Initial commit

app.py

@@ -0,0 +1,216 @@
+import gradio as gr
+import requests
+from PIL import Image
+import io
+import openai
+from gradio_image_annotation import image_annotator
+
+# Image Generation Functions
+def generate_ideogram_image(api_key, prompt, aspect_ratio="ASPECT_1_1"):
+    """Generate image using Ideogram API"""
+    if not api_key or not prompt:
+        return None, "Please provide both API key and prompt"
+    
+    url = "https://api.ideogram.ai/generate"
+    headers = {
+        "Api-Key": api_key,
+        "Content-Type": "application/json"
+    }
+    
+    payload = {
+        "image_request": {
+            "prompt": prompt,
+            "aspect_ratio": aspect_ratio,
+            "model": "V_2",
+            "magic_prompt_option": "AUTO"
+        }
+    }
+    
+    try:
+        response = requests.post(url, json=payload, headers=headers)
+        if response.status_code == 200:
+            result = response.json()
+            if result.get("data"):
+                image_url = result["data"][0]["url"]
+                # Download and return the image
+                img_response = requests.get(image_url)
+                image = Image.open(io.BytesIO(img_response.content))
+                return image, "Image generated successfully!"
+            else:
+                return None, "No image data received"
+        else:
+            return None, f"Error: {response.status_code} - {response.text}"
+    except Exception as e:
+        return None, f"Error generating image: {str(e)}"
+
+def generate_dalle_image(api_key, prompt, size="1024x1024"):
+    """Generate image using DALL-E 3 API"""
+    if not api_key or not prompt:
+        return None, "Please provide both API key and prompt"
+    
+    try:
+        client = openai.OpenAI(api_key=api_key)
+        response = client.images.generate(
+            model="dall-e-3",
+            prompt=prompt,
+            size=size,
+            quality="standard",
+            n=1,
+        )
+        
+        # Download the image from URL
+        image_url = response.data[0].url
+        img_response = requests.get(image_url)
+        image = Image.open(io.BytesIO(img_response.content))
+        return image, "Image generated successfully with DALL-E 3!"
+    
+    except Exception as e:
+        return None, f"Error generating image: {str(e)}"
+
+def process_uploaded_image(image):
+    """Process uploaded image"""
+    if image is None:
+        return None, "No image uploaded"
+    return image, "Image uploaded successfully!"
+
+# Image Annotation Functions
+def get_annotations_json(annotations):
+    """Extract annotations as JSON"""
+    return annotations.get("boxes", [])
+
+def save_annotated_image(annotations):
+    """Return the annotated image"""
+    if annotations and annotations.get("image") is not None:
+        return annotations["image"]
+    return None
+
+# Create the Gradio Interface
+with gr.Blocks(title="AI Image Generator & Annotator MCP Server") as demo:
+    gr.Markdown("# 🎨 AI Image Generator & Annotator")
+    gr.Markdown("Generate images with AI or upload your own, then add annotations!")
+    
+    # Tab 1: Image Generation
+    with gr.Tab("🖼️ Image Generation", id="generation_tab"):
+        gr.Markdown("## Generate or Upload Images")
+        
+        with gr.Row():
+            with gr.Column():
+                # API Key inputs
+                ideogram_key = gr.Textbox(
+                    label="Ideogram API Key", 
+                    type="password", 
+                    placeholder="Enter your Ideogram API key"
+                )
+                dalle_key = gr.Textbox(
+                    label="OpenAI API Key", 
+                    type="password", 
+                    placeholder="Enter your OpenAI API key"
+                )
+                
+                # Prompt input
+                prompt = gr.Textbox(
+                    label="Image Prompt", 
+                    placeholder="Describe the image you want to generate...",
+                    lines=3
+                )
+                
+                # Generation options
+                with gr.Row():
+                    ideogram_aspect = gr.Dropdown(
+                        choices=["ASPECT_1_1", "ASPECT_16_9", "ASPECT_9_16", "ASPECT_4_3", "ASPECT_3_4"],
+                        value="ASPECT_1_1",
+                        label="Ideogram Aspect Ratio"
+                    )
+                    dalle_size = gr.Dropdown(
