DeXtmL

installation is done with: `pip install numpy pyyaml addict imageio imageio-ffmpeg scikit-image tqdm tensorboardX "pytorch3d>=0.3.0" opencv-python transformers`

I am able to compile the csrc part on Windows but fail to link (Visual Studio) FYI, this is the error message. I'm no expert on cuda, so I'm not...

After some really tedious debugging and tackling various hidden problems, I managed to compile the whole module. This is the end result: [https://github.com/DeXtmL/bitsandbytes-win-prebuilt](https://github.com/DeXtmL/bitsandbytes-win-prebuilt) The binaries are compiled against CUDAToolkit 11.6...

I think this might be related to unclean finish of the previous generation. Some old cuda threads and buffers are still active when you hit the next Generate.

Two things: 1. It's not like i dont care about inpainted mesh; infact it's quite slow and often generates unrecognizable results. So usually , I just choose to render 2.5D...

**"The inpainting is slow yes, the simple mesh is very fast, have you tried that ?"** Yes, I am using the simple mesh. After obtaining the mesh, I have to...

I didn't say this is a perfect fix, but it's indeed a common one, even this RudeWindowFixer cannot fix all the bugs. I think common causes should be pointed out...

Error message: `[InvokeAI]::ERROR --> 1 validation error for LoRALyCORISConfig variant Object has no attribute 'variant' [type=no_such_attribute, input_value=, input_type=ModelVariantType] For further information visit https://errors.pydantic.dev/2.6/v/no_such_attribute`

Please refer to this issue: https://github.com/TimDettmers/bitsandbytes/issues/30#issuecomment-1257229487 If you wish to compile all other versions, the best way is to make a makefile