search

OpenTexture / Paint3D

[CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model
https://paint3d.github.io/
Apache License 2.0
691 stars 32 forks source link

unable to install dependencies #21

Open forresti opened 4 months ago

forresti commented 4 months ago

On Linux, I am trying to follow your exact recipe with:

conda create -n paint3d python=3.8

conda activate

export CUDA_HOME=/usr/local/cuda-11.6

# following directions from here: https://pytorch.org/get-started/previous-versions/ 
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.6 -c pytorch -c conda-forge

It fails with the following error:

$ conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.6 -c pytorch -c conda-forge
Collecting package metadata (current_repodata.json): \ WARNING conda.models.version:get_matcher(546): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.7.1.*, but conda is ignoring the .* and treating it as 1.7.1
done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Collecting package metadata (repodata.json): / WARNING conda.models.version:get_matcher(546): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.9.0.*, but conda is ignoring the .* and treating it as 1.9.0
WARNING conda.models.version:get_matcher(546): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.8.0.*, but conda is ignoring the .* and treating it as 1.8.0
WARNING conda.models.version:get_matcher(546): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.6.0.*, but conda is ignoring the .* and treating it as 1.6.0
done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Solving environment: done
## Package Plan ##
  environment location: /home/ubuntu/anaconda3/envs/paint3d
  added / updated specs:
    - cudatoolkit=11.6
    - pytorch==1.12.1
    - torchaudio==0.12.1
    - torchvision==0.13.1
The following packages will be downloaded:
    package                    |            build
    ---------------------------|-----------------
    blas-2.122                 |              mkl          14 KB  conda-forge
    blas-devel-3.9.0           |   22_linux64_mkl          14 KB  conda-forge
    brotli-python-1.1.0        |   py38h17151c0_1         343 KB  conda-forge
    certifi-2024.7.4           |     pyhd8ed1ab_0         156 KB  conda-forge
    cudatoolkit-11.6.2         |      hfc3e2af_13       598.8 MB  conda-forge
    gmp-6.3.0                  |       hac33072_2         449 KB  conda-forge
    jpeg-9e                    |       h0b41bf4_3         235 KB  conda-forge
    libblas-3.9.0              |   22_linux64_mkl          15 KB  conda-forge
    libcblas-3.9.0             |   22_linux64_mkl          14 KB  conda-forge
    libgfortran-ng-14.1.0      |       h69a702a_0          49 KB  conda-forge
    libgfortran5-14.1.0        |       hc5f4f2c_0         1.4 MB  conda-forge
    libhwloc-2.11.0            |default_h5622ce7_1000         2.3 MB  conda-forge
    liblapack-3.9.0            |   22_linux64_mkl          14 KB  conda-forge
    liblapacke-3.9.0           |   22_linux64_mkl          14 KB  conda-forge
    libxml2-2.12.7             |       hc051c1a_1         688 KB  conda-forge
    llvm-openmp-18.1.7         |       ha31de31_0        55.9 MB  conda-forge
    mkl-2024.1.0               |     ha957f24_693       121.2 MB  conda-forge
    mkl-devel-2024.1.0         |     ha770c72_693          34 KB  conda-forge
    mkl-include-2024.1.0       |     ha957f24_693         680 KB  conda-forge
    numpy-1.24.4               |   py38h59b608b_0         6.4 MB  conda-forge
    openh264-2.1.1             |       h780b84a_0         1.5 MB  conda-forge
    pillow-9.4.0               |   py38hde6dc18_1        43.8 MB  conda-forge
    python_abi-3.8             |           4_cp38           6 KB  conda-forge
    pytorch-1.12.1             |py3.8_cuda11.6_cudnn8.3.2_0        1.20 GB  pytorch
    tbb-2021.12.0              |       h434a139_2         188 KB  conda-forge
    torchaudio-0.12.1          |       py38_cu116         6.2 MB  pytorch
    torchvision-0.13.1         |       py38_cu116         7.7 MB  pytorch
    typing_extensions-4.12.2   |     pyha770c72_0          39 KB  conda-forge
    urllib3-2.2.2              |     pyhd8ed1ab_0          93 KB  conda-forge
    ------------------------------------------------------------