+                        choices=["1024x1024", "1792x1024", "1024x1792"],
+                        value="1024x1024",
+                        label="DALL-E Size"
+                    )
+                
+                # Generation buttons
+                with gr.Row():
+                    ideogram_btn = gr.Button("🎨 Generate with Ideogram", variant="primary")
+                    dalle_btn = gr.Button("🤖 Generate with DALL-E 3", variant="primary")
+                
+                # Upload option
+                gr.Markdown("### Or Upload Your Own Image")
+                upload_image = gr.Image(label="Upload Image", type="pil")
+                upload_btn = gr.Button("📁 Process Uploaded Image")
+            
+            with gr.Column():
+                # Output
+                generated_image = gr.Image(label="Generated/Uploaded Image", type="pil")
+                status_message = gr.Textbox(label="Status", interactive=False)
+        
+        # Event handlers for Tab 1
+        ideogram_btn.click(
+            generate_ideogram_image,
+            inputs=[ideogram_key, prompt, ideogram_aspect],
+            outputs=[generated_image, status_message]
+        )
+        
+        dalle_btn.click(
+            generate_dalle_image,
+            inputs=[dalle_key, prompt, dalle_size],
+            outputs=[generated_image, status_message]
+        )
+        
+        upload_btn.click(
+            process_uploaded_image,
+            inputs=[upload_image],
+            outputs=[generated_image, status_message]
+        )
+    
+    # Tab 2: Image Annotation
+    with gr.Tab("📝 Image Annotation", id="annotation_tab"):
+        gr.Markdown("## Add Signs and Annotations to Images")
+        gr.Markdown("Upload an image or use one from the generation tab, then add bounding boxes and labels.")
+        
+        with gr.Row():
+            with gr.Column():
+                # Image annotation component
+                annotator = image_annotator(
+                    label="Image Annotator",
+                    label_list=["Person", "Object", "Vehicle", "Animal", "Building", "Sign", "Text", "Custom"],
+                    label_colors=[
+                        (255, 0, 0),    # Red for Person
+                        (0, 255, 0),    # Green for Object  
+                        (0, 0, 255),    # Blue for Vehicle
+                        (255, 255, 0),  # Yellow for Animal
+                        (255, 0, 255),  # Magenta for Building
+                        (0, 255, 255),  # Cyan for Sign
+                        (128, 0, 128),  # Purple for Text
+                        (255, 165, 0)   # Orange for Custom
+                    ],
+                    image_type="pil"
+                )
+                
+                with gr.Row():
+                    get_annotations_btn = gr.Button("📊 Get Annotations", variant="secondary")
+                    save_image_btn = gr.Button("💾 Save Annotated Image", variant="primary")
+            
+            with gr.Column():
+                # Outputs
+                annotated_output = gr.Image(label="Annotated Image")
+                annotations_json = gr.JSON(label="Annotations Data")
+        
+        # Event handlers for Tab 2
+        get_annotations_btn.click(
+            get_annotations_json,
+            inputs=[annotator],
+            outputs=[annotations_json]
+        )
+        
+        save_image_btn.click(
+            save_annotated_image,
+            inputs=[annotator],
+            outputs=[annotated_output]
+        )
+
+# Launch as MCP Server
+if __name__ == "__main__":
+    demo.launch(
+        share=True,       # Create public link for testing
+        server_name="0.0.0.0",
+        server_port=7860
+    )

requirements.txt

@@ -0,0 +1,35 @@
+# Core web interface and MCP server
+gradio>=4.0.0
+gradio_client>=0.8.0
+
+# Image annotation component
+gradio_image_annotation>=0.3.0
+
+# HTTP requests for API calls
+requests>=2.31.0
+
+# Image processing
+Pillow>=10.0.0
+
+# OpenAI API for DALL-E
+openai>=1.10.0
+
+# Additional dependencies for image handling
+numpy>=1.24.0
+opencv-python>=4.8.0
+
+# For MCP server functionality
+fastapi>=0.104.0
+uvicorn>=0.24.0
+
+# For handling environment variables (optional but recommended)
+python-dotenv>=1.0.0
+
+# For enhanced error handling and logging
+loguru>=0.7.0
+
+# For data validation (useful for API responses)
+pydantic>=2.5.0
+
+# For async operations (if needed for future features)
+aiohttp>=3.9.0