app.py

import gradio as gr

from io import BytesIO
import requests
import PIL
from PIL import Image
import numpy as np
import os
import uuid
import torch
from torch import autocast
import cv2
from matplotlib import pyplot as plt
from torchvision import transforms
# from diffusers import DiffusionPipeline

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"]

BUILD_DIR = os.environ.get("LAMA_CLEANER_BUILD_DIR", "app/build")

from share_btn import community_icon_html, loading_icon_html, share_js

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

device = "cuda" if torch.cuda.is_available() else "cpu"

def get_image_ext(img_bytes):
    w = imghdr.what("", img_bytes)
    if w is None:
        w = "jpeg"
    return w
    
def diffuser_callback(i, t, latents):
    pass

def process(init_image, mask):
    global model
    '''
    input = request.files
    # RGB
    origin_image_bytes = input["image"].read()
    '''
    
    print(f'liuyz_1_here_')
    
    # image, alpha_channel = load_img(origin_image_bytes)
    original_shape = init_image.shape
    interpolation = cv2.INTER_CUBIC
    
    '''
    form = request.form
    '''
    size_limit = 1080 # : Union[int, str] = form.get("sizeLimit", "1080")
    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,
        '''
        ldm_steps=form["ldmSteps"],
        ldm_sampler=form["ldmSampler"],
        hd_strategy=form["hdStrategy"],
        zits_wireframe=form["zitsWireframe"],
        hd_strategy_crop_margin=form["hdStrategyCropMargin"],
        hd_strategy_crop_trigger_size=form["hdStrategyCropTrigerSize"],
        hd_strategy_resize_limit=form["hdStrategyResizeLimit"],
        prompt=form["prompt"],
        use_croper=form["useCroper"],
        croper_x=form["croperX"],
        croper_y=form["croperY"],
        croper_height=form["croperHeight"],
        croper_width=form["croperWidth"],
        sd_mask_blur=form["sdMaskBlur"],
        sd_strength=form["sdStrength"],
        sd_steps=form["sdSteps"],
        sd_guidance_scale=form["sdGuidanceScale"],
        sd_sampler=form["sdSampler"],
        sd_seed=form["sdSeed"],
        cv2_flag=form["cv2Flag"],
        cv2_radius=form['cv2Radius']
        '''
    )

    if config.sd_seed == -1:
        config.sd_seed = random.randint(1, 999999999)

    # logger.info(f"Origin image shape: {original_shape}")
    print(f"Origin image shape: {original_shape}")
    image = resize_max_size(image, size_limit=size_limit, interpolation=interpolation)
    # logger.info(f"Resized image shape: {image.shape}")
    print(f"Resized image shape: {image.shape}")

    mask, _ = load_img(input["mask"].read(), gray=True)
    mask = resize_max_size(mask, size_limit=size_limit, interpolation=interpolation)

    start = time.time()
    res_np_img = model(image, mask, config)
    logger.info(f"process time: {(time.time() - start) * 1000}ms")

    torch.cuda.empty_cache()

    if alpha_channel is not None:
        if alpha_channel.shape[:2] != res_np_img.shape[:2]:
            alpha_channel = cv2.resize(
                alpha_channel, dsize=(res_np_img.shape[1], res_np_img.shape[0])
            )
        res_np_img = np.concatenate(
            (res_np_img, alpha_channel[:, :, np.newaxis]), axis=-1
        )

    ext = get_image_ext(origin_image_bytes)
    return ext
    '''
    response = make_response(
        send_file(
            io.BytesIO(numpy_to_bytes(res_np_img, ext)),
            mimetype=f"image/{ext}",
        )
    )
    response.headers["X-Seed"] = str(config.sd_seed)
    return response
    '''
    
model = ModelManager(
        name='lama',
        device=device,
        # hf_access_token=HF_TOKEN_SD,
        # sd_disable_nsfw=False,
        # sd_cpu_textencoder=True,
        # sd_run_local=True,
        # callback=diffuser_callback,
    )
    

'''
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", dtype=torch.float16, revision="fp16", use_auth_token=auth_token).to(device)

transform = transforms.Compose([
      transforms.ToTensor(),
      transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
      transforms.Resize((512, 512)),
])
'''

def read_content(file_path: str) -> str:
    """read the content of target file
    """
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()

    return content

def predict(dict, prompt=""):
    init_image = dict["image"].convert("RGB") #.resize((512, 512))
    mask = dict["mask"].convert("RGB") #.resize((512, 512))
    output = process(init_image, mask)
    # output = pipe(prompt = prompt, image=init_image, mask_image=mask,guidance_scale=7.5)
    
    return output.images[0], gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)


css = '''
.container {max-width: 1150px;margin: auto;padding-top: 1.5rem}
#image_upload{min-height:400px}
#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 400px}
#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:
    # gr.HTML(read_content("header.html"))
    with gr.Group():
        with gr.Box():
            with gr.Row():
                with gr.Column():
                    image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Upload") #.style(height=400)
                    with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
                        # prompt = gr.Textbox(placeholder = 'Your prompt (what you want in place of what is erased)', show_label=False, elem_id="input-text")
                        btn = gr.Button("Done!").style(
                            margin=False,
                            rounded=(False, True, True, False),
                            full_width=False,
                        )
                '''
                with gr.Column():
                    image_out = gr.Image(label="Output", elem_id="output-img").style(height=400)
                    with gr.Group(elem_id="share-btn-container"):
                        community_icon = gr.HTML(community_icon_html, visible=False)
                        loading_icon = gr.HTML(loading_icon_html, visible=False)
                        share_button = gr.Button("Share to community", elem_id="share-btn", visible=False)
                '''

            # btn.click(fn=predict, inputs=[image, prompt], outputs=[image_out, community_icon, loading_icon, share_button])
            btn.click(fn=predict, inputs=[image], outputs=[image]) #, community_icon, loading_icon, share_button])
            # share_button.click(None, [], [], _js=share_js)

image_blocks.launch()