Update app.py

app.py

@@ -58,7 +58,7 @@ def _load_age_model():
 
     print("[AgeModel] Downloading ONNX from HuggingFace Hub …")
     onnx_path = hf_hub_download(
-        repo_id  = "TrungTran/faceage-dino",
+        repo_id  = "trungthanhtran/faceage-dino",
         filename = "faceage_dino_fp32.onnx",
     )
 
@@ -268,7 +268,7 @@ Upload a photo. **YuNet** auto-detects faces, then **FaceAge-DINOv3** predicts a
 
 | | |
 |--|--|
-| 🏆 LAGENDA 84k MAE | **3.760** (beats MiVOLO v2 measured on the public model 3.859) |
+| 🏆 LAGENDA 84k MAE | **3.760** (beats MiVOLO v2 measured 3.859) |
 | 🧠 Backbone | DINOv3-ViT-L/16 (Meta AI, 307M params) |
 | ⚡ Speed | ~100 ms / face on CPU (ONNX FP32) |
 | 🔍 Detector | YuNet (OpenCV, ~350 KB) |
@@ -281,7 +281,8 @@ with gr.Blocks(title="FaceAge-DINOv3", theme=gr.themes.Soft()) as demo:
 
     with gr.Row():
         with gr.Column(scale=1):
-            inp_img   = gr.Image(type="pil", label="📷 Upload photo")
+            inp_img   = gr.Image(type="pil", label="📷 Upload photo or use webcam",
+                                 sources=["upload", "webcam", "clipboard"])
             with gr.Row():
                 inp_max   = gr.Slider(1, 10, value=5, step=1,
                                       label="Max faces")
@@ -301,7 +302,7 @@ with gr.Blocks(title="FaceAge-DINOv3", theme=gr.themes.Soft()) as demo:
 
     gr.Markdown("""
 ---
-*Trained on Our data collection*
+*Trained on LAGENDA · IMDB-Clean · UTKFace · AgeDB · FairFace · Open Images.*
 *DINOv3-ViT-L pretrained by Meta AI on LVD-1.68B images.*
 """)