Brostopher

Results 4 comments of Brostopher

After updating to the latest version, flux nf4 becomes very slow

> > GGUF is a lot better, more flexible and will be faster than nf4 once someone ports the llama.cpp cuda kernels. > > Your slowdown however is probably just...

::: | Pytorch Update 2.3.1 | Popup error while loading ComfyUI

The links provided were useful in resolving the pop-up issue and the sluggish ksampler, but I want to avoid sharing incorrect information. https://github.com/facebookresearch/xformers/discussions/717 https://github.com/facebookresearch/xformers/actions/runs/10559887009

MOCHI problem: "model weight dtype torch.bfloat16, manual cast: torch.float32" + "unet unexpected: ['scaled_fp8']" DESPITE USING ALL THE RIGHT MODELS.

https://github.com/kijai/ComfyUI-MochiWrapper Have you tried with these nodes?

Cannot run workflow, Error occurred when executing DeepFuzeAdavance:

I have the same issue but i can get around it. load_video_cv (width, height, fps, duration, total_frames, target_frame_time) = next(gen) I don't have a ton of knowledge but I think...