Skip to content

GitLab

Commit 63bde97a authored by chenpangpang's avatar chenpangpang
Browse files

feat: 初始提交

parent 9cf8c6f1
Pipeline #1475 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 1093 additions and 0 deletions
Dockerfile 0 → 100644
View file @ 63bde97a
FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.2.0-python3.10-cuda12.1-ubuntu22.04 as base
ARG IMAGE=instantmesh
ARG IMAGE_UPPER=InstantMesh
ARG BRANCH=gpu
RUN cd /root && git clone -b $BRANCH http://developer.hpccube.com/codes/chenpangpang/$IMAGE.git
WORKDIR /root/$IMAGE/$IMAGE_UPPER
RUN pip install Ninja xformers triton
RUN pip install -r requirements.txt
#########
# Prod #
#########
FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.2.0-python3.10-cuda12.1-ubuntu22.04
ARG IMAGE=instantmesh
ARG IMAGE_UPPER=InstantMesh
COPY chenyh/$IMAGE/frpc_linux_amd64_v0.2 /opt/conda/lib/python3.10/site-packages/gradio/
RUN chmod +x /opt/conda/lib/python3.10/site-packages/gradio/frpc_linux_amd64_v0.2
COPY chenyh/$IMAGE/sudo-ai/zero123plus-v1.2 /root/$IMAGE_UPPER/sudo-ai/zero123plus-v1.2
COPY chenyh/$IMAGE/TencentARC/InstantMesh /root/$IMAGE_UPPER/TencentARC/InstantMesh
COPY --from=base /opt/conda/lib/python3.10/site-packages /opt/conda/lib/python3.10/site-packages
COPY --from=base /root/$IMAGE/$IMAGE_UPPER /root/$IMAGE_UPPER
COPY --from=base /root/$IMAGE/启动器.ipynb /root/$IMAGE/start.sh /root/
InstantMesh/LICENSE 0 → 100644
View file @ 63bde97a
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
InstantMesh/README.md 0 → 100644
View file @ 63bde97a
<div align="center">
# InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
<a href="https://arxiv.org/abs/2404.07191"><img src="https://img.shields.io/badge/ArXiv-2404.07191-brightgreen"></a>
<a href="https://huggingface.co/TencentARC/InstantMesh"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Model_Card-Huggingface-orange"></a>
<a href="https://huggingface.co/spaces/TencentARC/InstantMesh"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Gradio%20Demo-Huggingface-orange"></a> <br>
<a href="https://replicate.com/camenduru/instantmesh"><img src="https://img.shields.io/badge/Demo-Replicate-blue"></a>
<a href="https://colab.research.google.com/github/camenduru/InstantMesh-jupyter/blob/main/InstantMesh_jupyter.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>
<a href="https://github.com/jtydhr88/ComfyUI-InstantMesh"><img src="https://img.shields.io/badge/Demo-ComfyUI-8A2BE2"></a>
</div>
---
This repo is the official implementation of InstantMesh, a feed-forward framework for efficient 3D mesh generation from a single image based on the LRM/Instant3D architecture.
https://github.com/TencentARC/InstantMesh/assets/20635237/dab3511e-e7c6-4c0b-bab7-15772045c47d
# 🚩 Features and Todo List
- [x] 🔥🔥 Release Zero123++ fine-tuning code.
- [x] 🔥🔥 Support for running gradio demo on two GPUs to save memory.
- [x] 🔥🔥 Support for running demo with docker. Please refer to the [docker](docker/) directory.
- [x] Release inference and training code.
- [x] Release model weights.
- [x] Release huggingface gradio demo. Please try it at [demo](https://huggingface.co/spaces/TencentARC/InstantMesh) link.
- [ ] Add support for more multi-view diffusion models.
# ⚙️ Dependencies and Installation
We recommend using `Python>=3.10`, `PyTorch>=2.1.0`, and `CUDA>=12.1`.
```bash
conda create --name instantmesh python=3.10
conda activate instantmesh
pip install -U pip
# Ensure Ninja is installed
conda install Ninja
# Install the correct version of CUDA
conda install cuda -c nvidia/label/cuda-12.1.0
# Install PyTorch and xformers
# You may need to install another xformers version if you use a different PyTorch version
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
pip install xformers==0.0.22.post7
# For Linux users: Install Triton
pip install triton
# For Windows users: Use the prebuilt version of Triton provided here:
pip install https://huggingface.co/r4ziel/xformers_pre_built/resolve/main/triton-2.0.0-cp310-cp310-win_amd64.whl
# Install other requirements
pip install -r requirements.txt
```
# 💫 How to Use
## Download the models
We provide 4 sparse-view reconstruction model variants and a customized Zero123++ UNet for white-background image generation in the [model card](https://huggingface.co/TencentARC/InstantMesh).
