app.py

import os
import gradio as gr
import torch
import numpy as np
from transformers import pipeline
from PIL import Image


depth_estimator = pipeline(task="depth-estimation", model="Intel/dpt-hybrid-midas")


def launch(input_image):
    out = depth_estimator(input_image)

    # resize the prediction
    prediction = torch.nn.functional.interpolate(
        out["predicted_depth"].unsqueeze(1),
        size=input_image.size[::-1],
        mode="bicubic",
        align_corners=False,
    )

    # normalize the prediction
    output = prediction.squeeze().numpy()
    formatted = (output * 255 / np.max(output)).astype("uint8")
    depth = Image.fromarray(formatted)
    return depth


iface = gr.Interface(launch, 
                     inputs=gr.Image(type='pil'), 
                     outputs=gr.Image(type='pil'))


iface.launch(share=True)