app.py

import gradio as gr
import torch
import cv2
import numpy as np
from torchvision import transforms
from PIL import Image
from transformers import DPTForDepthEstimation, DPTFeatureExtractor

# Load depth estimation model
model_name = "Intel/dpt-large"
feature_extractor = DPTFeatureExtractor.from_pretrained(model_name)
depth_model = DPTForDepthEstimation.from_pretrained(model_name)
depth_model.eval()

def estimate_depth(image):
    """Estimate depth map from image."""
    image = image.convert("RGB")
    image = image.resize((384, 384))  # Resize for model input
    inputs = feature_extractor(images=image, return_tensors="pt")
    with torch.no_grad():
        outputs = depth_model(**inputs)
        depth = outputs.predicted_depth.squeeze().cpu().numpy()
    depth = cv2.resize(depth, (image.width, image.height))  # Resize back to original
    depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255
    return depth.astype(np.uint8)

def blend_design(cloth_img, design_img):
    """Blend design onto clothing naturally with fold adaptation."""
    cloth_img = cloth_img.convert("RGB")
    design_img = design_img.convert("RGBA")
    cloth_np = np.array(cloth_img)
    design_np = np.array(design_img)
    
    # Resize design to fit within clothing
    h, w, _ = cloth_np.shape
    dh, dw, _ = design_np.shape
    scale_factor = min(w / dw, h / dh) * 0.4  # Scale to 40% of clothing area
    new_w, new_h = int(dw * scale_factor), int(dh * scale_factor)
    design_np = cv2.resize(design_np, (new_w, new_h), interpolation=cv2.INTER_AREA)
    
    # Extract alpha channel for transparency
    alpha_channel = design_np[:, :, 3] / 255.0
    design_np = design_np[:, :, :3]
    
    # Create a blank canvas and paste the resized design at the center
    x_offset = (w - new_w) // 2
    y_offset = int(h * 0.35)  # Move slightly upward for a natural position
    
    for c in range(3):
        cloth_np[y_offset:y_offset+new_h, x_offset:x_offset+new_w, c] = (
            cloth_np[y_offset:y_offset+new_h, x_offset:x_offset+new_w, c] * (1 - alpha_channel) + 
            design_np[:, :, c] * alpha_channel
        )
    
    # Estimate depth for fold detection
    depth_map = estimate_depth(cloth_img)
    depth_map = cv2.resize(depth_map, (w, h))
    
    # Generate displacement map based on depth
    displacement_x = cv2.Sobel(depth_map, cv2.CV_32F, 1, 0, ksize=5)
    displacement_y = cv2.Sobel(depth_map, cv2.CV_32F, 0, 1, ksize=5)
    displacement_x = cv2.normalize(displacement_x, None, -5, 5, cv2.NORM_MINMAX)
    displacement_y = cv2.normalize(displacement_y, None, -5, 5, cv2.NORM_MINMAX)
    
    # Warp design using displacement map
    map_x, map_y = np.meshgrid(np.arange(w), np.arange(h))
    map_x = np.clip(np.float32(map_x + displacement_x), 0, w - 1)
    map_y = np.clip(np.float32(map_y + displacement_y), 0, h - 1)
    warped_cloth = cv2.remap(cloth_np, map_x, map_y, interpolation=cv2.INTER_LINEAR, borderMode=cv2.BORDER_REFLECT)
    
    return Image.fromarray(warped_cloth)

def main(cloth, design):
    return blend_design(cloth, design)

iface = gr.Interface(
    fn=main,
    inputs=[gr.Image(type="pil"), gr.Image(type="pil")],
    outputs=gr.Image(type="pil"),
    title="AI Cloth Design Warping",
    description="Upload a clothing image and a design to blend it naturally, ensuring it stays centered and follows fabric folds."
)

if __name__ == "__main__":
    iface.launch(share=True)