Our inference script will download the models automatically. Alternatively, you can manually download the models and put them under the `ckpts/` directory.
By default, we use the `instant-mesh-large` reconstruction model variant.
## Start a local gradio demo
To start a gradio demo in your local machine, simply run:
```bash
python app.py
```
If you have multiple GPUs in your machine, the demo app will run on two GPUs automatically to save memory. You can also force it to run on a single GPU:
```bash
CUDA_VISIBLE_DEVICES=0 python app.py
```
Alternatively, you can run the demo with docker. Please follow the instructions in the [docker](docker/) directory.
## Running with command line
To generate 3D meshes from images via command line, simply run:
```bash
python run.py configs/instant-mesh-large.yaml examples/hatsune_miku.png --save_video
```
We use [rembg](https://github.com/danielgatis/rembg) to segment the foreground object. If the input image already has an alpha mask, please specify the `no_rembg` flag:
```bash
python run.py configs/instant-mesh-large.yaml examples/hatsune_miku.png --save_video --no_rembg
```
By default, our script exports a `.obj` mesh with vertex colors, please specify the `--export_texmap` flag if you hope to export a mesh with a texture map instead (this will cost longer time):
```bash
python run.py configs/instant-mesh-large.yaml examples/hatsune_miku.png --save_video --export_texmap
```
Please use a different `.yaml` config file in the [configs](./configs) directory if you hope to use other reconstruction model variants. For example, using the `instant-nerf-large` model for generation:
```bash
python run.py configs/instant-nerf-large.yaml examples/hatsune_miku.png --save_video
```
**Note:** When using the `NeRF` model variants for image-to-3D generation, exporting a mesh with texture map by specifying `--export_texmap` may cost long time in the UV unwarping step since the default iso-surface extraction resolution is `256`. You can set a lower iso-surface extraction resolution in the config file.
# 💻 Training
We provide our training code to facilitate future research. But we cannot provide the training dataset due to its size. Please refer to our [dataloader](src/data/objaverse.py) for more details.
To train the sparse-view reconstruction models, please run:
```bash
# Training on NeRF representation
python train.py --base configs/instant-nerf-large-train.yaml --gpus 0,1,2,3,4,5,6,7 --num_nodes 1
# Training on Mesh representation
python train.py --base configs/instant-mesh-large-train.yaml --gpus 0,1,2,3,4,5,6,7 --num_nodes 1
```
We also provide our Zero123++ fine-tuning code since it is frequently requested. The running command is:
```bash
python train.py --base configs/zero123plus-finetune.yaml --gpus 0,1,2,3,4,5,6,7 --num_nodes 1
```
# :books: Citation
If you find our work useful for your research or applications, please cite using this BibTeX:
```BibTeX
@article{xu2024instantmesh,
title={InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models},
author={Xu, Jiale and Cheng, Weihao and Gao, Yiming and Wang, Xintao and Gao, Shenghua and Shan, Ying},
journal={arXiv preprint arXiv:2404.07191},
year={2024}
}
```
# 🤗 Acknowledgements
We thank the authors of the following projects for their excellent contributions to 3D generative AI!
- [Zero123++](https://github.com/SUDO-AI-3D/zero123plus)
- [OpenLRM](https://github.com/3DTopia/OpenLRM)
- [FlexiCubes](https://github.com/nv-tlabs/FlexiCubes)
- [Instant3D](https://instant-3d.github.io/)
Thank [@camenduru](https://github.com/camenduru) for implementing [Replicate Demo](https://replicate.com/camenduru/instantmesh) and [Colab Demo](https://colab.research.google.com/github/camenduru/InstantMesh-jupyter/blob/main/InstantMesh_jupyter.ipynb)!
Thank [@jtydhr88](https://github.com/jtydhr88) for implementing [ComfyUI support](https://github.com/jtydhr88/ComfyUI-InstantMesh)!