                                           Total:        2.03 GB
The following NEW packages will be INSTALLED:
  blas               conda-forge/linux-64::blas-2.122-mkl 
  blas-devel         conda-forge/linux-64::blas-devel-3.9.0-22_linux64_mkl 
  brotli-python      conda-forge/linux-64::brotli-python-1.1.0-py38h17151c0_1 
  certifi            conda-forge/noarch::certifi-2024.7.4-pyhd8ed1ab_0 
  charset-normalizer conda-forge/noarch::charset-normalizer-3.3.2-pyhd8ed1ab_0 
  cudatoolkit        conda-forge/linux-64::cudatoolkit-11.6.2-hfc3e2af_13 
  ffmpeg             pytorch/linux-64::ffmpeg-4.3-hf484d3e_0 
  freetype           conda-forge/linux-64::freetype-2.12.1-h267a509_2 
  gmp                conda-forge/linux-64::gmp-6.3.0-hac33072_2 
  gnutls             conda-forge/linux-64::gnutls-3.6.13-h85f3911_1 
  icu                conda-forge/linux-64::icu-73.2-h59595ed_0 
  idna               conda-forge/noarch::idna-3.7-pyhd8ed1ab_0 
  jpeg               conda-forge/linux-64::jpeg-9e-h0b41bf4_3 
  lame               conda-forge/linux-64::lame-3.100-h166bdaf_1003 
  lcms2              conda-forge/linux-64::lcms2-2.15-hfd0df8a_0 
  lerc               conda-forge/linux-64::lerc-4.0.0-h27087fc_0 
  libblas            conda-forge/linux-64::libblas-3.9.0-22_linux64_mkl 
  libcblas           conda-forge/linux-64::libcblas-3.9.0-22_linux64_mkl 
  libdeflate         conda-forge/linux-64::libdeflate-1.17-h0b41bf4_0 
  libgfortran-ng     conda-forge/linux-64::libgfortran-ng-14.1.0-h69a702a_0 
  libgfortran5       conda-forge/linux-64::libgfortran5-14.1.0-hc5f4f2c_0 
  libhwloc           conda-forge/linux-64::libhwloc-2.11.0-default_h5622ce7_1000 
  libiconv           conda-forge/linux-64::libiconv-1.17-hd590300_2 
  liblapack          conda-forge/linux-64::liblapack-3.9.0-22_linux64_mkl 
  liblapacke         conda-forge/linux-64::liblapacke-3.9.0-22_linux64_mkl 
  libpng             conda-forge/linux-64::libpng-1.6.43-h2797004_0 
  libstdcxx-ng       conda-forge/linux-64::libstdcxx-ng-14.1.0-hc0a3c3a_0 
  libtiff            conda-forge/linux-64::libtiff-4.5.0-h6adf6a1_2 
  libwebp-base       conda-forge/linux-64::libwebp-base-1.4.0-hd590300_0 
  libxcb             conda-forge/linux-64::libxcb-1.13-h7f98852_1004 
  libxml2            conda-forge/linux-64::libxml2-2.12.7-hc051c1a_1 
  llvm-openmp        conda-forge/linux-64::llvm-openmp-18.1.7-ha31de31_0 
  mkl                conda-forge/linux-64::mkl-2024.1.0-ha957f24_693 
  mkl-devel          conda-forge/linux-64::mkl-devel-2024.1.0-ha770c72_693 
  mkl-include        conda-forge/linux-64::mkl-include-2024.1.0-ha957f24_693 
  nettle             conda-forge/linux-64::nettle-3.6-he412f7d_0 
  numpy              conda-forge/linux-64::numpy-1.24.4-py38h59b608b_0 
  openh264           conda-forge/linux-64::openh264-2.1.1-h780b84a_0 
  openjpeg           conda-forge/linux-64::openjpeg-2.5.0-hfec8fc6_2 
  pillow             conda-forge/linux-64::pillow-9.4.0-py38hde6dc18_1 
  pthread-stubs      conda-forge/linux-64::pthread-stubs-0.4-h36c2ea0_1001 
  pysocks            conda-forge/noarch::pysocks-1.7.1-pyha2e5f31_6 
  python_abi         conda-forge/linux-64::python_abi-3.8-4_cp38 
  pytorch            pytorch/linux-64::pytorch-1.12.1-py3.8_cuda11.6_cudnn8.3.2_0 
  pytorch-mutex      pytorch/noarch::pytorch-mutex-1.0-cuda 
  requests           conda-forge/noarch::requests-2.32.3-pyhd8ed1ab_0 
  tbb                conda-forge/linux-64::tbb-2021.12.0-h434a139_2 
  torchaudio         pytorch/linux-64::torchaudio-0.12.1-py38_cu116 
  torchvision        pytorch/linux-64::torchvision-0.13.1-py38_cu116 
  typing_extensions  conda-forge/noarch::typing_extensions-4.12.2-pyha770c72_0 
  urllib3            conda-forge/noarch::urllib3-2.2.2-pyhd8ed1ab_0 
  xorg-libxau        conda-forge/linux-64::xorg-libxau-1.0.11-hd590300_0 
  xorg-libxdmcp      conda-forge/linux-64::xorg-libxdmcp-1.1.3-h7f98852_0 
  zlib               conda-forge/linux-64::zlib-1.2.13-h4ab18f5_6 
  zstd               conda-forge/linux-64::zstd-1.5.6-ha6fb4c9_0 
The following packages will be DOWNGRADED:
  _openmp_mutex                                   4.5-2_gnu --> 4.5-2_kmp_llvm 
  libzlib                                  1.3.1-h4ab18f5_1 --> 1.2.13-h4ab18f5_6 
Proceed ([y]/n)? y
Downloading and Extracting Packages

