Pixart Sigma - Low VRAM & SDXL+ Resolutions in ComfyUI for Free!

Рет қаралды 11,116

2 ай бұрын

Pixart Sigma was released recently, and while the main repo takes a little tweaking to run nicely on 24GB VRAM, ComfyUI comes to the rescue making it easy to run in just 6 GB!
Like with ELLA, T5 encodings replace CLIP leading to increased prompt adherence. Inthis video I show you how to get going for FREE in ComfyUI, and compare SDXL vs Pixart Sigma.
All this without one of those SD3 “no commercial use” licenses!
Want to support the channel? Get workflows and more!
/ nerdyrodent
Links
github.com/PixArt-alpha/PixAr...
github.com/city96/ComfyUI_Ext...
huggingface.co/spaces/PixArt-...
github.com/PixArt-alpha/PixAr...
huggingface.co/PixArt-alpha/P...
== More Stable Diffusion Stuff! ==
* Installing Anaconda for MS Windows Beginners - • Anaconda - Python Inst...
* Installing ComfyUI - • How to Install ComfyUI...
* ComfyUI Workflow Creation Essentials For Beginners - • ComfyUI Workflow Creat...
* Faster Stable Diffusions with the LCM LoRA - • LCM LoRA = Speedy Stab...
* Make an Animated, Talking Avatar - • Create your own animat...
* One Image Gets You a Consistent Character in ANY pose - • Reposer = Consistent S...

Пікірлер: 41

@MrSporf 2 ай бұрын

Wow. I'm impressed. The prompt understanding is something else - quite amazing!

@NerdyRodent 2 ай бұрын

Yup, it’s pretty good!

@swannschilling474 25 күн бұрын

Catching up on some stuff! Thanks Nerdy! 😊

@steffen_r 2 ай бұрын

Thx for sharing. The demo looks promising and the model has a good understanding of prompts.

@NerdyRodent 2 ай бұрын

Yup! It’s great for prompt understanding and so ideal for generating an initial image 👍🏽

@bebeno1 2 ай бұрын

I wish we could convert any fine-tune sdxl model to T5 encoder like juggernaut that would be amazing

@user-eq1rf2hq8s 2 ай бұрын

Ah, so that's why I couldn't load the model in comfy! Thanks - you cleared up where I was going wrong with the custom node install.

@NerdyRodent 2 ай бұрын

Glad I could help!

@valerymoyseenko 2 ай бұрын

Thanks buddy! Especially caught your words that PixArt generates more different faces than SD. These identical smiling cute ladies with almond-shaped features are already starting to get annoying, and it has not even been a year. I have installed PixArt at my place, I'm studying it now, but the first results are impressive.

@Digital_Toolbox 2 ай бұрын

Thanks for the great content! What I wasn't sure about was if I already have comfyui Install up and running, can I just skip the preparation step and move directly to step two? Thanks!

@NerdyRodent 2 ай бұрын

Yup, the video assumes you’ve got ComfyUI installed already 👍🏽

@zerorusher Ай бұрын

Since Stable diffusion 3 weight will probably never be released (or at least delayed until stability AI has something much better) its very nice to see new open models emerging!

@NerdyRodent Ай бұрын

All the stability ai stuff is research use only now anyway… unless you pay their subscription 😐

@Armaan27012012 2 ай бұрын

do you have a workflow which has pixart and controlnet and ipadapter?

@PhilipBrownEsq 13 күн бұрын

came for pixart, stayed for the outro. wait.. i guess.. I left after the outro? well, at least it got you a like, then !

@harshitpruthi4022 2 ай бұрын

i am trying to do some experiments , will it work with either ipadapter or faceid , have anyone tried it

@l.x6 2 ай бұрын

lol the end

@fredmcveigh9877 2 ай бұрын

Hey Nerdy. I respect your opinion and you haven't said anything about SD3. Please let us know what you think of it and the fact it doesn't seem to be open source anymore.

@NerdyRodent 2 ай бұрын

my focus is on things with open licensing, so with the SD stuff all being for research only, non-commercial use now it’s less of a focus. Great if you’re ok with paying the 20 dollars a month though!

@fredmcveigh9877 2 ай бұрын

@@NerdyRodent It's just sad that they seem to have changed their philosophy on people being able to use their product for free. Blender for example still continues to be free to the user. If the usage was reasonably priced then it wouldn't be such a problem but when you experiment and fiddle around with prompts like i and many others do it will be very expensive.

@WatchNoah 2 ай бұрын

what linux distro are you using / can recommend?

@NerdyRodent 2 ай бұрын

Ubuntu LTS 😀

@WatchNoah 2 ай бұрын

@@NerdyRodent nice, thanks for the quick reply

@WhatsThisStickyStuff 2 ай бұрын

This uses SDXL components but isnt actually sdxl right? Like we cant use sdxl control nets or anything

@NerdyRodent 2 ай бұрын

Yes, you need to use Pixart control nets

@chrisgreenwell3404 Ай бұрын

@@NerdyRodent Is there Pixart control nets workflow avail ?

@LouisGedo 2 ай бұрын

👋

@NerdyRodent 2 ай бұрын

👋

@JustFor-dq5wc 2 ай бұрын

This new model is great. Thanks Rodent! .git directory in pixart_sigma_sdxlvae_T5_diffusers have extra 20 GB. Can be deleted.

@maslaxali8826 2 ай бұрын

6min left

@Hooooodad 2 ай бұрын

Hoping this comes to forge

@phongtranletat9307 Ай бұрын

But I see you use CPU to run, not GPU to run.

@NerdyRodent Ай бұрын

Yes. Offloading the T5 node to run on the CPU saves loads of VRAM 😃

@phongtranletat9307 24 күн бұрын

@@NerdyRodent I don't quite understand, in what cases can we run GPU?

@CapsAdmin 2 ай бұрын

I'd guess they are samey on sdxl because you are using a community model. I think it would be fair if you used the base model, at least in addition.

@NerdyRodent 2 ай бұрын

There is, of course, the actual prompt understanding component to consider as well

@ngones7280 2 ай бұрын

I feel super sad when I see something very cool and is Cuda dependent, fuck AMD

@NerdyRodent 2 ай бұрын

Linux + CUDA is where it's at for AI at the moment :/

@ngones7280 2 ай бұрын

@@NerdyRodent ye.. :/

@San4itos 2 ай бұрын

I use ROCm on Linux and I'm Ok with it.

@ngones7280 2 ай бұрын

@@San4itos RX580 here so I don't know how to use Rocm properly and think HIP isn't available I even try to use Zluda in a new version and message related to HIP shows up