app.py

from qwenvl import QwenVLModel
import gradio as gr
from PIL import Image
import datetime
import os
import numpy as np

model = QwenVLModel()
DESCRIPTION = "[Qwen2-VL-7B Demo](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct)"

def array_to_image_path(image_array):
    # Convert numpy array to PIL Image
    img = Image.fromarray(np.uint8(image_array))
    
    # Generate a unique filename using timestamp
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    filename = f"image_{timestamp}.png"
    
    # Save the image
    img.save(filename)
    
    # Get the full path of the saved image
    full_path = os.path.abspath(filename)
    
    return full_path

css = """
  #output {
    height: 500px; 
    overflow: auto; 
    border: 1px solid #ccc; 
  }
"""

with gr.Blocks(css=css) as demo:
    gr.Markdown(DESCRIPTION)
    with gr.Tab(label="Qwen2-VL-7B Input"):
        with gr.Row():
            with gr.Column():
                input_img_arr = gr.Image(label="Input Picture")
                input_img = Image.fromarray(input_img_arr).convert("RGB")
                text_input = gr.Textbox(label="Question")
                submit_btn = gr.Button(value="Submit")
            with gr.Column():
                output_text = gr.Textbox(label="Output Text")

        submit_btn.click(model.oneImagecall, [input_img, text_input], [output_text])

demo.queue(api_open=False)
demo.launch(debug=True)