InvalidArchiveError('Error with archive /home/ubuntu/anaconda3/pkgs/llvm-openmp-18.1.7-ha31de31_0.conda.  You probably need to delete and re-download or re-create this file.  Message was:\n\nfailed with error: File is not a zip file')

Any suggestions on this? Or, are there any tips on how to get the right version of pytorch, compiled with the right version of cuda?

mrtpk commented 2 months ago

Try the following. It worked for me.

# update the path and hugging face API key
export WORKSPACE_DIR=/your/workspace/dir
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/

cd $WORKSPACE_DIR/repos
git clone https://github.com/OpenTexture/Paint3D.git
cd $WORKSPACE_DIR/repos/Paint3D/

conda create -y -n paint3d python=3.8.5
conda activate paint3d
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/
pip3 install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu118
pip3 install kaolin==0.14.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-2.0.0_cu118.html
pip3 install albumentations==1.3.0
pip3 install opencv-python==4.6.0.66
pip3 install imageio==2.9.0
pip3 install imageio-ffmpeg==0.4.2
pip3 install pytorch-lightning==1.4.2
pip3 install omegaconf==2.1.1
pip3 install test-tube>=0.7.5
pip3 install streamlit==1.12.1
pip3 install einops==0.3.0
pip3 install transformers==4.27.1
pip3 install webdataset==0.2.5
pip3 install kornia==0.6
pip3 install open_clip_torch==2.0.2
pip3 install invisible-watermark>=0.1.5
pip3 install streamlit-drawable-canvas==0.8.0
pip3 install torchmetrics==0.6.0
pip3 install diffusers==0.25.0
pip3 install accelerate==0.29.2
pip3 install loguru==0.7.2
pip3 install trimesh==3.20.2
pip3 install xatlas==0.0.7
pip3 install "huggingface_hub[cli]"
python3 -c "from huggingface_hub.hf_api import HfFolder; HfFolder.save_token('Your hugging face api key')"

python pipeline_paint3d_stage1.py  --sd_config controlnet/config/depth_based_inpaint_template.yaml  --render_config paint3d/config/train_config_paint3d.py  --mesh_path demo/objs/Suzanne_monkey/Suzanne_monkey.obj  --outdir outputs/stage1
python pipeline_paint3d_stage2.py --sd_config controlnet/config/UV_based_inpaint_template.yaml --render_config paint3d/config/train_config_paint3d.py --mesh_path demo/objs/Suzanne_monkey/Suzanne_monkey.obj --texture_path outputs/stage1/res-0/albedo.png --outdir outputs/stage2
python pipeline_UV_only.py  --sd_config controlnet/config/UV_gen_template.yaml  --render_config paint3d/config/train_config_paint3d.py  --mesh_path demo/objs/teapot/scene.obj  --outdir outputs/test_teapot
python pipeline_paint3d_stage1.py  --sd_config controlnet/config/depth_based_inpaint_template.yaml  --render_config paint3d/config/train_config_paint3d.py  --mesh_path demo/objs/Suzanne_monkey/Suzanne_monkey.obj  --prompt " "  --ip_adapter_image_path demo/objs/Suzanne_monkey/img_prompt.png  --outdir outputs/img_stage1
python pipeline_paint3d_stage2.py --sd_config controlnet/config/UV_based_inpaint_template.yaml --render_config paint3d/config/train_config_paint3d.py --mesh_path demo/objs/Suzanne_monkey/Suzanne_monkey.obj --texture_path outputs/img_stage1/res-0/albedo.png --prompt " "  --ip_adapter_image_path demo/objs/Suzanne_monkey/img_prompt.png --outdir outputs/img_stage2
conda deactivate