InstantMesh/app.py 0 → 100644
View file @ 63bde97a
import os
import imageio
import numpy as np
import torch
import rembg
from PIL import Image
from torchvision.transforms import v2
from pytorch_lightning import seed_everything
from omegaconf import OmegaConf
from einops import rearrange, repeat
from tqdm import tqdm
from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler
from src.utils.train_util import instantiate_from_config
from src.utils.camera_util import (
FOV_to_intrinsics,
get_zero123plus_input_cameras,
get_circular_camera_poses,
)
from src.utils.mesh_util import save_obj, save_glb
from src.utils.infer_util import remove_background, resize_foreground, images_to_video
import tempfile
if torch.cuda.is_available() and torch.cuda.device_count() >= 2:
device0 = torch.device('cuda:0')
device1 = torch.device('cuda:1')
else:
device0 = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
device1 = device0
def get_render_cameras(batch_size=1, M=120, radius=2.5, elevation=10.0, is_flexicubes=False):
"""
Get the rendering camera parameters.
"""
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(30.0).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 images_to_video(images, output_path, fps=30):
# images: (N, C, H, W)
os.makedirs(os.path.dirname(output_path), exist_ok=True)
frames = []
for i in range(images.shape[0]):
frame = (images[i].permute(1, 2, 0).cpu().numpy() * 255).astype(np.uint8).clip(0, 255)
assert frame.shape[0] == images.shape[2] and frame.shape[1] == images.shape[3], \
f"Frame shape mismatch: {frame.shape} vs {images.shape}"
assert frame.min() >= 0 and frame.max() <= 255, \
f"Frame value out of range: {frame.min()} ~ {frame.max()}"
frames.append(frame)
imageio.mimwrite(output_path, np.stack(frames), fps=fps, codec='h264')
###############################################################################
# Configuration.
###############################################################################
seed_everything(0)
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 = True if config_name.startswith('instant-mesh') else False
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'
)
# load custom white-background UNet
unet_ckpt_path = "TencentARC/InstantMesh/diffusion_pytorch_model.bin"
state_dict = torch.load(unet_ckpt_path, map_location='cpu')
pipeline.unet.load_state_dict(state_dict, strict=True)
pipeline = pipeline.to(device0)
# load reconstruction model
print('Loading reconstruction model ...')
model_ckpt_path = "TencentARC/InstantMesh/instant_mesh_large.ckpt"
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(device1)
if IS_FLEXICUBES:
model.init_flexicubes_geometry(device1, fovy=30.0)
model = model.eval()
print('Loading Finished!')
def check_input_image(input_image):
if input_image is None:
raise gr.Error("No image uploaded!")
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
def generate_mvs(input_image, sample_steps, sample_seed):
seed_everything(sample_seed)
# sampling
generator = torch.Generator(device=device0)
z123_image = pipeline(
input_image,
num_inference_steps=sample_steps,
generator=generator,
).images[0]
show_image = np.asarray(z123_image, dtype=np.uint8)
show_image = torch.from_numpy(show_image) # (960, 640, 3)
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
def make_mesh(mesh_fpath, planes):
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():
# get mesh
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
def make3d(images):
images = np.asarray(images, dtype=np.float32) / 255.0
images = torch.from_numpy(images).permute(2, 0, 1).contiguous().float() # (3, 960, 640)
images = rearrange(images, 'c (n h) (m w) -> (n m) c h w', n=3, m=2) # (6, 3, 320, 320)
input_cameras = get_zero123plus_input_cameras(batch_size=1, radius=4.0).to(device1)
render_cameras = get_render_cameras(
batch_size=1, radius=4.5, elevation=20.0, is_flexicubes=IS_FLEXICUBES).to(device1)
images = images.unsqueeze(0).to(device1)
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)
video_fpath = os.path.join(mesh_dirname, f"{mesh_basename}.mp4")
with torch.no_grad():
# get triplane
planes = model.forward_planes(images, input_cameras)
# get video
chunk_size = 20 if IS_FLEXICUBES else 1
render_size = 384
frames = []
for i in tqdm(range(0, render_cameras.shape[1], chunk_size)):
if IS_FLEXICUBES:
frame = model.forward_geometry(
planes,
render_cameras[:, i:i + chunk_size],
render_size=render_size,
)['img']
else:
frame = model.synthesizer(
planes,
cameras=render_cameras[:, i:i + chunk_size],
render_size=render_size,
)['images_rgb']
frames.append(frame)
frames = torch.cat(frames, dim=1)
images_to_video(
frames[0],
video_fpath,
fps=30,
)
print(f"Video saved to {video_fpath}")
mesh_fpath, mesh_glb_fpath = make_mesh(mesh_fpath, planes)
return video_fpath, mesh_fpath, mesh_glb_fpath
import gradio as gr
_HEADER_ = '''
<h2><b>Official 🤗 Gradio Demo</b></h2><h2><a href='https://github.com/TencentARC/InstantMesh' target='_blank'><b>InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models</b></a></h2>
**InstantMesh** is a feed-forward framework for efficient 3D mesh generation from a single image based on the LRM/Instant3D architecture.
