app.py

import gradio as gr
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")

def launch(input):
    messages = [
        {
        "role": "user",
        "content": 
            [
                {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
                },
                {
                    "type": "text", "text": "Describe this image."
                },
            ],
        }
    ]

    # Preparation for inference
    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")

    # Inference: Generation of the output
    generated_ids = model.generate(**inputs, max_new_tokens=128)
    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
    )
    return(output_text)

iface = gr.Interface(launch,
                     inputs=gr.Image(type='pil'),
                     outputs="text")

iface.launch()