app.py

import gradio as gr
from transformers import pipeline

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()