nodes/MrForExample-ComfyUI-3D-Pack
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
MrForExample
2024-01-22 22:00:36 +01:00
parent 39d3b15e16
commit 553416ac15
1 changed files with 27 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+27 -22
View File
@@ -14,7 +14,7 @@ ps: I'll show some generated result soon
- I tried install this package with ComfyUI embed python env first, but I can't find a way to build CUDA related libraries, e.g. diff-gaussian-rasterization, nvdiffrast, simple-knn.
- Torch version: 2.1.2+cu121/V.2.1.2+cu118
### Install:
## Install:
Assume you have already downloaded [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
@@ -41,27 +41,28 @@ cd C:\Users\reall\Softwares\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyU
install.bat
```
Just in case `install.bat` may not working in your PC, you could also run the following commands under this package's root directory:
```bash
# First make sure the Conda env: python_miniconda_env\ComfyUI is activated, then go to Go to ComfyUI Root Directory\ComfyUI\custom_nodes\ComfyUI-3D-Pack and:
pip install -r requirements.txt
- ***Install Plan B:***
git clone --recursive https://github.com/ashawkey/diff-gaussian-rasterization
pip install ./diff-gaussian-rasterization
Just in case `install.bat` may not working in your PC, you could also run the following commands under this package's root directory:
pip install ./simple-knn
```bash
# First make sure the Conda env: python_miniconda_env\ComfyUI is activated, then go to Go to ComfyUI Root Directory\ComfyUI\custom_nodes\ComfyUI-3D-Pack and:
pip install -r requirements.txt
git clone --recursive https://github.com/NVlabs/nvdiffrast/`
pip install ./nvdiffrast
```
git clone --recursive https://github.com/ashawkey/diff-gaussian-rasterization
pip install ./diff-gaussian-rasterization
### Run:
pip install ./simple-knn
git clone --recursive https://github.com/NVlabs/nvdiffrast/`
pip install ./nvdiffrast
```
## Run:
Copy the files inside folder [__New_ComfyUI_Bats](./_New_ComfyUI_Bats/) to your ComfyUI root directory, and double click run_nvidia_gpu_miniconda.bat to start ComfyUI!
- Alternatively you can just activate the Conda env: python_miniconda_env\ComfyUI, and go to your ComfyUI root directory then run command `python ./ComfyUI/main.py`
---
### Currently support:
## Currently support:
- For use case please check [example workflows](./_Example_Workflows/)
- **Note:** you need to put [Example Inputs Files & Folders](_Example_Workflows/_Example_Inputs_Files/) under ComfyUI Root Directory\ComfyUI\input folder before you can run the example workflow
- Stack Orbit Camera Poses node to automatically generate all range of camera pose combinations
@@ -88,15 +89,19 @@ Copy the files inside folder [__New_ComfyUI_Bats](./_New_ComfyUI_Bats/) to your
- Allow convert 3DGS .ply file to 3D mesh <br>
*Note: I didn't spent time to turn the hyperprameters yet, the result will be improved in the future!*
### To-Do Next:
- Add interactive 3D UI inside ComfuUI to visulaize training and generated results for 3D representations
- ~~Add DMTet algorithm to allow convertion from points cloud(Gaussian/.ply) to mesh (.obj, .ply, .glb)~~
- Improve DMTet result & add support to training it with images(RGB, Alpha, Normal Map)
- Add a general SDS/VSD Optimization algorithm to allow training 3D representations with diffusion model, *The real fun begins here* ;)
- Add a few best Nerf algorithms (No idea yet, [instant-ngp](https://github.com/NVlabs/instant-ngp) maybe?)
## Roadmap:
- [x] Add DMTet algorithm to allow convertion from points cloud(Gaussian/.ply) to mesh (.obj, .ply, .glb)
- [ ] Integrate [Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers](https://github.com/VAST-AI-Research/TriplaneGaussian)
- [ ] Add interactive 3D UI inside ComfuUI to visulaize training and generated results for 3D representations
- [ ] Improve DMTet result & add support to training it with images(RGB, Alpha, Normal Map)
- [ ] Add a general SDS/VSD Optimization algorithm to allow training 3D representations with diffusion model, *The real fun begins here* ;)
- [ ] Add a few best Nerf algorithms (No idea yet, [instant-ngp](https://github.com/NVlabs/instant-ngp) maybe?)
---
## Tips
* The world & camera coordinate system is the same as OpenGL: