Code Monkey home page Code Monkey logo

Comments (14)

0X-JonMichaelGalindo avatar 0X-JonMichaelGalindo commented on July 29, 2024 1

Hi @m-ali-awan I recommend using Miniconda, following the instructions in the readme. venv is bad at resolving version conflicts. Only Miniconda has worked for me.

from comfyui-3d-pack.

MrForExample avatar MrForExample commented on July 29, 2024

Hi friend, no problem, I'll add some description to each examples 👍
I also updated the examples yesterday, feel free to give a try

from comfyui-3d-pack.

salier avatar salier commented on July 29, 2024

Thank you very much. I have successfully run the legend. However, it seems that the model is based on a 256*256 resolution, and the effect is not ideal after changing the resolution. I noticed that many solutions are to create a new model from scratch, so I was wondering if it is possible to modify or refine the existing model by baking displacement and normal maps with Gaussian splash. Specifically, we generate textures, normals and displacement maps from fixed images and bake them to UV. Then we choose to re-bake low-mode or box-selection subdivision to achieve higher detail depending on the purpose. At present, I have achieved the verification stage in Blender (although the process is relatively complex).

from comfyui-3d-pack.

salier avatar salier commented on July 29, 2024

And, I probably don't know how to use it. It's not difficult to simply install dependencies. I haven't seen how to start it, so I may need some features on how to load "Preview 3DGS and 3D Mesh", "Gaussian Splitting Orbit Renderer", "Deep Marching Tetrahedrons", and "Switch Axis for 3DGS&3D Mesh". The functions are listed, but there is no relevant information.

from comfyui-3d-pack.

MrForExample avatar MrForExample commented on July 29, 2024

I was wondering if it is possible to modify or refine the existing model by baking displacement and normal maps with Gaussian splash ..... we generate textures, normals and displacement maps from fixed images and bake them to UV

Baking displacement and normal maps from Gaussian Splatting? Well, I haven't done my research on this yet, but from what I know, there is no easy to do so just yet, but I think you could try using currently available method to convert albedo texture into normal and displacement maps.
And, it is possible to bake high-resolution images onto existing mesh using Bake Multi-View images into UVTexture node, but currently this node only support single UV and single albedo texture for entire mesh. I'll extend it to FBX format and multiple UV & different types of textures in the future, currently I'm focus on ability for this tool to generate good enough initial result.

Document will be updated along with each feature update, cheers friend 👍

from comfyui-3d-pack.

salier avatar salier commented on July 29, 2024

Thank you very much. I use traditional methods such as Marigold depth recognition, which involves recalibrating the depth ruler to uniformly calibrate the depths on both images, and then performing baking replacement.Hope to see more solutions and better results, good luck

from comfyui-3d-pack.

m-ali-awan avatar m-ali-awan commented on July 29, 2024

Hi @salier @MrForExample

C:\Users\Owner\Downloads\StabilityMatrix-win-x64\Data\Packages\ComfyUI>"venv\Scripts\python.exe" -m pip install custom_nodes\ComfyUI-3D-Pack\diff-gaussian-rasterization
Processing c:\users\owner\downloads\stabilitymatrix-win-x64\data\packages\comfyui\custom_nodes\comfyui-3d-pack\diff-gaussian-rasterization
  Preparing metadata (setup.py) ... done
Building wheels for collected packages: diff_gaussian_rasterization
  Building wheel for diff_gaussian_rasterization (setup.py) ... error
  error: subprocess-exited-with-error

  × python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> [9 lines of output]
      running bdist_wheel
      running build
      running build_py
      creating build
      creating build\lib.win32-cpython-310
      creating build\lib.win32-cpython-310\diff_gaussian_rasterization
      copying diff_gaussian_rasterization\__init__.py -> build\lib.win32-cpython-310\diff_gaussian_rasterization
      running build_ext
      error: [WinError 2] The system cannot find the file specified
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for diff_gaussian_rasterization
  Running setup.py clean for diff_gaussian_rasterization
Failed to build diff_gaussian_rasterization
ERROR: Could not build wheels for diff_gaussian_rasterization, which is required to install pyproject.toml-based projects

I am not able to install this library, and have tried everything. Also I thought, maybe it is having problem with c++ build tools, so have tried adding cuda, cl to path etc

But still this error holds.

