File size: 10,070 Bytes
237dc54
39b4836
 
1c6c14b
 
39b4836
 
237dc54
 
4d6f443
39b4836
1c6c14b
39b4836
 
 
237dc54
 
1c6c14b
39b4836
237dc54
 
4d6f443
 
 
39b4836
237dc54
 
61c3cca
1c6c14b
39b4836
 
 
 
237dc54
39b4836
 
 
 
 
 
237dc54
 
 
 
 
 
 
 
 
4d6f443
 
237dc54
 
 
 
 
 
 
1c6c14b
237dc54
 
 
 
 
 
 
 
 
 
 
 
4d6f443
 
237dc54
39b4836
237dc54
4d6f443
237dc54
 
39b4836
4d6f443
 
 
 
237dc54
 
 
 
 
4d6f443
 
 
 
237dc54
 
 
 
39b4836
 
237dc54
4d6f443
 
 
 
237dc54
 
4d6f443
 
237dc54
 
4d6f443
237dc54
 
 
 
 
 
4d6f443
 
237dc54
 
 
39b4836
237dc54
 
 
4d6f443
 
237dc54
 
 
1c6c14b
 
 
d9aed5a
1c6c14b
 
 
 
 
 
 
 
 
 
 
4d6f443
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ccc4eeb
 
 
 
 
 
 
 
 
 
 
 
 
4d6f443
 
 
 
 
 
 
b27b04c
 
 
 
 
 
 
 
 
4d6f443
 
 
 
 
 
 
 
 
 
 
 
 
 
b27b04c
 
 
 
 
 
 
 
 
 
 
 
4d6f443
 
 
 
 
 
237dc54
4d6f443
237dc54
 
 
4d6f443
 
 
 
 
 
 
 
 
 
 
 
 
39b4836
4d6f443
 
 
 
 
 
 
 
b27b04c
4d6f443
b27b04c
 
4d6f443
 
b27b04c
4d6f443
 
 
 
 
 
 
61c3cca
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
import os
import shutil
import tempfile
import time
from os import path

import gradio as gr
import numpy as np
import rembg
import spaces
import torch
from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler, StableDiffusionXLPipeline, LCMScheduler
from einops import rearrange
from huggingface_hub import hf_hub_download
from omegaconf import OmegaConf
from PIL import Image
from pytorch_lightning import seed_everything
from safetensors.torch import load_file
from torchvision.transforms import v2
from tqdm import tqdm

from src.utils.camera_util import (FOV_to_intrinsics, get_circular_camera_poses,
                                   get_zero123plus_input_cameras)
from src.utils.infer_util import (remove_background, resize_foreground)
from src.utils.mesh_util import save_glb, save_obj
from src.utils.train_util import instantiate_from_config

torch.backends.cuda.matmul.allow_tf32 = True

def find_cuda():
    cuda_home = os.environ.get('CUDA_HOME') or os.environ.get('CUDA_PATH')
    if cuda_home and os.path.exists(cuda_home):
        return cuda_home

    nvcc_path = shutil.which('nvcc')
    if nvcc_path:
        cuda_path = os.path.dirname(os.path.dirname(nvcc_path))
        return cuda_path

    return None


def get_render_cameras(batch_size=1, M=120, radius=2.5, elevation=10.0, is_flexicubes=False):
    c2ws = get_circular_camera_poses(M=M, radius=radius, elevation=elevation)
    if is_flexicubes:
        cameras = torch.linalg.inv(c2ws)
        cameras = cameras.unsqueeze(0).repeat(batch_size, 1, 1, 1)
    else:
        extrinsics = c2ws.flatten(-2)
        intrinsics = FOV_to_intrinsics(50.0).unsqueeze(
            0).repeat(M, 1, 1).float().flatten(-2)
        cameras = torch.cat([extrinsics, intrinsics], dim=-1)
        cameras = cameras.unsqueeze(0).repeat(batch_size, 1, 1)
    return cameras


def check_input_image(input_image):
    if input_image is None:
        raise gr.Error("No image selected!")


