app.py

import numpy as np
import torch
import torch.nn.functional as F
import functools
from torchvision.transforms.functional import normalize
import gradio as gr
from gradio_imageslider import ImageSlider
from briarmbg import BriaRMBG
import PIL
from PIL import Image
from typing import Tuple
import requests
from io import BytesIO

net = BriaRMBG.from_pretrained("briaai/RMBG-1.4")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net.to(device)

@functools.lru_cache()
def get_url_im(url):
    user_agent = {'User-agent': 'gradio-app'}
    response = requests.get(url, headers=user_agent)
    return BytesIO(response.content)

def resize_image(image_url):
    image_data = get_url_im(image_url)
    image = Image.open(image_data)
    image = image.convert('RGB')
    model_input_size = (1024, 1024)
    image = image.resize(model_input_size, Image.BILINEAR)
    return image

def process(image_url):
    # prepare input
    orig_image = resize_image(image_url)
    w, h = orig_im_size = orig_image.size
    im_np = np.array(orig_image)
    im_tensor = torch.tensor(im_np, dtype=torch.float32).permute(2, 0, 1)
    im_tensor = torch.unsqueeze(im_tensor, 0)
    im_tensor = torch.divide(im_tensor, 255.0)
    im_tensor = normalize(im_tensor, [0.5, 0.5, 0.5], [1.0, 1.0, 1.0])
    if torch.cuda.is_available():
        im_tensor = im_tensor.cuda()

    # inference
    result = net(im_tensor)
    # post process
    result = torch.squeeze(F.interpolate(result[0][0], size=(h, w), mode='bilinear'), 0)
    ma = torch.max(result)
    mi = torch.min(result)
    result = (result - mi) / (ma - mi)
    # image to pil
    im_array = (result * 255).cpu().data.numpy().astype(np.uint8)
    pil_im = Image.fromarray(np.squeeze(im_array))
    # paste the mask on the original image
    new_im = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
    new_im.paste(orig_image, mask=pil_im)
    
    return new_im

iface = gr.Interface(
    fn=process,
    inputs=gr.Textbox(label="Text or Image URL"),
    outputs=gr.Image(type="pil", label="Output Image"),
)

iface.launch()