app.py

import os
import sys
import gradio as gr
import numpy as np
from PIL import Image
import io
import tempfile
from pathlib import Path

# Add notebook directory to path for inference code
NOTEBOOK_PATH = "notebook"
if os.path.exists(NOTEBOOK_PATH):
    sys.path.append(NOTEBOOK_PATH)

# Import inference code with error handling
try:
    from inference import Inference, load_image, load_single_mask
    INFERENCE_AVAILABLE = True
except ImportError as e:
    print(f"Warning: Could not import inference module: {e}")
    print("Running in demo mode with mock functionality")
    INFERENCE_AVAILABLE = False

def create_demo_3d_output():
    """Create a demo 3D file for demonstration purposes"""
    demo_content = b"""# Demo 3D model file
ply
format ascii 1.0
element vertex 1000
property float x
property float y
property float z
property float nx
property float ny
property float nz
property uchar red
property uchar green
property uchar blue
end_header
"""
    # Add some demo vertices
    for i in range(1000):
        x, y, z = np.random.normal(0, 1, 3)
        nx, ny, nz = np.random.normal(0, 1, 3)
        r, g, b = np.random.randint(0, 256, 3)
        demo_content += f"{x:.3f} {y:.3f} {z:.3f} {nx:.3f} {ny:.3f} {nz:.3f} {r} {g} {b}\n"
    
    return demo_content

def load_and_validate_image(image_path):
    """Load and validate image file"""
    try:
        img = Image.open(image_path)
        img = img.convert('RGB')
        return np.array(img)
    except Exception as e:
        raise ValueError(f"Error loading image: {str(e)}")

def process_image_to_3d(image, mask=None, seed=42, model_tag="hf"):
    """Process image to 3D model"""
    try:
        if not INFERENCE_AVAILABLE:
            # Demo mode - return mock output
            demo_content = create_demo_3d_output()
            return {
                "status": "demo",
                "message": "Demo mode - inference module not available",
                "file_content": demo_content,
                "filename": "demo_splat.ply"
            }
        
        # Initialize inference if not already done
        config_path = f"checkpoints/{model_tag}/pipeline.yaml"
        
        # Create temporary files for the uploaded image and mask
        with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as img_temp:
            img = Image.fromarray(image)
            img.save(img_temp.name)
            temp_image_path = img_temp.name
        
        temp_mask_path = None
        if mask is not None:
            with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as mask_temp:
                mask_img = Image.fromarray(mask)
                mask_img.save(mask_temp.name)
                temp_mask_path = mask_temp.name
        
        # Load the model
        inference = Inference(config_path, compile=False)
        
        # Load image and mask
        loaded_image = load_image(temp_image_path)
        loaded_mask = load_single_mask(temp_mask_path) if temp_mask_path else None
        
        # Run inference
        output = inference(loaded_image, loaded_mask, seed=seed)
        
        # Export gaussian splat
        output_path = f"output_splat_{seed}.ply"
        output["gs"].save_ply(output_path)
        
        # Read the generated file
        with open(output_path, "rb") as f:
            file_content = f.read()
        
        # Clean up temporary files
        try:
            os.unlink(temp_image_path)
            if temp_mask_path:
                os.unlink(temp_mask_path)
            os.unlink(output_path)
        except:
            pass
        
        return {
            "status": "success",
            "message": "3D model generated successfully!",
            "file_content": file_content,
            "filename": f"splat_{seed}.ply"
        }
        
    except Exception as e:
        return {
            "status": "error",
            "message": f"Error processing image: {str(e)}",
            "file_content": None,
            "filename": None
        }

def update_mask_status(mask_status, mask_image):
    """Update mask upload status"""
    if mask_image is not None:
        return "✓ Mask uploaded", gr.update(visible=True)
    else:
        return "No mask uploaded", gr.update(visible=False)

def process_wrapper(image, mask, seed, model_tag):
    """Wrapper function for gradio interface"""
    if image is None:
        return "Please upload an image first", None, None
    
    # Show processing status
    yield "Processing image to 3D model...", None, None
    
    result = process_image_to_3d(image, mask, seed, model_tag)
    
    if result["status"] == "success":
        yield result["message"], result["file_content"], result["filename"]
    elif result["status"] == "demo":
        yield "Demo: " + result["message"], result["file_content"], result["filename"]
    else:
        yield "Error: " + result["message"], None, None

def create_interface():
    """Create the Gradio interface"""
    
    # Custom CSS for better styling
    css = """
    .gradio-container {
        max-width: 1200px !important;
        margin: auto !important;
    }
    .upload-section {
        border: 2px dashed #ccc;
        padding: 20px;
        border-radius: 10px;
        background-color: #f9f9f9;
    }
    .status-message {
        padding: 10px;
        border-radius: 5px;
        margin: 10px 0;
    }
    .success {
        background-color: #d4edda;
        color: #155724;
        border: 1px solid #c3e6cb;
    }
    .error {
        background-color: #f8d7da;
        color: #721c24;
        border: 1px solid #f5c6cb;
    }
    """
    
    with gr.Blocks(css=css, title="Image to 3D Converter") as demo:
        
