you

megachad

AI & ML interests

None yet

Recent Activity

Organizations

None yet

megachad's activity

New activity in lmsys/fastchat-t5-3b-v1.0 29 days ago
New activity in HighCWu/FLUX.1-dev-4bit 30 days ago
New activity in HighCWu/FLUX.1-dev-4bit about 1 month ago
New activity in HighCWu/FLUX.1-dev-4bit about 1 month ago

Questions about LoRA

2
#5 opened 3 months ago by
tungdop2
New activity in HighCWu/FLUX.1-dev-4bit about 2 months ago

Quantization scripts

13
#1 opened 5 months ago by
WaveCut
New activity in KingNish/Realtime-FLUX 3 months ago

comfyui implementation?

5
#1 opened 3 months ago by
MayensGuds
replied to victor's post 3 months ago
view reply

Even coders don't use only ComfyUI or only Diffusers. Anyone who is concerned about only such things is just a madman. It is similar to the mouse-keyboard controversy or the GUI/CUI controversy, maybe a little different from the Mac, Windows controversy.

Meh not true. Comfyui is only useful if you're looking to generate manually (mostly porn). How many coders use it to make anything? Is it the defacto backend for image ai now?

Incidentally, coders can convert and use these single files, which are a small exception, and there are some who do so.

Is the what huggingface was always about? Having to convert files?

https://huggingface.co/spaces/nyanko7/flux1-dev-nf4
https://github.com/huggingface/diffusers/issues/9165#issue-2462431761

Yeah two examples out of many... and nobody has agreed on a format or they don't document at all so you're having to figure out a mystery every time.

New activity in p1atdev/FLUX.1-schnell-t5-xxl-quanto 3 months ago

How to inference

1
#2 opened 4 months ago by
zdxpan
replied to victor's post 3 months ago
view reply

I don't use comfyui so I would like to see comfyui models in their own section. I don't want to have to look dig through them for find usable huggingface. Frankly I dont think they belong on this site anyway, as huggingface seems to be more code-oriented. Let civitai have all the non-coders.

Even better, I would like to see models automatically tested to see if they will even run with huggingface code before they are posted.

New activity in coqui/XTTS-v2 4 months ago

Inference (Streaming)

4
#59 opened 7 months ago by
hxrdxk
New activity in HighCWu/FLUX.1-dev-4bit 4 months ago

Img2img works with this

1
#4 opened 4 months ago by
megachad
New activity in black-forest-labs/FLUX.1-dev 4 months ago
New activity in Kijai/flux-fp8 4 months ago