Update README.md

README.md

@@ -11,26 +11,19 @@ library_name: ultralytics
 ---
 ## Available Models  
 ### Anzhc's Face segmentation:  
-Small segmentation model aiming to create accurate masks of face for improved inpainting quality with adetailer extension.  
-Full showcase can be found at: https://civitai.com/models/293448/anzhcs-face-segmentation-prototype-or-yolov8-or-adetailer-model  
-Particularly useful at close-ups, as standard YOLO Face burns your generation.  
-Also it improves details better, while not inpainting area around face itself.  
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/8U8uuOAMlX2OGdw9Scvfd.png)
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/e_QPcmILsCUkAiKth02m7.png)
-
-### Anzhc's Head segmentation: 
-Lightweight head segmentation model for variable tasks and mediums(i.e. anime, real, cartoon, etc.)
-Full description and examples can be found at: https://civitai.com/models/326568
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/CXxbSaDm6pdQhgqDQgC5e.png)
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/NLxowgr8dAzfy_x10G3fk.png)
-
-### Anzhc's Eyes segmentation: 
-Miniature model to select sclera area, while trying to not go over it, and not select eyelashes.
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/DXHbFpVcUikj-aUo2kkNw.png)
-
-full description and examples here: https://civitai.com/models/342514/anzhcs-beautifeyer-or-yolov8-or-adetailer-model
+Series of models aiming at detecting and segmenting face accurately.
+| Model                       | Target                | mAP 50                        | mAP 50-95                 |Classes        |Training Resolution|
+| --------------------------- | --------------------- | ----------------------------- | ------------------------- |---------------|-------------------|
+  | Anzhc Face -seg.pt             | Face: illustration, real   | LOST DATA               | LOST DATA             |2(male, female)| 640|
+  | Anzhc Face -seg-hd.pt          | Face: illustration, real   | LOST DATA               | LOST DATA             |2(male, female)|1024|
+  | Anzhc Face seg 640 v2 y8n.pt   | Face: illustration, real   | 0.872(box),0.872(mask)  | 0.835(box),0.752(mask)|1(face)        | 640|
+  | Anzhc Face seg 768 v2 y8n.pt   | Face: illustration, real   | 0.86(box),0.86(mask)    | 0.81(box),0.726(mask) |1(face)        | 768|
+  | Anzhc Face seg 768MS v2 y8n.pt | Face: illustration, real   | 0.866(box),0.866(mask)  | 0.816(box),0.72(mask) |1(face)        | 768|(Multi-scale)|
+  | Anzhc Face seg 1024 v2 y8n.pt  | Face: illustration, real   | 0.872(box),0.872(mask)  | 0.804(box),0.726(mask)|1(face)        | 1024|
+
+Take those stats with a grain of salt, since im pretty sure i re-scrambled dataset partition after training those models ages ago.
+Benchmark was performed in 640px.
+Difference in v2 models are only in their target resolution, so their performance spread is marginal.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/G1vywwrYQOPSK9t3MZTen.png)
+
+/--UNDER CONSTRUCTION--/