Software Engineering Courses (SECourses)•12mo ago

Has anyone tried installing swarmUI on ramdisk to speed up t5xxl/clip/vae switching for fp16 workflo

Has anyone tried installing swarmUI on ramdisk to speed up t5xxl/clip/vae switching for fp16 workflows on 24GB VRAM cards?
Current process seems grossly inefficient on machines with huge RAM - why this models can't be always loaded in RAM for near instant swapping to VRAM (6GB/s)?

TimsonOP•1/27/25, 11:27 AM

I don't seem to understand what is the bottleneck for this operation. Suspect comfyUI always unload models from RAM cache after loading to VRAM that causes extreme slowdown of this process

druhl•1/27/25, 2:36 PM

You can install things on the RAM? Lol

AiInfluence•1/27/25, 3:09 PM

@Furkan Gözükara SECourses any comments on Deepseek R1?

42069•1/27/25, 4:53 PM

https://github.com/deepseek-ai/Janus

GitHub

GitHub - deepseek-ai/Janus: Janus-Series: Unified Multimodal Unders...

Janus-Series: Unified Multimodal Understanding and Generation Models - deepseek-ai/Janus

42069•1/27/25, 4:54 PM

DeepSeek Janus Pro just released

42069•1/27/25, 5:44 PM

Multimodal LLM capable of text to image

daroth•1/27/25, 9:58 PM

not impressed

daroth•1/27/25, 9:59 PM

daroth•1/27/25, 10:00 PM

Hunter•1/27/25, 10:05 PM

@Furkan Gözükara SECourses thank you for all your work. I have created a finetuning model of myself and the result so far have been quite awesome! I need to learn a lot more on prompting, but its very easy to get quite good results! If you have any tips to learn realism prompts that would be cool!

TimsonOP•1/27/25, 11:18 PM

Flux's ability to establish coherency never ceases to amaze me. Here is an example how model both perfectly simulated art style of an old HoMM 2 game to create a new unit but also established battelscape rules of units hex and troop counter when asked to add new non existing "purple sorceress unit" with nothing but this single image

TimsonOP•1/27/25, 11:19 PM

this one without troop counter but virtually indistinguishable art style from the original. Both examples just base flux dev no loras

watersocks•1/28/25, 12:36 AM

is face fusion still working on massed compute? can't seem to get it to install

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•1/28/25, 1:11 AM

Guys ,any advice on how to get Crystal clear face? Currently using my fluz fine char checkpoint, then some face detailing, but it always feels blurry or fake...

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭Guys ,any advice on how to get Crystal clear face? Currently using my fluz fine ...

Hunter•1/28/25, 1:17 AM

Have you tried upscaling with supir? Also how much % of the photo does your face take up?

Hunter•1/28/25, 1:17 AM

if its a small %, then you could try face inpainting, could be worth doing anyways. also have you tried adding words to your prompts that mean things like high-quality?

Aikage•1/28/25, 2:01 AM

<segment:face>

Aikage•1/28/25, 2:01 AM

Swarmui ftw

Aikage•1/28/25, 2:02 AM

Not sure how In comfy probably like 18 different mask nodes, a PhD, and three different rituals to elder gods

TTimson Flux's ability to establish coherency never ceases to amaze me. Here is an examp...

AiInfluence•1/28/25, 8:38 AM

is this possible with a Lora too?

Elli_Oaken•1/28/25, 1:26 PM

Hi! I have a question about this new Hunyuan Lora training method https://www.unite.ai/how-to-train-and-use-hunyuan-video-lora-models/
I was wondering if it willl interfere with the furkan-way comfyui installation as everything needs to be installed in a specific order? Or if it's advisable to train in any other way?
Like example https://github.com/tdrussell/diffusion-pipe
https://github.com/Nerogar/OneTrainer

Unite.AI

How to Train and Use Hunyuan Video LoRA Models

This article will show you how to install and use Windows-based software that can train Hunyuan video LoRA models, allowing the user to generate custom personalities in the Hunyuan Video foundation model: Click to play. Examples from the recent explosion of celebrity Hunyuan LoRAs from the civit.ai community. At the moment the two most popular ...

GitHub

GitHub - tdrussell/diffusion-pipe: A pipeline parallel training scr...