Kindly help me on this, if you are able to navigate through it..

Thanks

from comfyui-3d-pack.

m-ali-awan avatar m-ali-awan commented on July 29, 2024

Thanks @0X-JonMichaelGalindo ,
I have used miniconda as well, but this issue persists

from comfyui-3d-pack.

m-ali-awan avatar m-ali-awan commented on July 29, 2024

Can you kindly share me your library versions, and system specs..
eg, CUDA version, windows version etc..

from comfyui-3d-pack.

MrForExample avatar MrForExample commented on July 29, 2024

Very likely there is something to do with building tools.
I would try, update the C++ building tools in Visual Studio, I'm using VS2022.
And when using miniconda, try to use it's terminal, and activate the environment first before running install.

from comfyui-3d-pack.

grimbit avatar grimbit commented on July 29, 2024

I have VS2022 and was getting same issues.

Successfully built nvdiffrast kiui Failed to build pointnet2_ops simple_knn diff_gaussian_rasterization pytorch3d torch_scatter ERROR: Could not build wheels for pointnet2_ops, simple_knn, diff_gaussian_rasterization, pytorch3d, torch_scatter, which is required to install pyproject.toml-based projects

Some things build, while others don't.

from comfyui-3d-pack.

nikolaiusa avatar nikolaiusa commented on July 29, 2024

Hi @salier @MrForExample

C:\Users\Owner\Downloads\StabilityMatrix-win-x64\Data\Packages\ComfyUI>"venv\Scripts\python.exe" -m pip install custom_nodes\ComfyUI-3D-Pack\diff-gaussian-rasterization
Processing c:\users\owner\downloads\stabilitymatrix-win-x64\data\packages\comfyui\custom_nodes\comfyui-3d-pack\diff-gaussian-rasterization
  Preparing metadata (setup.py) ... done
Building wheels for collected packages: diff_gaussian_rasterization
  Building wheel for diff_gaussian_rasterization (setup.py) ... error
  error: subprocess-exited-with-error

  × python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> [9 lines of output]
      running bdist_wheel
      running build
      running build_py
      creating build
      creating build\lib.win32-cpython-310
      creating build\lib.win32-cpython-310\diff_gaussian_rasterization
      copying diff_gaussian_rasterization\__init__.py -> build\lib.win32-cpython-310\diff_gaussian_rasterization
      running build_ext
      error: [WinError 2] The system cannot find the file specified
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for diff_gaussian_rasterization
  Running setup.py clean for diff_gaussian_rasterization
Failed to build diff_gaussian_rasterization
ERROR: Could not build wheels for diff_gaussian_rasterization, which is required to install pyproject.toml-based projects

I am not able to install this library, and have tried everything. Also I thought, maybe it is having problem with c++ build tools, so have tried adding cuda, cl to path etc

But still this error holds.

Kindly help me on this, if you are able to navigate through it..

Thanks

do you can to fix the error? I have the same problem

from comfyui-3d-pack.

mothormothormothor avatar mothormothormothor commented on July 29, 2024

I have VS2022 and was getting same issues.

Successfully built nvdiffrast kiui Failed to build pointnet2_ops simple_knn diff_gaussian_rasterization pytorch3d torch_scatter ERROR: Could not build wheels for pointnet2_ops, simple_knn, diff_gaussian_rasterization, pytorch3d, torch_scatter, which is required to install pyproject.toml-based projects

Some things build, while others don't.

Hey there, have you managed to find a solution for this error? I have the same problem.
Cheers

from comfyui-3d-pack.

grimbit avatar grimbit commented on July 29, 2024

I have VS2022 and was getting same issues.
Successfully built nvdiffrast kiui Failed to build pointnet2_ops simple_knn diff_gaussian_rasterization pytorch3d torch_scatter ERROR: Could not build wheels for pointnet2_ops, simple_knn, diff_gaussian_rasterization, pytorch3d, torch_scatter, which is required to install pyproject.toml-based projects
Some things build, while others don't.

Hey there, have you managed to find a solution for this error? I have the same problem. Cheers

Nope. Haven't had time to check.

from comfyui-3d-pack.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.