Spaces:
Running
Running
File size: 2,406 Bytes
d5a06f6 8ffbf51 6e2e0c5 8ffbf51 7c56b7b 8ffbf51 79ec99d 8ffbf51 a93e14b 788e1b9 a93e14b 8ffbf51 a93e14b 8ffbf51 7c56b7b 8ffbf51 6e2e0c5 8ffbf51 a93e14b 8ffbf51 6e2e0c5 8ffbf51 6e2e0c5 8ffbf51 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
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.")
|