def preprocess(input_image, do_remove_background):
    rembg_session = rembg.new_session() if do_remove_background else None

    if do_remove_background:
        input_image = remove_background(input_image, rembg_session)
        input_image = resize_foreground(input_image, 0.85)

    return input_image


@spaces.GPU
def generate_mvs(input_image, sample_steps, sample_seed):
    seed_everything(sample_seed)

    z123_image = pipeline(
        input_image, num_inference_steps=sample_steps).images[0]

    show_image = np.asarray(z123_image, dtype=np.uint8)
    show_image = torch.from_numpy(show_image)
    show_image = rearrange(
        show_image, '(n h) (m w) c -> (n m) h w c', n=3, m=2)
    show_image = rearrange(
        show_image, '(n m) h w c -> (n h) (m w) c', n=2, m=3)
    show_image = Image.fromarray(show_image.numpy())

    return z123_image, show_image


@spaces.GPU
def make3d(images):
    global model
    if IS_FLEXICUBES:
        model.init_flexicubes_geometry(device, use_renderer=False)
    model = model.eval()

    images = np.asarray(images, dtype=np.float32) / 255.0
    images = torch.from_numpy(images).permute(2, 0, 1).contiguous().float()
    images = rearrange(images, 'c (n h) (m w) -> (n m) c h w', n=3, m=2)

    input_cameras = get_zero123plus_input_cameras(
        batch_size=1, radius=4.0).to(device)
    render_cameras = get_render_cameras(
        batch_size=1, radius=2.5, is_flexicubes=IS_FLEXICUBES).to(device)

    images = images.unsqueeze(0).to(device)
    images = v2.functional.resize(
        images, (320, 320), interpolation=3, antialias=True).clamp(0, 1)

    mesh_fpath = tempfile.NamedTemporaryFile(suffix=f".obj", delete=False).name
    print(mesh_fpath)
    mesh_basename = os.path.basename(mesh_fpath).split('.')[0]
    mesh_dirname = os.path.dirname(mesh_fpath)
    mesh_glb_fpath = os.path.join(mesh_dirname, f"{mesh_basename}.glb")

    with torch.no_grad():
        planes = model.forward_planes(images, input_cameras)
        mesh_out = model.extract_mesh(
            planes, use_texture_map=False, **infer_config)

        vertices, faces, vertex_colors = mesh_out
        vertices = vertices[:, [1, 2, 0]]

        save_glb(vertices, faces, vertex_colors, mesh_glb_fpath)
        save_obj(vertices, faces, vertex_colors, mesh_fpath)

        print(f"Mesh saved to {mesh_fpath}")

    return mesh_fpath, mesh_glb_fpath


@spaces.GPU
def process_image(num_images, prompt):
    global pipe
    with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
        return pipe(
            prompt=[prompt]*num_images,
            generator=torch.Generator().manual_seed(123),
            num_inference_steps=1,
            guidance_scale=0.,
            height=int(512),
            width=int(512),
            timesteps=[800]
        ).images


# Configuration
cuda_path = find_cuda()
config_path = 'configs/instant-mesh-large.yaml'
config = OmegaConf.load(config_path)
config_name = os.path.basename(config_path).replace('.yaml', '')
model_config = config.model_config
infer_config = config.infer_config

IS_FLEXICUBES = config_name.startswith('instant-mesh')
device = torch.device('cuda')

# Load diffusion model
print('Loading diffusion model ...')
pipeline = DiffusionPipeline.from_pretrained(
    "sudo-ai/zero123plus-v1.2",
    custom_pipeline="zero123plus",
    torch_dtype=torch.float16,
)
pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(
    pipeline.scheduler.config, timestep_spacing='trailing'
)

unet_ckpt_path = hf_hub_download(
    repo_id="TencentARC/InstantMesh", filename="diffusion_pytorch_model.bin", repo_type="model")
state_dict = torch.load(unet_ckpt_path, map_location='cpu')
pipeline.unet.load_state_dict(state_dict, strict=True)

pipeline = pipeline.to(device)

