Falkonar

Results 29 comments of Falkonar

Installation issues

the same...

The download of pytorch_model-00001-of-00003.safetensors got stuck

> > Same happened to me, just download the model manually and then use local path as model in config where it reads **name_or_path** : > > ``` > >...

v2 is released!

Thank you for adding InsightFace Loader. Can you please provide workflow how to use V2 model in ComfyUI? The one you add to commit for v1

Why is the logic for long video generation not entirely consistent with what is described in the paper?

Do you have any tips for this? I have same question about long videos.

cannot import name 'NODE_CLASS_MAPPINGS' from 'ComfyUI-SVD.comfyui_svd

same

[BUG]python3.12 wsl cu124 pip cannot install auto-gptq

maybe it's not working with cu124 and only with 121

The size of tensor a (36) must match the size of tensor b (16) at non-singleton dimension 1

I have the same issue for several days. I have redownload models from different PC . Windows 11 / Linux arch ; 3090 and 5090 ! The results are the...

The size of tensor a (36) must match the size of tensor b (16) at non-singleton dimension 1

> Hi, I'm trying to train a low noise WAN lora local on a 5090 using images > > I'm getting an error on sampling > > RuntimeError: The size...

The size of tensor a (36) must match the size of tensor b (16) at non-singleton dimension 1

> Nice! Did a pull this morning and now its generating sample images again! Thanks for the quick turnaround! (Training up some Wan 2.2 Loras now using it - trying...