A pipeline parallel training script for diffusion models. - tdrussell/diffusion-pipe

GitHub

GitHub - Nerogar/OneTrainer: OneTrainer is a one-stop solution for ...

OneTrainer is a one-stop solution for all your stable diffusion training needs. - Nerogar/OneTrainer

TTimson this one without troop counter but virtually indistinguishable art style from th...

Neuromasters•1/28/25, 1:51 PM

I did a similar project, only on the basis of our game that my studio does, also created the environment and new characters

MeLL•1/28/25, 4:24 PM

Hello, good afternoon.
Does anyone here who understands this very well create workflows for customized ComfyUI?
I'll pay for it

BBNP4535353 The 48g 4090 is currently available for private consumers in China (you can buy ...

Furkan Gözükara SECourses•1/29/25, 12:20 AM

that is great but useless for me since i cant buy or my followers cant but

Furkan Gözükara SECourses•1/29/25, 12:20 AM

but hopefully i will buy first day rtx 5090 to do full testing

Furkan Gözükara SECourses•1/29/25, 12:20 AM

and show you

TTimson no single config fits all cases, you always have to play around with creativity ...

Furkan Gözükara SECourses•1/29/25, 12:22 AM

thanks posted your screenshot on #tips-info

NN7-Blackbird there is a huge difference between a raw photo (digital or analog) and a stylize...

Furkan Gözükara SECourses•1/29/25, 12:22 AM

1.1 ultra is great. i wish they had published that too

AAiInfluence @Furkan Gözükara SECourses @Timson I'm planning as a next project to train shoes...

Furkan Gözükara SECourses•1/29/25, 12:22 AM

yes . you will get used to logic as you train more

Ssergio_gonzo Dr Furkan I try to use the copuon in massconpute but have a error,, dont accept ...

Furkan Gözükara SECourses•1/29/25, 12:23 AM

only L40, A6000, and A6000 ALT works

FFlakdragoon hi, I'm trying to use flux fill in SwarmUI to replace an orange wristband over a...

Furkan Gözükara SECourses•1/29/25, 12:25 AM

perhaps finding accurate prompts or post processing manually

AAlexGilSeg Anyone that has trained loras locally with a 3060 using kohya?

Furkan Gözükara SECourses•1/29/25, 12:31 AM

yes i have 3060

TTimson Has anyone tried installing swarmUI on ramdisk to speed up t5xxl/clip/vae switch...

Furkan Gözükara SECourses•1/29/25, 12:32 AM

i think it should keep them on RAM. RAMdisk you mean using disk as a RAM?

AAiInfluence @Furkan Gözükara SECourses any comments on Deepseek R1?

Furkan Gözükara SECourses•1/29/25, 12:32 AM

yes it is amazing

Furkan Gözükara SECourses•1/29/25, 12:33 AM

i hope china will bring gpus as well

Dazzastrous [4090]•1/29/25, 12:34 AM

yeh 5090's with 64gb

DDazzastrous [4090]yeh 5090's with 64gb

Furkan Gözükara SECourses•1/29/25, 1:01 AM

5090 must have been 64 gb

Furkan Gözükara SECourses•1/29/25, 1:01 AM

i hope China brings some real GPUs like DeepSeek effect

Furkan Gözükara SECourses•1/29/25, 1:02 AM

for a long time now I am using China made phones

Furkan Gözükara SECourses•1/29/25, 1:02 AM

currently poco x6 pro

TTimson Is there a way to install SwarmUI non interactively? I'm so tired of deselecting...

Renzo•1/29/25, 2:59 PM

Did you find a workaround?

FFurkan Gözükara SECourses 5090 must have been 64 gb

N7-Blackbird•1/29/25, 3:08 PM

I am still using my poco x3 pro and it runs without any issues for almost 3 years now. Great phones.

RRenzo Did you find a workaround?

TimsonOP•1/29/25, 3:21 PM

nope, didn't have time to research it. Should be not that hard, just gzip installation folder before putting in any models in dirs. My only concern is dotnet framework

42069•1/29/25, 8:36 PM

I won 50usd credits in Fal and on replicate

42069•1/29/25, 8:36 PM

Could I create a good realist face LoRA with that money?