import spaces
import os
import time
import torch
import gradio as gr
from threading import Thread
from PIL import Image
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Model and processor initialization
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/QVQ-72B-Preview", 
    torch_dtype="auto", 
    device_map="auto"
)
processor = AutoProcessor.from_pretrained("Qwen/QVQ-72B-Preview")

# Footer
footer = """
<div style="text-align: center; margin-top: 20px;">
    <p>Powered by QVQ-72B Model</p>
</div>
"""

# Vision model function
@spaces.GPU()
def process_image(image, text_input=None):
    try:
        # Convert image to PIL format if needed
        if not isinstance(image, Image.Image):
            image = Image.fromarray(image).convert("RGB")
        
        # Prepare messages
        if not text_input:
            text_input = "Please describe this image in detail."
            
        messages = [
            {
                "role": "system",
                "content": [
                    {"type": "text", "text": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."}
                ],
            },
            {
                "role": "user",
                "content": [
                    {"type": "image", "image": image},
                    {"type": "text", "text": text_input}
                ],
            }
        ]

        # Process inputs
        text = processor.apply_chat_template(
            messages, 
            tokenize=False, 
            add_generation_prompt=True
        )
        image_inputs, video_inputs = process_vision_info(messages)
        inputs = processor(
            text=[text],
            images=image_inputs,
            videos=video_inputs,
            padding=True,
            return_tensors="pt",
        )
        inputs = inputs.to("cuda")

        # Generate response
        generated_ids = model.generate(**inputs, max_new_tokens=8192)
        generated_ids_trimmed = [
            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
        ]
        output_text = processor.batch_decode(
            generated_ids_trimmed, 
            skip_special_tokens=True, 
            clean_up_tokenization_spaces=False
        )[0]
        
        return output_text
    except Exception as e:
        return f"Error processing image: {str(e)}"

# CSS styling
css = """
footer {
    visibility: hidden;
}
"""

# Gradio interface
with gr.Blocks(theme="Yntec/HaleyCH_Theme_Orange", css=css) as demo:
    with gr.Row():
        input_img = gr.Image(label="Input Image")
    with gr.Row():
        text_input = gr.Textbox(label="Question (Optional)")
    with gr.Row():
        submit_btn = gr.Button(value="Submit")
    with gr.Row():
        output_text = gr.Textbox(label="Response")

    submit_btn.click(process_image, [input_img, text_input], [output_text])
    
    gr.HTML(footer)

# Launch the app
demo.launch(debug=True)