app.py

import os
import json
import urllib.request
from PIL import Image
from gtts import gTTS
import cv2
import moviepy.editor as mp
import logging
from hercai import Hercai
import uuid
import time
import gradio as gr
from typing import Tuple, List

# Enhanced logging configuration
log_dir = os.getenv('LOG_DIRECTORY', './')
LOGGER_FILE_PATH = os.path.join(str(log_dir), 'utils.log')

logging.basicConfig(
    filename=LOGGER_FILE_PATH,
    filemode='a',
    format='[%(asctime)s] [%(levelname)s] [%(filename)s] [%(lineno)s:%(funcName)s()] %(message)s',
    datefmt='%Y-%b-%d %H:%M:%S',
    level=logging.INFO,
    handlers=[
        logging.FileHandler(LOGGER_FILE_PATH),
        logging.StreamHandler()
    ]
)
LOGGER = logging.getLogger(__name__)

class Text2Video:
    def __init__(self) -> None:
        """Initialize the Text2Video class."""
        self.herc = Hercai()
        LOGGER.info("Initialized Text2Video with Hercai API")

    def get_image(self, img_prompt: str) -> str:
        """Generate an image based on the provided text prompt."""
        try:
            # Enhanced prompt engineering similar to DALL-E 3
            enhanced_prompt = (
                f"Create a high-quality comic panel: {img_prompt}. "
                "Style: Professional comic book illustration, "
                "vivid colors, clear composition, dramatic lighting. "
                "Include text as comic-style captions. "
                "Resolution: High detail, 1792x1024 aspect ratio. "
                "Quality: Professional grade comic art."
            )

            result = self.herc.draw_image(
                model="simurg",  # Using Hercai's best model
                prompt=enhanced_prompt,
                negative_prompt="blurry, low quality, poorly drawn, distorted"
            )

            LOGGER.info(f"Successfully generated image for prompt: {img_prompt[:50]}...")
            return result["url"]

        except Exception as e:
            LOGGER.error(f"Error generating image: {e}")
            raise

    def download_img_from_url(self, image_url: str, image_path: str) -> str:
        """Download and process image from URL."""
        try:
            urllib.request.urlretrieve(image_url, image_path)
            
            # Image processing for consistent quality
            img = Image.open(image_path)
            target_size = (1792, 1024)  # Matching DALL-E 3 size
            img = img.resize(target_size, Image.Resampling.LANCZOS)
            img.save(image_path, quality=95)
            
            LOGGER.info(f"Successfully downloaded and processed image: {image_path}")
            return image_path

        except Exception as e:
            LOGGER.error(f"Error downloading image: {e}")
            raise

    def create_video_from_images_and_audio(self, image_files: list, audio_files: list, output_path: str) -> None:
        """Create video with enhanced quality settings."""
        try:
            if len(image_files) != len(audio_files):
                raise ValueError("Number of images doesn't match number of audio files")

            video_clips = []
            for image_file, audio_file in zip(image_files, audio_files):
                audio_clip = mp.AudioFileClip(audio_file)
                video_clip = mp.ImageClip(image_file).set_duration(audio_clip.duration)
                video_clip = video_clip.set_audio(audio_clip)
                video_clips.append(video_clip)

            final_clip = mp.concatenate_videoclips(video_clips)
            
            # Enhanced video quality settings
            final_clip.write_videofile(
                output_path,
                codec='libx264',
                fps=24,
                audio_codec='aac',
                audio_bitrate='192k',
                preset='medium',
                threads=4
            )
            
            LOGGER.info("Video created successfully")

        except Exception as e:
            LOGGER.error(f"Error creating video: {e}")
            raise

    # [Previous methods remain the same]

    def gradio_interface(self):
        """Create enhanced Gradio interface."""
        with gr.Blocks(theme='abidlabs/dracula_revamped') as demo:
            gr.HTML("""
                <center>
                    <h1 style="color:#fff">AI Comic Video Generator</h1>
                    <p style="color:#ddd">Create engaging comic-style videos from your stories</p>
                </center>
            """)

            with gr.Row():
                input_text = gr.Textbox(
                    label="Story Script",
                    placeholder="Enter your story (separate scenes with ,,)",
                    lines=5
                )

            with gr.Row():
                generate_btn = gr.Button("🎬 Generate Comic Video", variant="primary")

            with gr.Row():
                output = gr.Video(label="Generated Comic Video")

            example_txt = """Once upon a time in a magical forest,, 
            A brave knight discovered a mysterious crystal,, 
            The crystal began to glow with incredible power"""
            
            gr.Examples([[example_txt]], [input_text])

            generate_btn.click(
                self.generate_video,
                inputs=[input_text],
                outputs=[output]
            )

        demo.launch(debug=True)