app.py

import gradio as gr
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model versi open-source (Gratis selamanya)
model_id = "vikhyatk/moondream2"
revision = "2024-08-26"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, revision=revision)
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)

def predict(image, prompt):
    if image is None:
        return "No image uploaded"
    # Proses gambar ke model
    enc_image = model.encode_image(image)
    answer = model.answer_question(enc_image, prompt, tokenizer)
    return answer

# Interface Gradio sederhana buat bot PHP lo
interface = gr.Interface(
    fn=predict,
    inputs=[gr.Image(type="pil"), gr.Textbox(label="Prompt")],
    outputs=gr.Text(),
)

interface.launch()