File size: 8,254 Bytes
18d2806
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29e1fe9
18d2806
 
 
 
 
 
 
 
29e1fe9
 
 
 
18d2806
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Open Source Model Licensed under the Apache License Version 2.0
# and Other Licenses of the Third-Party Components therein:
# The below Model in this distribution may have been modified by THL A29 Limited
# ("Tencent Modifications"). All Tencent Modifications are Copyright (C) 2024 THL A29 Limited.

# Copyright (C) 2024 THL A29 Limited, a Tencent company.  All rights reserved.
# The below software and/or models in this distribution may have been
# modified by THL A29 Limited ("Tencent Modifications").
# All Tencent Modifications are Copyright (C) THL A29 Limited.

# Hunyuan 3D is licensed under the TENCENT HUNYUAN NON-COMMERCIAL LICENSE AGREEMENT
# except for the third-party components listed below.
# Hunyuan 3D does not impose any additional limitations beyond what is outlined
# in the repsective licenses of these third-party components.
# Users must comply with all terms and conditions of original licenses of these third-party
# components and must ensure that the usage of the third party components adheres to
# all relevant laws and regulations.

# For avoidance of doubts, Hunyuan 3D means the large language models and
# their software and algorithms, including trained model weights, parameters (including
# optimizer states), machine-learning model code, inference-enabling code, training-enabling code,
# fine-tuning enabling code and other elements of the foregoing made publicly available
# by Tencent in accordance with TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT.


import logging
import os

import numpy as np
import torch
from PIL import Image

from .differentiable_renderer.mesh_render import MeshRender
from .utils.dehighlight_utils import Light_Shadow_Remover
from .utils.multiview_utils import Multiview_Diffusion_Net
from .utils.uv_warp_utils import mesh_uv_wrap

logger = logging.getLogger(__name__)


class Hunyuan3DTexGenConfig:

    def __init__(self, light_remover_ckpt_path, multiview_ckpt_path):
        self.device = 'cuda'
        self.light_remover_ckpt_path = light_remover_ckpt_path
        self.multiview_ckpt_path = multiview_ckpt_path

        self.candidate_camera_azims = [0, 90, 180, 270, 0, 180]
        self.candidate_camera_elevs = [0, 0, 0, 0, 90, -90]
        self.candidate_view_weights = [1, 0.1, 0.5, 0.1, 0.05, 0.05]

        self.render_size = 2048
        self.texture_size = 1024
        self.bake_exp = 4
        self.merge_method = 'fast'


class Hunyuan3DPaintPipeline:
    @classmethod
    def from_pretrained(cls, model_path):
        original_model_path = model_path
        if not os.path.exists(model_path):
            # try local path
            base_dir = os.environ.get('HY3DGEN_MODELS', '~/.cache/hy3dgen')
            model_path = os.path.expanduser(os.path.join(base_dir, model_path))

            delight_model_path = os.path.join(model_path, 'hunyuan3d-delight-v2-0')
            multiview_model_path = os.path.join(model_path, 'hunyuan3d-paint-v2-0')

            if not os.path.exists(delight_model_path) or not os.path.exists(multiview_model_path):
                try:
                    import huggingface_hub
                    # download from huggingface
                    model_path = huggingface_hub.snapshot_download(repo_id=original_model_path)
                    delight_model_path = os.path.join(model_path, 'hunyuan3d-delight-v2-0')
                    multiview_model_path = os.path.join(model_path, 'hunyuan3d-paint-v2-0')
                    return cls(Hunyuan3DTexGenConfig(delight_model_path, multiview_model_path))
                except ImportError:
                    logger.warning(
                        "You need to install HuggingFace Hub to load models from the hub."
                    )
                    raise RuntimeError(f"Model path {model_path} not found")
            else:
                return cls(Hunyuan3DTexGenConfig(delight_model_path, multiview_model_path))

        raise FileNotFoundError(f"Model path {original_model_path} not found and we could not find it at huggingface")

