Upload app.py

app.py

@@ -5,7 +5,7 @@ import base64
 from PIL import Image, ImageDraw, ImageFont
 import io
 
-def process_with_openrouter(image, prompt, api_key, model="google/gemini-2.5-pro", temperature=0.5):
+def process_with_openrouter(image, prompt, api_key, model="openai/gpt-5-chat", temperature=0.5):
     """Process image with OpenRouter API for object detection"""
     if not api_key:
         return "Please enter your OpenRouter API key", "error"
@@ -220,8 +220,20 @@ def create_interface():
                     type="password"
                 )
                 
-                model = gr.Dropdown(
+                with gr.Row():
+                    use_preset = gr.Radio(
+                        choices=["Preset Model", "Custom Model"],
+                        value="Preset Model",
+                        label="Model Selection",
+                        info="Choose preset or enter custom OpenRouter model"
+                    )
+                
+                model_preset = gr.Dropdown(
                     choices=[
+                        "openai/gpt-5-chat",
+                        "openai/gpt-5-mini",
+                        "anthropic/claude-opus-4.1",
+                        "x-ai/grok-4",
                         "google/gemini-2.5-pro",
                         "google/gemini-1.5-pro",
                         "google/gemini-1.5-flash",
@@ -229,8 +241,17 @@ def create_interface():
                         "openai/gpt-4o",
                         "openai/gpt-4o-mini"
                     ],
-                    value="google/gemini-2.5-pro",
-                    label="Detection Model"
+                    value="openai/gpt-5-chat",
+                    label="Preset Models",
+                    info="Select from popular OpenRouter models",
+                    visible=True
+                )
+                
+                custom_model_input = gr.Textbox(
+                    label="Custom Model ID",
+                    placeholder="Enter any OpenRouter model ID (e.g., google/gemini-1.5-flash, anthropic/claude-3-haiku)",
+                    visible=False,
+                    info="Copy model IDs from openrouter.ai/models"
                 )
                 
                 detection_mode = gr.Radio(
@@ -303,7 +324,20 @@ concrete spalling deeper than 1cm""",
                     lines=3
                 )
         
-        def process_detection(image, detailed_specs, conf_threshold, api_key_val, model_val, temp_val, mode_val):
+        # Show/hide model input based on selection
+        def update_model_visibility(use_preset_val):
+            if use_preset_val == "Custom Model":
+                return gr.update(visible=False), gr.update(visible=True)
+            else:
+                return gr.update(visible=True), gr.update(visible=False)
+        
+        use_preset.change(
+            update_model_visibility,
+            inputs=[use_preset],
+            outputs=[model_preset, custom_model_input]
+        )
+        
+        def process_detection(image, detailed_specs, conf_threshold, api_key_val, use_preset_val, model_preset_val, custom_model_val, temp_val, mode_val):
             if not api_key_val:
                 return None, "❌ Please enter your OpenRouter API key", "No API key provided"
             
@@ -313,10 +347,18 @@ concrete spalling deeper than 1cm""",
             if not detailed_specs or not detailed_specs.strip():
                 return None, "❌ Please enter at least one detailed specification", "No specifications provided"
             
+            # Determine which model to use
+            if use_preset_val == "Custom Model":
+                if not custom_model_val or custom_model_val.strip() == "":
+                    return None, "❌ Please enter a custom model ID", "Custom model required"
+                final_model = custom_model_val.strip()
+            else:
+                final_model = model_preset_val
+            
             try:
                 prompt = create_detection_prompt(detailed_specs, conf_threshold, mode_val)
                 
-                result, error = process_with_openrouter(image, prompt, api_key_val, model_val, temp_val)
+                result, error = process_with_openrouter(image, prompt, api_key_val, final_model, temp_val)
                 
                 if error:
                     return None, f"❌ Error: {result}", "Detection failed"
@@ -334,7 +376,7 @@ concrete spalling deeper than 1cm""",
                         "exclude": "Excluding objects matching detailed specifications"
                     }
                     
-                    summary_text = f"✅ {mode_descriptions.get(mode_val, 'Detection')} - Found {len(filtered_detections)} objects"
+                    summary_text = f"✅ {mode_descriptions.get(mode_val, 'Detection')} - Found {len(filtered_detections)} objects\n🤖 Model: {final_model}"
                     
                     if filtered_detections:
                         # Group by class and show details
@@ -374,7 +416,7 @@ concrete spalling deeper than 1cm""",
         
         detect_btn.click(
             process_detection,
-            inputs=[image_input, detailed_specifications, confidence_threshold, api_key, model, temperature, detection_mode],
+            inputs=[image_input, detailed_specifications, confidence_threshold, api_key, use_preset, model_preset, custom_model_input, temperature, detection_mode],
             outputs=[annotated_image, detection_results, detection_summary]
         )
         
@@ -384,6 +426,15 @@ concrete spalling deeper than 1cm""",
         - **Include Mode**: Detect your specified criteria plus any other objects found
         - **Exclude Mode**: Detect everything except objects matching your specifications
         
+        ### 🤖 Model Selection
+        **Default Models (Recommended):**
+        - `openai/gpt-5-chat` - Latest GPT-5 with advanced vision capabilities (Default)
+        - `openai/gpt-5-mini` - Faster, efficient GPT-5 variant
+        - `anthropic/claude-opus-4.1` - Next-gen Claude with superior reasoning
+        - `x-ai/grok-4` - Advanced Grok model with detailed analysis
+        
+        **Custom Models**: Enter any OpenRouter model ID from [openrouter.ai/models](https://openrouter.ai/models)
+        
         ### Example Detailed Specifications:
         ```
         crack width more than 2mm