Spaces:
Running
on
L40S
Running
on
L40S
File size: 5,649 Bytes
b155b2e e3e5f9e |
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 |
# 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.l
import os
import warnings
import torch
from PIL import Image
import argparse
from infer import Text2Image, Removebg, Image2Views, Views2Mesh, GifRenderer
warnings.simplefilter('ignore', category=UserWarning)
warnings.simplefilter('ignore', category=FutureWarning)
warnings.simplefilter('ignore', category=DeprecationWarning)
def get_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--use_lite", default=False, action="store_true"
)
parser.add_argument(
"--mv23d_cfg_path", default="./svrm/configs/svrm.yaml", type=str
)
parser.add_argument(
"--mv23d_ckt_path", default="weights/svrm/svrm.safetensors", type=str
)
parser.add_argument(
"--text2image_path", default="weights/hunyuanDiT", type=str
)
parser.add_argument(
"--save_folder", default="./outputs/test/", type=str
)
parser.add_argument(
"--text_prompt", default="", type=str,
)
parser.add_argument(
"--image_prompt", default="", type=str
)
parser.add_argument(
"--device", default="cuda:0", type=str
)
parser.add_argument(
"--t2i_seed", default=0, type=int
)
parser.add_argument(
"--t2i_steps", default=25, type=int
)
parser.add_argument(
"--gen_seed", default=0, type=int
)
parser.add_argument(
"--gen_steps", default=50, type=int
)
parser.add_argument(
"--max_faces_num", default=80000, type=int,
help="max num of face, suggest 80000 for effect, 10000 for speed"
)
parser.add_argument(
"--save_memory", default=False, action="store_true"
)
parser.add_argument(
"--do_texture_mapping", default=False, action="store_true"
)
parser.add_argument(
"--do_render", default=False, action="store_true"
)
return parser.parse_args()
if __name__ == "__main__":
args = get_args()
assert not (args.text_prompt and args.image_prompt), "Text and image can only be given to one"
assert args.text_prompt or args.image_prompt, "Text and image can only be given to one"
# init model
rembg_model = Removebg()
image_to_views_model = Image2Views(
device=args.device,
use_lite=args.use_lite,
save_memory=args.save_memory
)
views_to_mesh_model = Views2Mesh(
args.mv23d_cfg_path,
args.mv23d_ckt_path,
args.device,
use_lite=args.use_lite,
save_memory=args.save_memory
)
if args.text_prompt:
text_to_image_model = Text2Image(
pretrain = args.text2image_path,
device = args.device,
save_memory = args.save_memory
)
if args.do_render:
gif_renderer = GifRenderer(device=args.device)
# ---- ----- ---- ---- ---- ----
os.makedirs(args.save_folder, exist_ok=True)
# stage 1, text to image
if args.text_prompt:
res_rgb_pil = text_to_image_model(
args.text_prompt,
seed=args.t2i_seed,
steps=args.t2i_steps
)
res_rgb_pil.save(os.path.join(args.save_folder, "img.jpg"))
elif args.image_prompt:
res_rgb_pil = Image.open(args.image_prompt)
# stage 2, remove back ground
res_rgba_pil = rembg_model(res_rgb_pil)
res_rgb_pil.save(os.path.join(args.save_folder, "img_nobg.png"))
# stage 3, image to views
(views_grid_pil, cond_img), view_pil_list = image_to_views_model(
res_rgba_pil,
seed = args.gen_seed,
steps = args.gen_steps
)
views_grid_pil.save(os.path.join(args.save_folder, "views.jpg"))
# stage 4, views to mesh
views_to_mesh_model(
views_grid_pil,
cond_img,
seed = args.gen_seed,
target_face_count = args.max_faces_num,
save_folder = args.save_folder,
do_texture_mapping = args.do_texture_mapping
)
# stage 5, render gif
if args.do_render:
gif_renderer(
os.path.join(args.save_folder, 'mesh.obj'),
gif_dst_path = os.path.join(args.save_folder, 'output.gif'),
)
|