rename files

.ipynb_checkpoints/README-checkpoint.md

@@ -1,68 +0,0 @@
-**中文版本 [中文](README_zh.md)**
-
-# Unique3D
-High-Quality and Efficient 3D Mesh Generation from a Single Image
-
-## [Paper]() | [Project page](https://wukailu.github.io/Unique3D/) | [Huggingface Demo]() | [Online Demo](https://www.aiuni.ai/)
-
-![](assets/fig_teaser.png)
-
-High-fidelity and diverse textured meshes generated by Unique3D from single-view wild images in 30 seconds.
-
-## More features 
-
-The repo is still being under construction, thanks for your patience. 
-- [x] Local gradio demo.
-- [ ] Detailed tutorial.
-- [ ] Huggingface demo.
-- [ ] Detailed local demo.
-- [ ] Comfyui support.
-- [ ] Windows support.
-- [ ] Docker support.
-- [ ] More stable reconstruction with normal.
-- [ ] Training code release.
-
-## Preparation for inference
-
-### Linux System Setup.
-```angular2html
-conda create -n unique3d
-conda activate unique3d
-pip install -r requirements.txt
-```
-
-### Interactive inference: run your local gradio demo.
-
-1. Download the [ckpt.zip](), and extract it to `ckpt/*`.
-```
-Unique3D
-    ├──ckpt
-        ├── controlnet-tile/
-        ├── image2normal/
-        ├── img2mvimg/
-        ├── realesrgan-x4.onnx
-        └── v1-inference.yaml
-```
-
-2. Run the interactive inference locally.
-```bash
-python app/gradio_local.py --port 7860
-```
-
-## Tips to get better results
-
-1. Unique3D is sensitive to the facing direction of input images. Due to the distribution of the training data, orthographic front-facing images with a rest pose always lead to good reconstructions.
-2. Images with occlusions will cause worse reconstructions, since four views cannot cover the complete object. Images with fewer occlusions lead to better results.
-3. Pass an image with as high a resolution as possible to the input when resolution is a factor.
-
-## Acknowledgement
-
-We have intensively borrowed code from the following repositories. Many thanks to the authors for sharing their code.
-- [Stable Diffusion](https://github.com/CompVis/stable-diffusion)
-- [Wonder3d](https://github.com/xxlong0/Wonder3D)
-- [Zero123Plus](https://github.com/SUDO-AI-3D/zero123plus)
-- [Continues Remeshing](https://github.com/Profactor/continuous-remeshing)
-- [Depth from Normals](https://github.com/YertleTurtleGit/depth-from-normals)
-
-## Collaborations
-Our mission is to create a 4D generative model with 3D concepts. This is just our first step, and the road ahead is still long, but we are confident. We warmly invite you to join the discussion and explore potential collaborations in any capacity. <span style="color:red">**If you're interested in connecting or partnering with us, please don't hesitate to reach out via email (wkl22@mails.tsinghua.edu.cn)**</span>.

README.md

@@ -1,13 +0,0 @@
----
-title: Unique3D
-emoji: 🐨
-colorFrom: pink
-colorTo: gray
-sdk: gradio
-sdk_version: 4.32.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

