app.py

import gradio as gr
from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from PIL import Image
import torch
from qwen_vl_utils import process_vision_info

# Load model and processor
model_id = "DiagramAgent/Diagram_to_Code_Agent"
model = Qwen2VLForConditionalGeneration.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(model_id)

def generate_code(image):
    messages = [{"role": "user", "content": [{"type": "image", "image": image}, {"type": "text", "text": "diagram"}]}]
    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").to(model.device)
    generated_ids = model.generate(**inputs, max_new_tokens=8192)
    output_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
    return output_text[0]

gr.Interface(fn=generate_code, inputs=gr.Image(type="pil"), outputs="text", title="Diagram to Code Agent").launch()