File size: 5,658 Bytes
c24da45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31ec2b7
 
 
 
c24da45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31ec2b7
c24da45
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
import torch
from libs.base_utils import do_resize_content
from imagedream.ldm.util import (
    instantiate_from_config,
    get_obj_from_str,
)
from omegaconf import OmegaConf
from PIL import Image
import numpy as np
from inference import generate3d
from huggingface_hub import hf_hub_download
import json
import argparse
import shutil
from model import CRM
import PIL
import rembg
import os
from pipelines import TwoStagePipeline

rembg_session = rembg.new_session()

def expand_to_square(image, bg_color=(0, 0, 0, 0)):
    # expand image to 1:1
    width, height = image.size
    if width == height:
        return image
    new_size = (max(width, height), max(width, height))
    new_image = Image.new("RGBA", new_size, bg_color)
    paste_position = ((new_size[0] - width) // 2, (new_size[1] - height) // 2)
    new_image.paste(image, paste_position)
    return new_image

def remove_background(
    image: PIL.Image.Image,
    rembg_session = None,
    force: bool = False,
    **rembg_kwargs,
) -> PIL.Image.Image:
    do_remove = True
    if image.mode == "RGBA" and image.getextrema()[3][0] < 255:
        # explain why current do not rm bg
        print("alhpa channl not enpty, skip remove background, using alpha channel as mask")
        background = Image.new("RGBA", image.size, (0, 0, 0, 0))
        image = Image.alpha_composite(background, image)
        do_remove = False
    do_remove = do_remove or force
    if do_remove:
        image = rembg.remove(image, session=rembg_session, **rembg_kwargs)
    return image

def do_resize_content(original_image: Image, scale_rate):
    # resize image content wile retain the original image size
    if scale_rate != 1:
        # Calculate the new size after rescaling
        new_size = tuple(int(dim * scale_rate) for dim in original_image.size)
        # Resize the image while maintaining the aspect ratio
        resized_image = original_image.resize(new_size)
        # Create a new image with the original size and black background
        padded_image = Image.new("RGBA", original_image.size, (0, 0, 0, 0))
        paste_position = ((original_image.width - resized_image.width) // 2, (original_image.height - resized_image.height) // 2)
        padded_image.paste(resized_image, paste_position)
        return padded_image
    else:
        return original_image

def add_background(image, bg_color=(255, 255, 255)):
    # given an RGBA image, alpha channel is used as mask to add background color
    background = Image.new("RGBA", image.size, bg_color)
    return Image.alpha_composite(background, image)


def preprocess_image(image, background_choice, foreground_ratio, backgroud_color):
    """
    input image is a pil image in RGBA, return RGB image
    """
    print(background_choice)
    if background_choice == "Alpha as mask":
        background = Image.new("RGBA", image.size, (0, 0, 0, 0))
        image = Image.alpha_composite(background, image)
    else:
        image = remove_background(image, rembg_session, force_remove=True)
    image = do_resize_content(image, foreground_ratio)
    image = expand_to_square(image)
    image = add_background(image, backgroud_color)
    return image.convert("RGB")

if __name__ == "__main__":

    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--inputdir",
        type=str,
        default="examples/kunkun.webp",
        help="dir for input image",
    )
    parser.add_argument(
        "--scale",
        type=float,
        default=5.0,
    )
    parser.add_argument(
        "--step",
        type=int,
        default=50,
    )
    parser.add_argument(
        "--bg_choice",
        type=str,
        default="Auto Remove background",
        help="[Auto Remove background] or [Alpha as mask]",
    )
    parser.add_argument(
        "--outdir",
        type=str,
        default="out/",
    )    
    args = parser.parse_args()
    

    img = Image.open(args.inputdir)
    img = preprocess_image(img, args.bg_choice, 1.0, (127, 127, 127))
    os.makedirs(args.outdir, exist_ok=True)
    img.save(args.outdir+"preprocessed_image.png")

    crm_path = hf_hub_download(repo_id="Zhengyi/CRM", filename="CRM.pth")
    specs = json.load(open("configs/specs_objaverse_total.json"))
    # model = CRM(specs).to("cuda")
    model = CRM(specs).to("cpu")

    model.load_state_dict(torch.load(crm_path, map_location = "cpu"), strict=False)

    stage1_config = OmegaConf.load("configs/nf7_v3_SNR_rd_size_stroke.yaml").config
    stage2_config = OmegaConf.load("configs/stage2-v2-snr.yaml").config
    stage2_sampler_config = stage2_config.sampler
    stage1_sampler_config = stage1_config.sampler

    stage1_model_config = stage1_config.models
    stage2_model_config = stage2_config.models

    xyz_path = hf_hub_download(repo_id="Zhengyi/CRM", filename="ccm-diffusion.pth")
    pixel_path = hf_hub_download(repo_id="Zhengyi/CRM", filename="pixel-diffusion.pth")
    stage1_model_config.resume = pixel_path
    stage2_model_config.resume = xyz_path

    pipeline = TwoStagePipeline(
        stage1_model_config,
        stage2_model_config,
        stage1_sampler_config,
        stage2_sampler_config,
    )

    rt_dict = pipeline(img, scale=args.scale, step=args.step)
    stage1_images = rt_dict["stage1_images"]
    stage2_images = rt_dict["stage2_images"]
    np_imgs = np.concatenate(stage1_images, 1)
    np_xyzs = np.concatenate(stage2_images, 1)
    Image.fromarray(np_imgs).save(args.outdir+"pixel_images.png")
    Image.fromarray(np_xyzs).save(args.outdir+"xyz_images.png")

    glb_path, obj_path = generate3d(model, np_imgs, np_xyzs, "cpu")
    shutil.copy(obj_path, args.outdir+"output3d.zip")