restore maxDim=256 — 160 was too coarse for sprinter-scale objects

README.md

@@ -11,10 +11,8 @@ short_description: Open-vocabulary detection in-browser via WebGPU
 
 # Falcon Perception — In-Browser Demo
 
-Interactive demo of [tiiuae/Falcon-Perception](https://huggingface.co/tiiuae/Falcon-Perception), a 0.6B-parameter vision-language model for open-vocabulary detection.
+Interactive demo of [tiiuae/Falcon-Perception](https://huggingface.co/tiiuae/Falcon-Perception), a 0.6B-parameter VLM for open-vocabulary detection.
 
-Image, webcam, and video input. Three render modes: Detection, Segmentation, and a HUD Tracker with corner brackets + amber TGT/BRG/C labels for the plane-tracking use case.
+Image, webcam, and video input with Detection, Segmentation, and HUD Tracker render modes. Runs multi-threaded WASM via `coi-serviceworker`; example images are base64-inlined so the COEP-enforced document can still load them.
 
-Uses multi-threaded WASM via [coi-serviceworker](https://github.com/gzuidhof/coi-serviceworker) for faster inference. Example images are base64-inlined to bypass the COEP / CORP restriction that would otherwise block same-origin asset fetches.
-
-Weights: [shreyask/falcon-perception-onnx-webgpu](https://huggingface.co/shreyask/falcon-perception-onnx-webgpu). `unified_v2.onnx` restores 2D golden RoPE on image tokens.
+Weights: [shreyask/falcon-perception-onnx-webgpu](https://huggingface.co/shreyask/falcon-perception-onnx-webgpu).

index.html

@@ -15,7 +15,7 @@
         });
       }
     </script>
-    <script type="module" crossorigin src="/assets/index-BSIp3TMC.js"></script>
+    <script type="module" crossorigin src="/assets/index-Bc_fcDsI.js"></script>
     <link rel="stylesheet" crossorigin href="/assets/index-DpjQuLKn.css">
   </head>
   <body class="bg-gray-950 text-gray-100 antialiased">