Code: <a href='https://github.com/TencentARC/InstantMesh' target='_blank'>GitHub</a>. Techenical report: <a href='https://arxiv.org/abs/2404.07191' target='_blank'>ArXiv</a>.
❗️❗️❗️**Important Notes:**
- Our demo can export a .obj mesh with vertex colors or a .glb mesh now. If you prefer to export a .obj mesh with a **texture map**, please refer to our <a href='https://github.com/TencentARC/InstantMesh?tab=readme-ov-file#running-with-command-line' target='_blank'>Github Repo</a>.
- The 3D mesh generation results highly depend on the quality of generated multi-view images. Please try a different **seed value** if the result is unsatisfying (Default: 42).
'''
_CITE_ = r"""
If InstantMesh is helpful, please help to ⭐ the <a href='https://github.com/TencentARC/InstantMesh' target='_blank'>Github Repo</a>. Thanks! [![GitHub Stars](https://img.shields.io/github/stars/TencentARC/InstantMesh?style=social)](https://github.com/TencentARC/InstantMesh)
---
📝 **Citation**
If you find our work useful for your research or applications, please cite using this bibtex:
```bibtex
@article{xu2024instantmesh,
title={InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models},
author={Xu, Jiale and Cheng, Weihao and Gao, Yiming and Wang, Xintao and Gao, Shenghua and Shan, Ying},
journal={arXiv preprint arXiv:2404.07191},
year={2024}
}
```
📋 **License**
Apache-2.0 LICENSE. Please refer to the [LICENSE file](https://huggingface.co/spaces/TencentARC/InstantMesh/blob/main/LICENSE) for details.
📧 **Contact**
If you have any questions, feel free to open a discussion or contact us at <b>bluestyle928@gmail.com</b>.
"""
with gr.Blocks() as demo:
gr.Markdown(_HEADER_)
with gr.Row(variant="panel"):
with gr.Column():
with gr.Row():
input_image = gr.Image(
label="Input Image",
image_mode="RGBA",
sources="upload",
width=256,
height=256,
type="pil",
elem_id="content_image",
)
processed_image = gr.Image(
label="Processed Image",
image_mode="RGBA",
width=256,
height=256,
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",
examples_per_page=20
)
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.Column():
output_video = gr.Video(
label="video", format="mp4",
width=379,
autoplay=True,
interactive=False
)
with gr.Row():
with gr.Tab("OBJ"):
output_model_obj = gr.Model3D(
label="Output Model (OBJ Format)",
# width=768,
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)",
# width=768,
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).''')
gr.Markdown(_CITE_)
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_video, output_model_obj, output_model_glb]
)
demo.queue(max_size=10)
demo.launch(server_name="0.0.0.0", share=True)
InstantMesh/configs/instant-mesh-base.yaml 0 → 100644
View file @ 63bde97a
model_config:
target: src.models.lrm_mesh.InstantMesh
params:
encoder_feat_dim: 768
encoder_freeze: false
encoder_model_name: facebook/dino-vitb16
transformer_dim: 1024
transformer_layers: 12
transformer_heads: 16
triplane_low_res: 32
triplane_high_res: 64
triplane_dim: 40
rendering_samples_per_ray: 96
grid_res: 128
grid_scale: 2.1
infer_config:
unet_path: ckpts/diffusion_pytorch_model.bin
model_path: ckpts/instant_mesh_base.ckpt
texture_resolution: 1024
render_resolution: 512
\ No newline at end of file
InstantMesh/configs/instant-mesh-large-train.yaml 0 → 100644
View file @ 63bde97a
model:
base_learning_rate: 4.0e-05
target: src.model_mesh.MVRecon
params:
init_ckpt: logs/instant-nerf-large-train/checkpoints/last.ckpt
input_size: 320
render_size: 512
lrm_generator_config:
target: src.models.lrm_mesh.InstantMesh
params:
encoder_feat_dim: 768
encoder_freeze: false
encoder_model_name: facebook/dino-vitb16
transformer_dim: 1024
transformer_layers: 16
transformer_heads: 16
triplane_low_res: 32
triplane_high_res: 64
triplane_dim: 80
rendering_samples_per_ray: 128
grid_res: 128
