app.py

import os
import streamlit as st
from openai import OpenAI
from PIL import Image
import io

# Set up the OpenAI client
client = OpenAI(
    base_url="https://api.studio.nebius.ai/v1/",
    api_key=os.environ.get("NEBIUS_API_KEY")
)

# Function to generate caption from image URL
def generate_caption(image_data):
    completion = client.chat.completions.create(
        model="Qwen/Qwen2-VL-72B-Instruct",
        messages=[
            {
                "role": "system",
                "content": """You are an image to prompt converter. Your work is to observe each and every detail of the image and craft a detailed prompt under 75 words in this format: [image content/subject, description of action, state, and mood], [art form, style], [artist/photographer reference if needed], [additional settings such as camera and lens settings, lighting, colors, effects, texture, background, rendering]."""
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": """Write a caption for this image"""
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": image_data
                        }
                    }
                ]
            }
        ],
        temperature=0
    )
    
    caption = completion.to_json().get("choices", [{}])[0].get("message", {}).get("content", "")
    return caption

# Streamlit UI
st.title("Image to Caption Generator")
st.write("Upload an image, and the app will generate a detailed caption for it.")

uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    # Display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)
    
    # Convert image to a base64 string
    buffered = io.BytesIO()
    image.save(buffered, format="PNG")
    img_base64 = buffered.getvalue().decode("utf-8")

    # Generate caption using the OpenAI API
    st.write("Generating caption...")
    caption = generate_caption(img_base64)

    # Display the generated caption
    if caption:
        st.subheader("Generated Caption:")
        st.write(caption)
    else:
        st.write("No caption could be generated.")