app.py

import base64
import os
from io import BytesIO

import gradio as gr
from huggingface_hub import InferenceClient

PROMPT = os.environ.get("PROMPT", "Describe this image.")

client = InferenceClient(model="https://text.pollinations.ai/openai")

def image_to_base64(image):
    buf = BytesIO()
    image.save(buf, "JPEG")
    buf.seek(0)
    return base64.b64encode(buf.getvalue()).decode("utf-8")

def caption(image, prompt):
    image = image_to_base64(image)
    return client.chat.completions.create(
        model="openai-large",
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {"url": f"data:image/jpeg;base64,{image}"}
                    },
                    {"type": "text", "text": prompt}
               ]
            }
        ],
        max_tokens=1024
    ).choices[0].message.content

gr.Interface(
    caption,
    inputs=[
        gr.Image(type="pil", label="Image"), 
        gr.Textbox(label="Prompt", value=PROMPT)
    ],
    outputs=gr.Textbox(label="Caption"),
    title="Image Captioning"
).launch(debug=True)