vision model

vision/Text_to_image/main.py

@@ -0,0 +1,20 @@
+# main.py
+from textToPdf import create_pdf
+from pdfToImage import pdf_to_image
+
+def main():
+    # Sample input text
+    input_text = "This is a sample text that will be used to generate the PDF. " * 500  # Example long text
+    
+    # Call the create_pdf function and get the path of the generated PDF
+    pdf_path = create_pdf(input_text)
+    image_path = pdf_to_image(pdf_path)
+
+    # Print the output path of the generated PDF
+    print(f"PDF generated successfully: {pdf_path}")
+
+    for i in image_path:
+        print(i)
+
+if __name__ == "__main__":
+    main()

vision/Text_to_image/pdfToImage.py

@@ -0,0 +1,30 @@
+import fitz  # PyMuPDF
+import os
+
+def pdf_to_image(pdf_path, zoom=2.0):
+    # Open the PDF file
+    pdf_document = fitz.open(pdf_path)
+    
+    # Create a list to store image paths
+    image_paths = []
+    
+    # Create an 'Images' directory if it doesn't exist
+    os.makedirs("Images", exist_ok=True)
+    
+    # Iterate over PDF pages and convert each to an image
+    for page_num in range(len(pdf_document)):
+        page = pdf_document.load_page(page_num)  # Load the page
+        
+        # Set zoom level to improve quality
+        mat = fitz.Matrix(zoom, zoom)  # Create a transformation matrix with the zoom level
+        pix = page.get_pixmap(matrix=mat)  # Render the page to an image with the specified zoom
+        
+        image_file = f'Images/{os.path.basename(pdf_path)}_page_{page_num}.png'
+        pix.save(image_file)  # Save the image as PNG
+        image_paths.append(image_file)
+    
+    # Return the list containing paths of all images
+    return image_paths
+
+# Example usage
+# pdf_to_image('your_pdf_file.pdf', zoom=2.0)  # Increase zoom for higher quality

vision/Text_to_image/textToPdf.py

@@ -0,0 +1,30 @@
+from fpdf import FPDF
+from datetime import datetime
+import os
+
+def create_pdf(input_text):
+    # Create instance of FPDF class
+    pdf = FPDF()
+    
+    # Add a page
+    pdf.add_page()
+    
+    # Set font
+    pdf.set_font("Arial", size=10)
+    
+    # Split the input text into multiple lines if necessary
+    # This ensures that the text fits the page and multiple pages are handled
+    pdf.multi_cell(0, 5, txt=input_text)
+    
+    # Create a unique file name with the current time
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    file_name = f"PDFs/Aditya_{timestamp}.pdf"
+    
+    # Create output directory if it doesn't exist
+    os.makedirs(os.path.dirname(file_name), exist_ok=True)
+    
+    # Save the PDF
+    pdf.output(file_name)
+    
+    # Return the file path
+    return file_name