app.py

import gradio as gr
import torch
import os
import tempfile
import shutil
import time
import ffmpeg
import numpy as np
from PIL import Image, ImageOps
import moviepy.editor as mp
from infer import lotus, load_models
import logging

# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Set device to use the L40s GPU explicitly
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Load models once
task_name = 'depth'
pipe_g, pipe_d = load_models(task_name, device)

# Preprocess the video to adjust resolution and frame rate
def preprocess_video(video_path, target_fps=24, max_resolution=None):
    """Preprocess the video to adjust its frame rate."""
    video = mp.VideoFileClip(video_path)

    # Adjust FPS if target_fps is specified
    if target_fps > 0:
        video = video.set_fps(target_fps)

    return video

# Resize image while preserving aspect ratio and adding padding
def resize_and_pad(image, target_size):
    """Resize and pad an image to the target size while preserving aspect ratio."""
    # Calculate the new size preserving aspect ratio
    image.thumbnail(target_size, Image.ANTIALIAS)

    # Create a new image with the target size and black background
    new_image = Image.new("RGB", target_size)
    new_image.paste(
        image, ((target_size[0] - image.width) // 2, (target_size[1] - image.height) // 2)
    )
    return new_image

# Process a single frame through the depth model
def process_frame(frame, seed=0, target_size=(512, 512)):
    """Process a single frame and return depth map."""
    try:
        torch.cuda.empty_cache()  # Clear GPU cache

        # Convert frame to PIL Image
        image = Image.fromarray(frame).convert('RGB')

        # Resize and pad image
        input_image = resize_and_pad(image, target_size)

        # Run inference
        depth_map = lotus(input_image, 'depth', seed, device, pipe_g, pipe_d)

        # Crop the output depth map back to original image size
        width, height = image.size
        left = (target_size[0] - width) // 2
        top = (target_size[1] - height) // 2
        right = left + width
        bottom = top + height
        depth_map_cropped = depth_map.crop((left, top, right, bottom))

        return depth_map_cropped

    except Exception as e:
        logger.error(f"Error processing frame: {e}")
        return None

# Process video frames and generate depth maps
def process_video(video_path, fps=0, seed=0):
    """Process video frames individually and generate depth maps."""
    # Create a persistent temporary directory
    temp_dir = tempfile.mkdtemp()
    try:
        start_time = time.time()

        # Preprocess the video
        video = preprocess_video(video_path, target_fps=fps)

        # Use original video FPS if not specified
        if fps == 0:
            fps = video.fps

        frames = list(video.iter_frames())
        total_frames = len(frames)

        logger.info(f"Processing {total_frames} frames at {fps} FPS...")

        # Create directory for frame sequence and outputs
        frames_dir = os.path.join(temp_dir, "frames")
        os.makedirs(frames_dir, exist_ok=True)

        # Process frames individually
        for i, frame in enumerate(frames):
            depth_map = process_frame(frame, seed)

            if depth_map is not None:
                # Save frame
                frame_path = os.path.join(frames_dir, f"frame_{i:06d}.png")
                depth_map.save(frame_path, format='PNG', compress_level=0)

                # Update live preview every 10% progress
                if i % max(1, total_frames // 10) == 0:
                    elapsed_time = time.time() - start_time
                    progress = (i / total_frames) * 100
                    yield depth_map, None, None, f"Processed {i}/{total_frames} frames... ({progress:.2f}%) Elapsed: {elapsed_time:.2f}s"
            else:
                logger.error(f"Error processing frame {i}")

        logger.info("Creating output files...")

        # Create ZIP of frame sequence
        zip_filename = f"depth_frames_{int(time.time())}.zip"
        zip_path = os.path.join(temp_dir, zip_filename)
        shutil.make_archive(zip_path[:-4], 'zip', frames_dir)

        # Create MP4 video
        video_filename = f"depth_video_{int(time.time())}.mp4"
        output_video_path = os.path.join(temp_dir, video_filename)

        try:
            # FFmpeg settings for high-quality MP4
            input_pattern = os.path.join(frames_dir, 'frame_%06d.png')
            (
                ffmpeg
                .input(input_pattern, pattern_type='sequence', framerate=fps)
                .output(output_video_path, vcodec='libx264', pix_fmt='yuv420p', crf=17, preset='slow')
                .run(overwrite_output=True, quiet=True)
            )
            logger.info("MP4 video created successfully!")

        except ffmpeg.Error as e:
            logger.error(f"Error creating video: {e.stderr.decode() if e.stderr else str(e)}")
            output_video_path = None

        total_time = time.time() - start_time
        logger.info("Processing complete!")

        # Yield the file paths
        yield None, zip_path, output_video_path, f"Processing complete! Total time: {total_time:.2f} seconds"

    except Exception as e:
        logger.error(f"Error: {e}")
        yield None, None, None, f"Error processing video: {e}"

    finally:
        # Clean up temporary directory if necessary
        pass

# Wrapper function with error handling
def process_wrapper(video, fps=0, seed=0):
    if video is None:
        raise gr.Error("Please upload a video.")
    try:
        outputs = []
        # Use video directly, since it's the file path
        for output in process_video(video, fps, seed):
            outputs.append(output)
            yield output
        return outputs[-1]
    except Exception as e:
        raise gr.Error(f"Error processing video: {str(e)}")

# Custom CSS for styling (unchanged)
custom_css = """
    .title-container {
        text-align: center;
        padding: 10px 0;
    }

    #title {
        font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
        font-size: 36px;
        font-weight: bold;
        color: #000000;
        padding: 10px;
        border-radius: 10px;
        display: inline-block;
        background: linear-gradient(
            135deg,
            #e0f7fa, #e8f5e9, #fff9c4, #ffebee,
            #f3e5f5, #e1f5fe, #fff3e0, #e8eaf6
        );
        background-size: 400% 400%;
        animation: gradient-animation 15s ease infinite;
    }

    @keyframes gradient-animation {
        0% { background-position: 0% 50%; }
        50% { background-position: 100% 50%; }
        100% { background-position: 0% 50%; }
    }
"""

# Gradio Interface
with gr.Blocks(css=custom_css) as demo:
    gr.HTML('''
        <div class="title-container">
            <div id="title">Video Depth Estimation</div>
        </div>
    ''')

    with gr.Row():
        with gr.Column():
            video_input = gr.Video(label="Upload Video", interactive=True)
            fps_slider = gr.Slider(minimum=0, maximum=60, step=1, value=0, label="Output FPS (0 for original)")
            seed_slider = gr.Number(value=0, label="Seed")
            btn = gr.Button("Process Video")

        with gr.Column():
            preview_image = gr.Image(label="Live Preview")
            output_frames_zip = gr.File(label="Download Frame Sequence (ZIP)")
            output_video = gr.File(label="Download Video (MP4)")
            time_textbox = gr.Textbox(label="Status", interactive=False)

    btn.click(
        fn=process_wrapper,
        inputs=[video_input, fps_slider, seed_slider],
        outputs=[preview_image, output_frames_zip, output_video, time_textbox]
    )

    demo.queue()

if __name__ == "__main__":
    demo.launch(debug=True)