app.py

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

model_id = "vikhyatk/moondream2"
revision = "2024-03-06"
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, revision=revision
)
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)

def describe_image(image):
    image = Image.fromarray(image)
    enc_image = model.encode_image(image)
    description = model.answer_question(enc_image, "Describe this image.", tokenizer)
    return description

input_image = gr.inputs.Image()
output_text = gr.outputs.Textbox()

gr.Interface(
    fn=describe_image,
    inputs=input_image,
    outputs=output_text,
    title="Image Description",
    description="Enter an image and get its description.",
).launch()