YAN Wenkun
YAN Wenkun
Hi, When I design my late-game sub, I set all items to masterwork quality (if possible), to reduce heavy labor of carrying-over all items from old sub to new sub....
### 1. Use LZMA2 algorithm for 7zip compression: LZMA2 is a variant of LZMA, it uses significantly more RAM, and ~70% faster (trade space for time). [My test](https://github.com/YanWenKun/ComfyUI/actions/workflows/windows_release_package.yml) result: ```...
As described in the [PyTorch Scatter's doc](https://github.com/rusty1s/pytorch_scatter?tab=readme-ov-file#binaries), instead of compile-install, we can install its official binaries: ``` python3 -m pip install \ torch-scatter --find-links https://data.pyg.org/whl/torch-2.2.2+cu121.html ``` I guess maybe we...
With table code: ``` [cols=2] |=== |1 |2 |3 |4 |5 |=== ``` Would expect: | 1 | 2 | |--|--| | 3 | 4 | | 5 || But...
 Link: **https://github.com/YanWenKun/Comfy3D-WinPortable** Recently I've been working on this project. Please give me feed back if it works for you (or not). I'm planning to make the PyTorch 2.4 +...