    def __init__(self, config):
        self.config = config
        self.models = {}
        self.render = MeshRender(
            default_resolution=self.config.render_size,
            texture_size=self.config.texture_size)

        self.load_models()

    def load_models(self):
        # empty cude cache
        torch.cuda.empty_cache()
        # Load model
        self.models['delight_model'] = Light_Shadow_Remover(self.config)
        self.models['multiview_model'] = Multiview_Diffusion_Net(self.config)

    def render_normal_multiview(self, camera_elevs, camera_azims, use_abs_coor=True):
        normal_maps = []
        for elev, azim in zip(camera_elevs, camera_azims):
            normal_map = self.render.render_normal(
                elev, azim, use_abs_coor=use_abs_coor, return_type='pl')
            normal_maps.append(normal_map)

        return normal_maps

    def render_position_multiview(self, camera_elevs, camera_azims):
        position_maps = []
        for elev, azim in zip(camera_elevs, camera_azims):
            position_map = self.render.render_position(
                elev, azim, return_type='pl')
            position_maps.append(position_map)

        return position_maps

    def bake_from_multiview(self, views, camera_elevs,
                            camera_azims, view_weights, method='graphcut'):
        project_textures, project_weighted_cos_maps = [], []
        project_boundary_maps = []
        for view, camera_elev, camera_azim, weight in zip(
            views, camera_elevs, camera_azims, view_weights):
            project_texture, project_cos_map, project_boundary_map = self.render.back_project(
                view, camera_elev, camera_azim)
            project_cos_map = weight * (project_cos_map ** self.config.bake_exp)
            project_textures.append(project_texture)
            project_weighted_cos_maps.append(project_cos_map)
            project_boundary_maps.append(project_boundary_map)

        if method == 'fast':
            texture, ori_trust_map = self.render.fast_bake_texture(
                project_textures, project_weighted_cos_maps)
        else:
            raise f'no method {method}'
        return texture, ori_trust_map > 1E-8

    def texture_inpaint(self, texture, mask):

        texture_np = self.render.uv_inpaint(texture, mask)
        texture = torch.tensor(texture_np / 255).float().to(texture.device)

        return texture

    @torch.no_grad()
    def __call__(self, mesh, image):

        if isinstance(image, str):
            image_prompt = Image.open(image)
        else:
            image_prompt = image

        image_prompt = self.models['delight_model'](image_prompt)

        mesh = mesh_uv_wrap(mesh)

        self.render.load_mesh(mesh)

        selected_camera_elevs, selected_camera_azims, selected_view_weights = \
            self.config.candidate_camera_elevs, self.config.candidate_camera_azims, self.config.candidate_view_weights

        normal_maps = self.render_normal_multiview(
            selected_camera_elevs, selected_camera_azims, use_abs_coor=True)
        position_maps = self.render_position_multiview(
            selected_camera_elevs, selected_camera_azims)

        camera_info = [(((azim // 30) + 9) % 12) // {-20: 1, 0: 1, 20: 1, -90: 3, 90: 3}[
            elev] + {-20: 0, 0: 12, 20: 24, -90: 36, 90: 40}[elev] for azim, elev in
                       zip(selected_camera_azims, selected_camera_elevs)]
        multiviews = self.models['multiview_model'](image_prompt, normal_maps + position_maps, camera_info)

        for i in range(len(multiviews)):
            multiviews[i] = multiviews[i].resize(
                (self.config.render_size, self.config.render_size))

        texture, mask = self.bake_from_multiview(multiviews,
                                                 selected_camera_elevs, selected_camera_azims, selected_view_weights,
                                                 method=self.config.merge_method)

        mask_np = (mask.squeeze(-1).cpu().numpy() * 255).astype(np.uint8)

        texture = self.texture_inpaint(texture, mask_np)

        self.render.set_texture(texture)
        textured_mesh = self.render.save_mesh()

        return textured_mesh