        # Header
        gr.HTML("""
        <div style="text-align: center; padding: 20px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); color: white; border-radius: 10px; margin-bottom: 30px;">
            <h1 style="margin: 0; font-size: 2.5em;">🎨 Image to 3D Converter</h1>
            <p style="margin: 10px 0 0 0; font-size: 1.2em;">Transform your 2D images into stunning 3D models</p>
            <div style="margin-top: 15px; font-size: 0.9em;">
                <a href="https://huggingface.co/spaces/akhaliq/anycoder" target="_blank" style="color: #fff; text-decoration: none; border: 1px solid rgba(255,255,255,0.5); padding: 5px 15px; border-radius: 20px;">Built with anycoder</a>
            </div>
        </div>
        """)
        
        with gr.Row():
            with gr.Column(scale=1):
                gr.HTML("""
                <div class="upload-section">
                    <h3>📤 Upload Image</h3>
                    <p>Upload the image you want to convert to 3D</p>
                </div>
                """)
                
                image_input = gr.Image(
                    label="Input Image",
                    type="numpy",
                    image_mode="RGB",
                    elem_classes=["upload-area"]
                )
                
                with gr.Row():
                    mask_upload = gr.Image(
                        label="Optional Mask",
                        type="numpy", 
                        image_mode="L",
                        image_edit=True,
                        elem_classes=["upload-area"]
                    )
                
                mask_status = gr.Textbox(
                    label="Mask Status",
                    value="No mask uploaded",
                    interactive=False,
                    elem_classes=["mask-status"]
                )
            
            with gr.Column(scale=1):
                gr.HTML("""
                <div style="background: #f0f8ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
                    <h3>⚙️ Configuration</h3>
                </div>
                """)
                
                with gr.Row():
                    seed = gr.Slider(
                        minimum=0,
                        maximum=999999,
                        value=42,
                        step=1,
                        label="Random Seed",
                        info="Controls the randomness in generation"
                    )
                
                model_tag = gr.Dropdown(
                    choices=["hf"],
                    value="hf",
                    label="Model Tag",
                    info="Select the model configuration"
                )
                
                run_button = gr.Button(
                    "🚀 Generate 3D Model",
                    variant="primary",
                    size="lg"
                )
        
        with gr.Row():
            with gr.Column():
                status_output = gr.Textbox(
                    label="Status",
                    max_lines=5,
                    interactive=False,
                    elem_classes=["status-message"]
                )
        
        with gr.Row():
            with gr.Column():
                output_file = gr.File(
                    label="Download 3D Model",
                    file_types=[".ply"],
                    visible=False,
                    elem_classes=["download-section"]
                )
        
        # Wire up the interface
        mask_upload.upload(
            fn=update_mask_status,
            inputs=[mask_status, mask_upload],
            outputs=[mask_status, output_file]
        )
        
        run_button.click(
            fn=process_wrapper,
            inputs=[image_input, mask_upload, seed, model_tag],
            outputs=[status_output, output_file, gr.File()]
        )
        
        # Examples section
        gr.HTML("""
        <div style="margin-top: 40px; text-align: center;">
            <h3>📖 How to Use</h3>
            <div style="display: flex; justify-content: space-around; margin-top: 20px; flex-wrap: wrap;">
                <div style="max-width: 300px; padding: 20px; background: #f8f9fa; border-radius: 10px; margin: 10px;">
                    <h4>1. Upload Image</h4>
                    <p>Choose a clear, well-lit image for best results</p>
                </div>
                <div style="max-width: 300px; padding: 20px; background: #f8f9fa; border-radius: 10px; margin: 10px;">
                    <h4>2. Add Mask (Optional)</h4>
                    <p>Upload a mask to focus on specific areas</p>
                </div>
                <div style="max-width: 300px; padding: 20px; background: #f8f9fa; border-radius: 10px; margin: 10px;">
                    <h4>3. Generate</h4>
                    <p>Click generate and wait for your 3D model</p>
                </div>
            </div>
        </div>
        """)
    
    return demo

if __name__ == "__main__":
    # Create and launch the interface
    demo = create_interface()
    
    # Print available model paths for debugging
    print("Checking for model checkpoints...")
    if os.path.exists("checkpoints"):
        for root, dirs, files in os.walk("checkpoints"):
            print(f"Found in {root}: {files}")
    else:
        print("No checkpoints directory found")
    
    print("Available inference modules:", "✓" if INFERENCE_AVAILABLE else "✗")
    
    # Launch with proper configuration
    demo.launch(
        server_name="0.0.0.0",
        server_port=7860,
        share=False,
        show_error=True,
        debug=True,
        inbrowser=True
    )