app.py

import gradio as gr
import PIL
from PIL import Image
import numpy as np
import os
import uuid
import torch
from torch import autocast
import cv2
from io import BytesIO

from matplotlib import pyplot as plt
from torchvision import transforms

import io
import logging
import multiprocessing
import random
import time
import imghdr
from pathlib import Path
from typing import Union
from loguru import logger

from lama_cleaner.model_manager import ModelManager
from lama_cleaner.schema import Config

try:
    torch._C._jit_override_can_fuse_on_cpu(False)
    torch._C._jit_override_can_fuse_on_gpu(False)
    torch._C._jit_set_texpr_fuser_enabled(False)
    torch._C._jit_set_nvfuser_enabled(False)
except:
    pass


from lama_cleaner.helper import (
    load_img,
    numpy_to_bytes,
    resize_max_size,
)

NUM_THREADS = str(multiprocessing.cpu_count())

# fix libomp problem on windows https://github.com/Sanster/lama-cleaner/issues/56
os.environ["KMP_DUPLICATE_LIB_OK"] = "True"

os.environ["OMP_NUM_THREADS"] = NUM_THREADS
os.environ["OPENBLAS_NUM_THREADS"] = NUM_THREADS
os.environ["MKL_NUM_THREADS"] = NUM_THREADS
os.environ["VECLIB_MAXIMUM_THREADS"] = NUM_THREADS
os.environ["NUMEXPR_NUM_THREADS"] = NUM_THREADS
if os.environ.get("CACHE_DIR"):
    os.environ["TORCH_HOME"] = os.environ["CACHE_DIR"]

HF_TOKEN_SD = os.environ.get('HF_TOKEN_SD')

device = "cuda" if torch.cuda.is_available() else "cpu"
print(f'device = {device}')

def get_image_ext(img_bytes):
    w = imghdr.what("", img_bytes)
    if w is None:
        w = "jpeg"
    return w
    
def read_content(file_path):
    """read the content of target file
    """
    with open(file_path, 'rb') as f:
        content = f.read()
    return content
    
model = None

def model_process(image, mask):
    global model
    
    if mask.shape[0] == image.shape[1] and mask.shape[1] == image.shape[0]:
        # rotate image
        image = np.transpose(image[::-1, ...][:, ::-1], axes=(1, 0, 2))[::-1, ...]
        
    original_shape = image.shape
    interpolation = cv2.INTER_CUBIC
    
    size_limit = 1080 #1080 # "Original"
    if size_limit == "Original":
        size_limit = max(image.shape)
    else:
        size_limit = int(size_limit)

    config = Config(
        ldm_steps=25,
        ldm_sampler='plms',
        zits_wireframe=True,
        hd_strategy='Original',
        hd_strategy_crop_margin=196,
        hd_strategy_crop_trigger_size=1280,
        hd_strategy_resize_limit=2048,
        prompt='',
        use_croper=False,
        croper_x=0,
        croper_y=0,
        croper_height=512,
        croper_width=512,
        sd_mask_blur=5,
        sd_strength=0.75,
        sd_steps=50,
        sd_guidance_scale=7.5,
        sd_sampler='ddim',
        sd_seed=42,
        cv2_flag='INPAINT_NS',
        cv2_radius=5,
    )
    
    if config.sd_seed == -1:
        config.sd_seed = random.randint(1, 999999999)

    print(f"Origin image shape_0_: {original_shape} / {size_limit}")
    image = resize_max_size(image, size_limit=size_limit, interpolation=interpolation)
    print(f"Resized image shape_1_: {image.shape}")
    
    print(f"mask image shape_0_: {mask.shape} / {type(mask)}")
    mask = resize_max_size(mask, size_limit=size_limit, interpolation=interpolation)
    print(f"mask image shape_1_: {mask.shape} / {type(mask)}")

    if model is None:
        return None
        
    res_np_img = model(image, mask, config)
    torch.cuda.empty_cache()
  
    image = Image.open(io.BytesIO(numpy_to_bytes(res_np_img, 'png')))
    return  image # image
    
model = ModelManager(
        name='lama',
        device=device,
    )

image_type = 'pil' # filepath' #'pil'
def predict(input):
    if image_type == 'filepath':
        # input: {'image': '/tmp/tmp8mn9xw93.png', 'mask': '/tmp/tmpn5ars4te.png'}
        origin_image_bytes = read_content(input["image"])
        print(f'origin_image_bytes = ', type(origin_image_bytes), len(origin_image_bytes))    
        image, _ = load_img(origin_image_bytes) 
        mask, _ = load_img(read_content(input["mask"]), gray=True)       
    elif image_type == 'pil':
        # input: {'image': pil, 'mask': pil}
        image_pil = input['image']
        mask_pil = input['mask']
        image = np.array(image_pil)
        mask = np.array(mask_pil.convert("L"))
        # output = mask_pil 
    output = model_process(image, mask)
    return output

css = '''
.container {max-width: 1150px;margin: auto;padding-top: 1.5rem}
#image_upload{min-height:512px}
#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 512px}
#mask_radio .gr-form{background:transparent; border: none}
#word_mask{margin-top: .75em !important}
#word_mask textarea:disabled{opacity: 0.3}
.footer {margin-bottom: 45px;margin-top: 35px;text-align: center;border-bottom: 1px solid #e5e5e5}
.footer>p {font-size: .8rem; display: inline-block; padding: 0 10px;transform: translateY(10px);background: white}
.dark .footer {border-color: #303030}
.dark .footer>p {background: #0b0f19}
.acknowledgments h4{margin: 1.25em 0 .25em 0;font-weight: bold;font-size: 115%}
#image_upload .touch-none{display: flex}
@keyframes spin {
    from {
        transform: rotate(0deg);
    }
    to {
        transform: rotate(360deg);
    }
}
#share-btn-container {
    display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
}
#share-btn {
    all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;
}
#share-btn * {
    all: unset;
}
#share-btn-container div:nth-child(-n+2){
    width: auto !important;
    min-height: 0px !important;
}
#share-btn-container .wrap {
    display: none !important;
}
'''

image_blocks = gr.Blocks(css=css)
with image_blocks as demo:
    with gr.Group():
        with gr.Box():
            with gr.Row():
                with gr.Column():
                    image = gr.Image(source='upload', elem_id="image_upload",tool='sketch', type=f'{image_type}', label="Upload").style(mobile_collapse=False, height=512)
                    with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
                        btn_in = gr.Button("Done!").style(
                            margin=True,
                            rounded=(True, True, True, True),
                            full_width=True,
                        )                
                
                with gr.Column():
                    image_out = gr.Image(label="Output", elem_id="image_output", visible=True).style(height=512)
            btn_in.click(fn=predict, inputs=[image], outputs=[image_out])
            
image_blocks.launch()