README_zh.md

@@ -1,56 +0,0 @@
-**其他语言版本 [English](README.md)**
-
-# Unique3D
-High-Quality and Efficient 3D Mesh Generation from a Single Image
-
-## [论文]() | [项目页面](https://wukailu.github.io/Unique3D/)  | [Huggingface Demo]() | [在线演示](https://www.aiuni.ai/)
-
-![](assets/fig_teaser.png)
-
-Unique3D从单视图图像生成高保真度和多样化纹理的网格，在4090上大约需要30秒。
-
-### 推理准备
-
-#### Linux系统设置
-```angular2html
-conda create -n unique3d
-conda activate unique3d
-pip install -r requirements.txt
-```
-
-#### 交互式推理：运行您的本地gradio演示
-
-1. 下载[ckpt.zip]()，并将其解压到`ckpt/*`。
-```
-Unique3D
-    ├──ckpt
-        ├── controlnet-tile/
-        ├── image2normal/
-        ├── img2mvimg/
-        ├── realesrgan-x4.onnx
-        └── v1-inference.yaml
-```
-
-2. 在本地运行交互式推理。
-```bash
-python app/gradio_local.py --port 7860
-```
-
-## 获取更好结果的提示
-
-1. Unique3D对输入图像的朝向非常敏感。由于训练数据的分布，**正交正视图像**通常总是能带来良好的重建。对于人物而言，最好是 A-pose 或者 T-pose，因为目前训练数据很少含有其他类型姿态。
-2. 有遮挡的图像会导致更差的重建，因为4个视图无法覆盖完整的对象。遮挡较少的图像会带来更好的结果。
-3. 尽可能将高分辨率的图像用作输入。
-
-## 致谢
-
-我们借用了以下代码库的代码。非常感谢作者们分享他们的代码。
-- [Stable Diffusion](https://github.com/CompVis/stable-diffusion) 
-- [Wonder3d](https://github.com/xxlong0/Wonder3D) 
-- [Zero123Plus](https://github.com/SUDO-AI-3D/zero123plus) 
-- [Continues Remeshing](https://github.com/Profactor/continuous-remeshing) 
-- [Depth from Normals](https://github.com/YertleTurtleGit/depth-from-normals) 
-
-## 合作
-
-我们使命是创建一个具有3D概念的4D生成模型。这只是我们的第一步，前方的道路仍然很长，但我们有信心。我们热情邀请您加入讨论，并探索任何形式的潜在合作。<span style="color:red">**如果您有兴趣联系或与我们合作，欢迎通过电子邮件(wkl22@mails.tsinghua.edu.cn)与我们联系**</span>。

gradio_app.py → app.py

@@ -9,8 +9,8 @@ if __name__ == "__main__":
 
 import fire
 import gradio as gr
-from app.gradio_3dgen import create_ui as create_3d_ui
-from app.all_models import model_zoo
+from gradio_app.gradio_3dgen import create_ui as create_3d_ui
+from gradio_app.all_models import model_zoo
 
 
 _TITLE = '''Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image'''

{app → gradio_app}/custom_models/mvimg_prediction.py

@@ -4,8 +4,8 @@ import gradio as gr
 from PIL import Image
 import numpy as np
 from rembg import remove
-from app.utils import change_rgba_bg, rgba_to_rgb
-from app.custom_models.utils import load_pipeline
+from gradio_app.utils import change_rgba_bg, rgba_to_rgb
+from gradio_app.custom_models.utils import load_pipeline
 from scripts.all_typing import *
 from scripts.utils import session, simple_preprocess
 

{app → gradio_app}/custom_models/normal_prediction.py

@@ -1,7 +1,7 @@
 import sys
 from PIL import Image
-from app.utils import rgba_to_rgb, simple_remove
-from app.custom_models.utils import load_pipeline
+from gradio_app.utils import rgba_to_rgb, simple_remove
+from gradio_app.custom_models.utils import load_pipeline
 from scripts.utils import rotate_normals_torch
 from scripts.all_typing import *
 

{app → gradio_app}/custom_models/utils.py

@@ -1,7 +1,7 @@
 import torch
 from typing import List
 from dataclasses import dataclass
-from app.utils import rgba_to_rgb
+from gradio_app.utils import rgba_to_rgb
 from custum_3d_diffusion.trainings.config_classes import ExprimentConfig, TrainerSubConfig
 from custum_3d_diffusion import modules
 from custum_3d_diffusion.custum_modules.unifield_processor import AttnConfig, ConfigurableUNet2DConditionModel
@@ -24,7 +24,7 @@ def init_trainers(cfg_path: str, weight_dtype: torch.dtype, extras: dict):
     trainers: List[BasicTrainer] = [modules.find(trainer.trainer_type)(accelerator, None, configurable_unet, trainer.trainer, weight_dtype, i) for i, trainer in enumerate(trainer_cfgs)]
     return trainers, configurable_unet
 