# Load reconstruction model
print('Loading reconstruction model ...')
model_ckpt_path = hf_hub_download(
    repo_id="TencentARC/InstantMesh", filename="instant_mesh_large.ckpt", repo_type="model")
model = instantiate_from_config(model_config)
state_dict = torch.load(model_ckpt_path, map_location='cpu')['state_dict']
state_dict = {k[14:]: v for k, v in state_dict.items() if k.startswith(
    'lrm_generator.') and 'source_camera' not in k}
model.load_state_dict(state_dict, strict=True)

model = model.to(device)

# Load text-to-image model
print('Loading text-to-image model ...')

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16)
pipe.to(device="cuda", dtype=torch.bfloat16)

unet_state = load_file(hf_hub_download(
    "ByteDance/Hyper-SD", "Hyper-SDXL-1step-Unet.safetensors"), device="cuda")
pipe.unet.load_state_dict(unet_state)
pipe.scheduler = LCMScheduler.from_config(
    pipe.scheduler.config, timestep_spacing="trailing")

print('Loading Finished!')

# Gradio UI
with gr.Blocks() as demo:
    with gr.Row(variant="panel"):
        with gr.Column():
            with gr.Row():
                input_image = gr.Image(
                    label="Input Image",
                    image_mode="RGBA",
                    sources="upload",
                    type="pil",
                    elem_id="content_image",
                )
                processed_image = gr.Image(
                    label="Processed Image",
                    image_mode="RGBA",
                    type="pil",
                    interactive=False
                )
            with gr.Row():
                with gr.Group():
                    do_remove_background = gr.Checkbox(
                        label="Remove Background", value=True)
                    sample_seed = gr.Number(
                        value=42, label="Seed Value", precision=0)
                    sample_steps = gr.Slider(
                        label="Sample Steps", minimum=30, maximum=75, value=75, step=5)

            with gr.Row():
                submit = gr.Button(
                    "Generate", elem_id="generate", variant="primary")

            with gr.Row(variant="panel"):
                gr.Examples(
                    examples=[os.path.join("examples", img_name)
                              for img_name in sorted(os.listdir("examples"))],
                    inputs=[input_image],
                    label="Examples",
                    cache_examples=False,
                    examples_per_page=16
                )

        with gr.Column():
            with gr.Row():
                with gr.Column():
                    mv_show_images = gr.Image(
                        label="Generated Multi-views",
                        type="pil",
                        width=379,
                        interactive=False
                    )

            with gr.Row():
                with gr.Tab("OBJ"):
                    output_model_obj = gr.Model3D(
                        label="Output Model (OBJ Format)",
                        interactive=False,
                    )
                    gr.Markdown(
                        "Note: Downloaded .obj model will be flipped. Export .glb instead or manually flip it before usage.")
                with gr.Tab("GLB"):
                    output_model_glb = gr.Model3D(
                        label="Output Model (GLB Format)",
                        interactive=False,
                    )
                    gr.Markdown(
                        "Note: The model shown here has a darker appearance. Download to get correct results.")

            with gr.Row():
                gr.Markdown(
                    '''Try a different <b>seed value</b> if the result is unsatisfying (Default: 42).''')

    mv_images = gr.State()

    submit.click(fn=check_input_image, inputs=[input_image]).success(
        fn=preprocess,
        inputs=[input_image, do_remove_background],
        outputs=[processed_image],
    ).success(
        fn=generate_mvs,
        inputs=[processed_image, sample_steps, sample_seed],
        outputs=[mv_images, mv_show_images]
    ).success(
        fn=make3d,
        inputs=[mv_images],
        outputs=[output_model_obj, output_model_glb]
    )

demo.launch()