grid_scale: 2.1
data:
target: src.data.objaverse.DataModuleFromConfig
params:
batch_size: 2
num_workers: 8
train:
target: src.data.objaverse.ObjaverseData
params:
root_dir: data/objaverse
meta_fname: filtered_obj_name.json
input_image_dir: rendering_random_32views
target_image_dir: rendering_random_32views
input_view_num: 6
target_view_num: 4
total_view_n: 32
fov: 50
camera_rotation: true
validation: false
validation:
target: src.data.objaverse.ValidationData
params:
root_dir: data/valid_samples
input_view_num: 6
input_image_size: 320
fov: 30
lightning:
modelcheckpoint:
params:
every_n_train_steps: 2000
save_top_k: -1
save_last: true
callbacks: {}
trainer:
benchmark: true
max_epochs: -1
val_check_interval: 1000
num_sanity_val_steps: 0
accumulate_grad_batches: 1
check_val_every_n_epoch: null # if not set this, validation does not run
InstantMesh/configs/instant-mesh-large.yaml 0 → 100644
View file @ 63bde97a
model_config:
target: src.models.lrm_mesh.InstantMesh
params:
encoder_feat_dim: 768
encoder_freeze: false
encoder_model_name: facebook/dino-vitb16
transformer_dim: 1024
transformer_layers: 16
transformer_heads: 16
triplane_low_res: 32
triplane_high_res: 64
triplane_dim: 80
rendering_samples_per_ray: 128
grid_res: 128
grid_scale: 2.1
infer_config:
unet_path: ckpts/diffusion_pytorch_model.bin
model_path: ckpts/instant_mesh_large.ckpt
texture_resolution: 1024
render_resolution: 512
\ No newline at end of file
InstantMesh/configs/instant-nerf-base.yaml 0 → 100644
View file @ 63bde97a
model_config:
target: src.models.lrm.InstantNeRF
params:
encoder_feat_dim: 768
encoder_freeze: false
encoder_model_name: facebook/dino-vitb16
transformer_dim: 1024
transformer_layers: 12
transformer_heads: 16
triplane_low_res: 32
triplane_high_res: 64
triplane_dim: 40
rendering_samples_per_ray: 96
infer_config:
unet_path: ckpts/diffusion_pytorch_model.bin
model_path: ckpts/instant_nerf_base.ckpt
mesh_threshold: 10.0
mesh_resolution: 256
render_resolution: 384
\ No newline at end of file
InstantMesh/configs/instant-nerf-large-train.yaml 0 → 100644
View file @ 63bde97a
model:
base_learning_rate: 4.0e-04
target: src.model.MVRecon
params:
input_size: 320
render_size: 192
lrm_generator_config:
target: src.models.lrm.InstantNeRF
params:
encoder_feat_dim: 768
encoder_freeze: false
encoder_model_name: facebook/dino-vitb16
transformer_dim: 1024
transformer_layers: 16
transformer_heads: 16
triplane_low_res: 32
triplane_high_res: 64
triplane_dim: 80
rendering_samples_per_ray: 128
data:
target: src.data.objaverse.DataModuleFromConfig
params:
batch_size: 2
num_workers: 8
train:
target: src.data.objaverse.ObjaverseData
params:
root_dir: data/objaverse
meta_fname: filtered_obj_name.json
input_image_dir: rendering_random_32views
target_image_dir: rendering_random_32views
input_view_num: 6
target_view_num: 4
total_view_n: 32
fov: 50
camera_rotation: true
validation: false
validation:
target: src.data.objaverse.ValidationData
params:
root_dir: data/valid_samples
input_view_num: 6
input_image_size: 320
fov: 30
lightning:
modelcheckpoint:
params:
every_n_train_steps: 1000
save_top_k: -1
save_last: true
callbacks: {}
trainer:
benchmark: true
max_epochs: -1
gradient_clip_val: 1.0
val_check_interval: 1000
num_sanity_val_steps: 0
accumulate_grad_batches: 1
check_val_every_n_epoch: null # if not set this, validation does not run
InstantMesh/configs/instant-nerf-large.yaml 0 → 100644
View file @ 63bde97a
model_config:
target: src.models.lrm.InstantNeRF
params:
encoder_feat_dim: 768
encoder_freeze: false
encoder_model_name: facebook/dino-vitb16
transformer_dim: 1024
transformer_layers: 16
transformer_heads: 16
triplane_low_res: 32
triplane_high_res: 64
triplane_dim: 80
rendering_samples_per_ray: 128
infer_config:
unet_path: ckpts/diffusion_pytorch_model.bin
model_path: ckpts/instant_nerf_large.ckpt
