Create app.py

app.py

@@ -0,0 +1,160 @@
+import gradio as gr
+import logging
+from roboflow import Roboflow
+from PIL import Image, ImageDraw, ImageFont, ImageFilter
+import cv2
+import numpy as np
+import os
+from math import atan2, degrees
+from diffusers import AutoPipelineForText2Image
+import torch
+
+# Configure logging
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler("debug.log"),
+        logging.StreamHandler()
+    ]
+)
+
+# Roboflow and model configuration
+ROBOFLOW_API_KEY = "KUP9w62eUcD5PrrRMJsV"  # Replace with your API key
+PROJECT_NAME = "model_verification_project"
+VERSION_NUMBER = 2
+
+# Initialize the FLUX handwriting model
+device = "cuda" if torch.cuda.is_available() else "cpu"
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    'black-forest-labs/FLUX.1-dev',
+    torch_dtype=torch.float16
+).to(device)
+pipeline.load_lora_weights('fofr/flux-handwriting', weight_name='lora.safetensors')
+
+# Function to detect paper angle within bounding box
+def detect_paper_angle(image, bounding_box):
+    x1, y1, x2, y2 = bounding_box
+    roi = np.array(image)[y1:y2, x1:x2]
+    gray = cv2.cvtColor(roi, cv2.COLOR_RGBA2GRAY)
+    edges = cv2.Canny(gray, 50, 150)
+    lines = cv2.HoughLinesP(edges, 1, np.pi / 180, threshold=100, minLineLength=50, maxLineGap=10)
+    if lines is not None:
+        longest_line = max(lines, key=lambda line: np.linalg.norm((line[0][2] - line[0][0], line[0][3] - line[0][1])))
+        x1, y1, x2, y2 = longest_line[0]
+        dx = x2 - x1
+        dy = y2 - y1
+        angle = degrees(atan2(dy, dx))
+        return angle
+    else:
+        return 0
+
+# Function to process image and overlay text
+def process_image(image, text):
+    try:
+        # Initialize Roboflow
+        rf = Roboflow(api_key=ROBOFLOW_API_KEY)
+        logging.debug("Initialized Roboflow API.")
+        project = rf.workspace().project(PROJECT_NAME)
+        logging.debug("Accessed project in Roboflow.")
+        model = project.version(VERSION_NUMBER).model
+        logging.debug("Loaded model from Roboflow.")
+
+        # Save input image temporarily
+        input_image_path = "/tmp/input_image.jpg"
+        image.save(input_image_path)
+        logging.debug(f"Input image saved to {input_image_path}.")
+
+        # Perform inference
+        logging.debug("Performing inference on the image...")
+        prediction = model.predict(input_image_path, confidence=70, overlap=50).json()
+        logging.debug(f"Inference result: {prediction}")
+
+        # Open the image for processing
+        pil_image = image.convert("RGBA")
+        logging.debug("Converted image to RGBA mode.")
+
+        # Iterate over detected objects
+        for obj in prediction['predictions']:
+            white_paper_width = obj['width']
+            white_paper_height = obj['height']
+            padding_x = int(white_paper_width * 0.1)
+            padding_y = int(white_paper_height * 0.1)
+            box_width = white_paper_width - 2 * padding_x
+            box_height = white_paper_height - 2 * padding_y
+            logging.debug(f"Padded white paper dimensions: width={box_width}, height={box_height}.")
+
+            x1_padded = int(obj['x'] - white_paper_width / 2 + padding_x)
+            y1_padded = int(obj['y'] - white_paper_height / 2 + padding_y)
+            x2_padded = int(obj['x'] + white_paper_width / 2 - padding_x)
+            y2_padded = int(obj['y'] + white_paper_height / 2 - padding_y)
+
+            # Detect paper angle
+            angle = detect_paper_angle(np.array(image), (x1_padded, y1_padded, x2_padded, y2_padded))
+            logging.debug(f"Detected paper angle: {angle} degrees.")
+
+            # Generate handwriting image with transparent background
+            prompt = f'HWRIT handwriting saying "{text}", neat style, black ink on transparent background'
+            generated_image = pipeline(prompt).images[0].convert("RGBA")
+            logging.debug("Generated handwriting image.")
+
+            # Resize generated handwriting to fit the detected area
+            generated_image = generated_image.resize((box_width, box_height), Image.ANTIALIAS)
+
+            # Create a mask for the generated handwriting
+            mask = generated_image.split()[3]
+
+            # Rotate the generated handwriting to match the detected paper angle
+            rotated_handwriting = generated_image.rotate(-angle, resample=Image.BICUBIC, center=(box_width // 2, box_height // 2))
+            mask = mask.rotate(-angle, resample=Image.BICUBIC, center=(box_width // 2, box_height // 2))
+
+            # Paste the rotated handwriting onto the original image
+            pil_image.paste(rotated_handwriting, (x1_padded, y1_padded), mask)
+            logging.debug("Pasted generated handwriting onto the original image.")
+
+        # Save and return output image path
+        output_image_path = "/tmp/output_image.png"
+        pil_image.convert("RGB").save(output_image_path)
+        logging.debug(f"Output image saved to {output_image_path}.")
+        return output_image_path
+
+    except Exception as e:
+        logging.error(f"Error during image processing: {e}")
+        return None
+
+# Gradio interface function
+def gradio_inference(image, text):
+    logging.debug("Starting Gradio inference.")
+    result_path = process_image(image, text)
+    if result_path:
+        logging.debug("Gradio inference successful.")
+        return result_path, result_path, "Processing complete! Download the image below."
+    logging.error("Gradio inference failed.")
+    return None, None, "An error occurred while processing the image. Please check the logs."
+
+# Gradio interface
+# Gradio interface
+interface = gr.Interface(
+    fn=gradio_inference,
+    inputs=[
+        gr.Image(type="pil", label="Upload an Image"),  # Upload an image
+        gr.Textbox(label="Enter Text to Overlay"),  # Enter text to overlay
+    ],
+    outputs=[
+        gr.Image(label="Processed Image Preview"),  # Preview the processed image
+        gr.File(label="Download Processed Image"),  # Download the image
+        gr.Textbox(label="Status"),  # Status message
+    ],
+    title="Handwriting Overlay on White Paper",
+    description=(
+        "Upload an image with white paper detected, and enter the text to overlay. "
+        "This app will generate handwriting using the FLUX handwriting model and overlay it on the detected white paper. "
+        "Preview or download the output image below."
+    ),
+    allow_flagging="never",  # Disables flagging
+)
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    logging.debug("Launching Gradio interface.")
+    interface.launch(share=True)