app.py

def generate_caption(image):
    if not isinstance(image, Image.Image):
        image = Image.fromarray(image)
    
    task = "<CAPTION>"  # เปลี่ยน task เป็น caption ธรรมดา
    
    inputs = florence_processor(text=task, images=image, return_tensors="pt").to(device)
    generated_ids = florence_model.generate(
        input_ids=inputs["input_ids"],
        pixel_values=inputs["pixel_values"],
        max_new_tokens=1024,
        early_stopping=False,
        do_sample=False,
        num_beams=3,
    )
    generated_text = florence_processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
    parsed_answer = florence_processor.post_process_generation(
        generated_text,
        task=task,
        image_size=(image.width, image.height)
    )
    prompt = parsed_answer[task]
    print("\n\nGeneration completed!:" + prompt)
    return prompt