mesh_threshold: 10.0
mesh_resolution: 256
render_resolution: 384
\ No newline at end of file
InstantMesh/configs/zero123plus-finetune.yaml 0 → 100644
View file @ 63bde97a
model:
base_learning_rate: 1.0e-05
target: zero123plus.model.MVDiffusion
params:
drop_cond_prob: 0.1
stable_diffusion_config:
pretrained_model_name_or_path: sudo-ai/zero123plus-v1.2
custom_pipeline: ./zero123plus
data:
target: src.data.objaverse_zero123plus.DataModuleFromConfig
params:
batch_size: 6
num_workers: 8
train:
target: src.data.objaverse_zero123plus.ObjaverseData
params:
root_dir: data/objaverse
meta_fname: lvis-annotations.json
image_dir: rendering_zero123plus
validation: false
validation:
target: src.data.objaverse_zero123plus.ObjaverseData
params:
root_dir: data/objaverse
meta_fname: lvis-annotations.json
image_dir: rendering_zero123plus
validation: true
lightning:
modelcheckpoint:
params:
every_n_train_steps: 1000
save_top_k: -1
save_last: true
callbacks: {}
trainer:
benchmark: true
max_epochs: -1
gradient_clip_val: 1.0
val_check_interval: 1000
num_sanity_val_steps: 0
accumulate_grad_batches: 1
check_val_every_n_epoch: null # if not set this, validation does not run
InstantMesh/docker/Dockerfile 0 → 100644
View file @ 63bde97a
# get the development image from nvidia cuda 12.1
FROM nvidia/cuda:12.4.1-runtime-ubuntu22.04
LABEL name="instantmesh" maintainer="instantmesh"
# Add a volume for downloaded models
VOLUME /workspace/models
# create workspace folder and set it as working directory
RUN mkdir -p /workspace/instantmesh
WORKDIR /workspace
# Set the timezone
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \
apt-get install -y tzdata && \
ln -fs /usr/share/zoneinfo/America/Chicago /etc/localtime && \
dpkg-reconfigure --frontend noninteractive tzdata
# update package lists and install git, wget, vim, libegl1-mesa-dev, and libglib2.0-0
RUN apt-get update && \
apt-get install -y build-essential git wget vim libegl1-mesa-dev libglib2.0-0 unzip
# install conda
RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh && \
chmod +x Miniconda3-latest-Linux-x86_64.sh && \
./Miniconda3-latest-Linux-x86_64.sh -b -p /workspace/miniconda3 && \
rm Miniconda3-latest-Linux-x86_64.sh
# update PATH environment variable
ENV PATH="/workspace/miniconda3/bin:${PATH}"
# initialize conda
RUN conda init bash
# create and activate conda environment
RUN conda create -n instantmesh python=3.10 && echo "source activate instantmesh" > ~/.bashrc
ENV PATH /workspace/miniconda3/envs/instantmesh/bin:$PATH
RUN conda install Ninja
RUN conda install cuda -c nvidia/label/cuda-12.4.1 -y
RUN pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
RUN pip install xformers==0.0.22.post7
RUN pip install triton
# change the working directory to the repository
WORKDIR /workspace/instantmesh
# other dependencies
ADD ./requirements.txt /workspace/instantmesh/requirements.txt
RUN pip install -r requirements.txt
COPY . /workspace/instantmesh
# Run the command when the container starts
CMD ["python", "app.py"]
InstantMesh/docker/README.md 0 → 100644
View file @ 63bde97a
# Docker setup
This docker setup is tested on Ubuntu.
make sure you are under directory `yourworkspace/instantmesh/`
Build docker image:
```bash
docker build -t instantmesh -f docker/Dockerfile .
```
Run docker image with a local model cache (so it is fast when container is started next time):
```bash
mkdir -p $HOME/models/
export MODEL_DIR=$HOME/models/
docker run -it -p 43839:43839 --platform=linux/amd64 --gpus all -v $MODEL_DIR:/workspace/instantmesh/models instantmesh
```
To use specific GPUs:
```bash
docker run -it -p 43839:43839 --platform=linux/amd64 --gpus '"device=0,1"' -v $MODEL_DIR:/workspace/instantmesh/models instantmesh
```
Navigate to `http://localhost:43839` to use the demo.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment