality generations and artifacts
-✓ SFW and NSFW content equally
-✓ Edge cases that break traditional face detectors
+- GitHub Issues: [ComfyUI-Forbidden-Vision](https://github.com/luxdelux7/ComfyUI-Forbidden-Vision/issues)
+- Support: [Ko-fi](https://ko-fi.com/luxdelux)