-from app.utils import make_image_grid, split_image
+from gradio_app.utils import make_image_grid, split_image
 def process_image(function, img, guidance_scale=2., merged_image=False, remove_bg=True):
     from rembg import remove
     if remove_bg:

{app → gradio_app}/gradio_3dgen.py

@@ -2,9 +2,9 @@ import os
 import gradio as gr
 from PIL import Image
 from pytorch3d.structures import Meshes
-from app.utils import clean_up
-from app.custom_models.mvimg_prediction import run_mvprediction
-from app.custom_models.normal_prediction import predict_normals
+from gradio_app.utils import clean_up
+from gradio_app.custom_models.mvimg_prediction import run_mvprediction
+from gradio_app.custom_models.normal_prediction import predict_normals
 from scripts.refine_lr_to_sr import run_sr_fast
 from scripts.utils import save_glb_and_video
 from scripts.multiview_inference import geo_reconstruct

{app → gradio_app}/gradio_3dgen_steps.py

@@ -1,8 +1,8 @@
 import gradio as gr
 from PIL import Image
 
-from app.custom_models.mvimg_prediction import run_mvprediction
-from app.utils import make_image_grid, split_image
+from gradio_app.custom_models.mvimg_prediction import run_mvprediction
+from gradio_app.utils import make_image_grid, split_image
 from scripts.utils import save_glb_and_video
 
 def concept_to_multiview(preview_img, input_processing, seed, guidance=1.):
@@ -40,7 +40,7 @@ def concept_to_multiview_ui(concurrency_id="wkl"):
     )
     return output_rgb, output_front
 
-from app.custom_models.normal_prediction import predict_normals
+from gradio_app.custom_models.normal_prediction import predict_normals
 from scripts.multiview_inference import geo_reconstruct
 def multiview_to_mesh_v2(rgb_pil, normal_pil, front_pil, do_refine=False, expansion_weight=0.1, init_type="std"):
     rgb_pils = split_image(rgb_pil, rows=2)

{app → gradio_app}/gradio_local.py

@@ -17,9 +17,9 @@ if __name__ == "__main__":
 import gradio as gr
 import argparse
 
-from app.gradio_3dgen import create_ui as create_3d_ui
+from gradio_app.gradio_3dgen import create_ui as create_3d_ui
 # from app.gradio_3dgen_steps import create_step_ui
-from app.all_models import model_zoo
+from gradio_app.all_models import model_zoo
 
 
 _TITLE = '''Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image'''

scripts/multiview_inference.py

@@ -4,8 +4,8 @@ from scripts.mesh_init import build_mesh, calc_w_over_h, fix_border_with_pymeshl
 from scripts.project_mesh import multiview_color_projection
 from scripts.refine_lr_to_sr import run_sr_fast
 from scripts.utils import simple_clean_mesh
-from app.utils import simple_remove, split_image
-from app.custom_models.normal_prediction import predict_normals
+from gradio_app.utils import simple_remove, split_image
+from gradio_app.custom_models.normal_prediction import predict_normals
 from mesh_reconstruction.recon import reconstruct_stage1
 from mesh_reconstruction.refine import run_mesh_refine
 from scripts.project_mesh import get_cameras_list
@@ -36,9 +36,9 @@ def fast_geo(front_normal: Image.Image, back_normal: Image.Image, side_normal: I
 def refine_rgb(rgb_pils, front_pil):
     from scripts.refine_lr_to_sr import refine_lr_with_sd
     from scripts.utils import NEG_PROMPT
-    from app.utils import make_image_grid
-    from app.all_models import model_zoo
-    from app.utils import rgba_to_rgb
+    from gradio_app.utils import make_image_grid
+    from gradio_app.all_models import model_zoo
+    from gradio_app.utils import rgba_to_rgb
     rgb_pil = make_image_grid(rgb_pils, rows=2)
     prompt = "4views, multiview"
     neg_prompt = NEG_PROMPT