app.py

import numpy as np
import torch
import torch.nn.functional as F
from torchvision.transforms.functional import normalize
from huggingface_hub import hf_hub_download
import gradio as gr
from gradio_imageslider import ImageSlider
from briarmbg import BriaRMBG
import PIL
from PIL import Image
from typing import Tuple

net=BriaRMBG()
# model_path = "./model1.pth"
model_path = hf_hub_download("briaai/RMBG-1.4", 'model.pth')
if torch.cuda.is_available():
    net.load_state_dict(torch.load(model_path))
    net=net.cuda()
else:
    net.load_state_dict(torch.load(model_path,map_location="cpu"))
net.eval() 

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


def process(image):
    # 이미지가 numpy 배열인 경우에만 PIL.Image 객체로 변환
    if isinstance(image, np.ndarray):
        orig_image = Image.fromarray(image)
    else:
        # 이미 PIL.Image.Image 객체인 경우, 변환 없이 사용
        orig_image = image

    w, h = orig_im_size = orig_image.size
    image = resize_image(orig_image)
    im_np = np.array(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

def calculate_position(org_size, add_size, position):
    if position == "상단 좌측":
        return (0, 0)
    elif position == "상단 가운데":
        return ((org_size[0] - add_size[0]) // 2, 0)
    elif position == "상단 우측":
        return (org_size[0] - add_size[0], 0)
    elif position == "중앙 좌측":
        return (0, (org_size[1] - add_size[1]) // 2)
    elif position == "중앙 가운데":
        return ((org_size[0] - add_size[0]) // 2, (org_size[1] - add_size[1]) // 2)
    elif position == "중앙 우측":
        return (org_size[0] - add_size[0], (org_size[1] - add_size[1]) // 2)
    elif position == "하단 좌측":
        return (0, org_size[1] - add_size[1])
    elif position == "하단 가운데":
        return ((org_size[0] - add_size[0]) // 2, org_size[1] - add_size[1])
    elif position == "하단 우측":
        return (org_size[0] - add_size[0], org_size[1] - add_size[1])


def merge(org_image, add_image, scale, position, display_size):
    # 사용자가 선택한 디스플레이 크기에 따라 결과 이미지 크기 조절
    display_width, display_height = map(int, display_size.split('x'))
    
    # 이미지 병합 로직
    scale_percentage = scale / 100.0
    new_size = (int(add_image.width * scale_percentage), int(add_image.height * scale_percentage))
    add_image = add_image.resize(new_size, Image.Resampling.LANCZOS)
    
    position = calculate_position(org_image.size, add_image.size, position)
    merged_image = Image.new("RGBA", org_image.size)
    merged_image.paste(org_image, (0, 0))
    merged_image.paste(add_image, position, add_image)
    
    # 결과 이미지 디스플레이 크기 조절
    final_image = merged_image.resize((display_width, display_height), Image.Resampling.LANCZOS)
    
    return final_image


with gr.Blocks() as demo:
    with gr.Tab("Background Removal"):
        with gr.Column():
            gr.Markdown("## BRIA RMBG 1.4")
            gr.HTML('''
                <p style="margin-bottom: 10px; font-size: 94%">
                This is a demo for BRIA RMBG 1.4 that using
                <a href="https://huggingface.co/briaai/RMBG-1.4" target="_blank">BRIA RMBG-1.4 image matting model</a> as backbone. 
                </p>
            ''')
            input_image = gr.Image(type="pil")
            output_image = gr.Image()
            process_button = gr.Button("Remove Background")
            process_button.click(fn=process, inputs=input_image, outputs=output_image)

    with gr.Tab("Merge"):
        with gr.Column():
            org_image = gr.Image(label="Background", type='pil', image_mode='RGBA', height=400)  # 예시로 높이 조절
            add_image = gr.Image(label="Foreground", type='pil', image_mode='RGBA', height=400)  # 예시로 높이 조절
            scale = gr.Slider(minimum=10, maximum=200, step=1, value=100, label="Scale of Foreground Image (%)")
            position = gr.Radio(choices=["중앙 가운데", "상단 좌측", "상단 가운데", "상단 우측", "중앙 좌측", "중앙 우측", "하단 좌측", "하단 가운데", "하단 우측"], value="중앙 가운데", label="Position of Foreground Image")
            display_size = gr.Textbox(value="1024x768", label="Display Size (Width x Height)")
            btn_merge = gr.Button("Merge Images")
            result_merge = gr.Image()
            
            btn_merge.click(
                fn=merge,
                inputs=[org_image, add_image, scale, position, display_size],
                outputs=result_merge,
            )

demo.launch()