install.sh

pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ PromptTrack (version test)

pip install --no-deps bytetracker



'''import gradio as gr
import numpy as np
import random

# import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024


# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    generator = torch.Generator().manual_seed(seed)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed


examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image Gradio Template")

        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )

            run_button = gr.Button("Run", scale=0, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=False,
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )

            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=0.0,  # Replace with defaults that work for your model
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=2,  # Replace with defaults that work for your model
                )

        gr.Examples(examples=examples, inputs=[prompt])
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

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


import gradio as gr
import shutil
import os
import subprocess
import sys
# Run the .bat file before launching the app
"""try:
    import PromptTrack
except ImportError:
    print("PromptTrack not found. Installing...")
    subprocess.run([sys.executable, "-m", "pip", "install", 
                    "--index-url", "https://test.pypi.org/simple/", 
                    "--extra-index-url", "https://pypi.org/simple/", 
                    "PromptTrack"], check=True)
    subprocess.run([sys.executable, "-m", "pip", "install", 
                    "--no-deps", "bytetracker"], check=True)
    import PromptTrack  # Retry import after installation


from PromptTrack import PromptTracker
tracker = PromptTracker()"""
def process_video(video_path, prompt):
    detection_threshold=0.3
    track_thresh=0.4
    match_thresh=1
    max_time_lost=float("inf")
    nbr_frames_fixing=800
    output_video = video_path.split('mp4')[0]+"_with_id.mp4"  # Placeholder for processed video
    output_file = video_path.split('mp4')[0]+"_mot_.json"    # Tracking result
    output_file_2 = video_path.split('mp4')[0]+"_object_detection.json"    # detection results
    video_file = video_path
    """tracker.detect_objects(video_file, prompt=prompt, nms_threshold=0.8, detection_threshold=detection_threshold, detector="OWL-VITV2")
    tracker.process_mot(video_file, fixed_parc=True, track_thresh=track_thresh, match_thresh=match_thresh, frame_rate=25, max_time_lost=max_time_lost, nbr_frames_fixing=nbr_frames_fixing)
    tracker.read_video_with_mot(video_file, fps=25)
    """
    
    output_video = "output.mp4"  # Placeholder for processed video
    output_file = "output.txt"    # Placeholder for generated file
    
    
    # Copy the input video to simulate processing
    shutil.copy(video_path, output_video)
    
    # Create an output text file with the prompt content
    with open(output_file, "w") as f:
        f.write(f"User Prompt: {prompt}\n")
    
    return output_video, output_file

# Define Gradio interface
iface = gr.Interface(
    fn=process_video,
    inputs=[gr.File(label="Upload Video"), gr.Textbox(placeholder="Enter your prompt")],
    outputs=[gr.Video(), gr.File(label="Generated File")],
    title="Video Processing App",
    description="Upload a video and enter a prompt. The app will return the processed video and a generated file."
)


# Launch the app
if __name__ == "__main__":
    iface.launch()