ℹ️Try Comfy3D-WinPortable if you can't install

[YanWenKun]

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 + CUDA 12.1 build works as intended before releasing the PyTorch 2.5+ CUDA 12.4 build.

Have a nice day!

[MrForExample]

Thanks for making this my friend🤗, I'll add it in Readme, and if more people find it useful, then maybe we can find a way to work together on Comfy3D, cheers 🍻

[YanWenKun]

The new release is out:
https://github.com/YanWenKun/Comfy3D-WinPortable/releases/tag/r6-pt25

It is based on PyTorch 2.5.1, CUDA 12.4, Python 3.12.
It now supports TRELLIS and Hunyuan3D-1.
It now can run most example workflows (except InstantMesh).

Until next time! 🍻

[marcovth]

Is there a video somewhere on how to install Comfy3D-WinPortable?

[igs-kumayu]

WHAT is control_unique3d_sd15_tile.safetensors?
google it , nothing.....

[YanWenKun]

WHAT is control_unique3d_sd15_tile.safetensors? google it , nothing.....

It's here:
https://huggingface.co/spaces/Wuvin/Unique3D/tree/main/ckpt/controlnet-tile

You may need more models listed in the README of 3D-Pack:

• To use the All stage Unique3D workflow, Download Models:
  • sdv1.5-pruned-emaonly and put it into Your ComfyUI root directory/ComfyUI/models/checkpoints
  • fine-tuned controlnet-tile and put it into Your ComfyUI root directory/ComfyUI/models/controlnet
  • ip-adapter_sd15 and put it into Your ComfyUI root directory/ComfyUI/models/ipadapter
  • OpenCLIP-ViT-H-14, rename it to OpenCLIP-ViT-H-14.safetensors and put it into Your ComfyUI root directory/ComfyUI/models/clip_vision
  • RealESRGAN_x4plus and put it into Your ComfyUI root directory/ComfyUI/models/upscale_models
• Model weights: https://huggingface.co/spaces/Wuvin/Unique3D/tree/main/ckpt