Spaces:
Running
Running
File size: 1,349 Bytes
205e6c3 f399174 205e6c3 |
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 |
import openai
import base64
def describe_image_with_gpt4o(image_path, api_key):
"""
Given an image file, sends it to GPT-4o Vision API and gets a detailed description.
Returns the description as a string.
"""
openai.api_key = api_key
# Read and encode image
with open(image_path, "rb") as img_file:
img_base64 = base64.b64encode(img_file.read()).decode("utf-8")
img_data_url = f"data:image/png;base64,{img_base64}"
# Compose the prompt
prompt = (
"Describe this face with as much detail as possible, "
"focusing on facial features, hairstyle, expression, accessories, and notable traits. "
"Be specific, provide detail on Clothing, style and background"
"Be specific, as if explaining to an artist who will draw a sticker of this person."
)
# Call GPT-4o Vision API
response = openai.chat.completions.create(
model="gpt-4o",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": prompt},
{"type": "image_url","image_url": {"url": img_data_url}},
],
}
],
max_tokens=256,
)
# Extract the description
description = response.choices[0].message.content.strip()
return description
|