Software Engineering Courses (SECourses)•16mo ago

<@205854764540362752> after finetune, is there a script to compare results with all different settin

@Furkan Gözükara SECourses after finetune, is there a script to compare results with all different settings ( different samplers, different refiners etc, it almost not fun anymore to do it manually for every saved epoch). Some saved Epoch looks overtrained, but when use another sampler or weight, suddenly it becomes much better as the next saved epoch?

JJUR <@205854764540362752> after finetune, is there a script to compare results with ...

Furkan Gözükara SECourses•9/8/24, 5:18 PM

Yes grid feature of swarm ui

Furkan Gözükara SECourses•9/8/24, 5:18 PM

Shown in both latest 2 tutorials

JUROP•9/8/24, 5:24 PM

yes, i did found them just now (sooo many tutorials) thankz

JJUR yes, i did found them just now (sooo many tutorials) thankz

Furkan Gözükara SECourses•9/8/24, 5:44 PM

You are welcome. This grid is amazing

Dazzastrous [4090]•9/8/24, 5:46 PM

Doc do u have shares in Swarmui and Massed compute lol

DDazzastrous [4090]Doc do u have shares in Swarmui and Massed compute lol

Furkan Gözükara SECourses•9/8/24, 9:35 PM

they give 10% if you use my link , 10% of what you spend

FFurkan Gözükara SECourses we already have config for that 😄

dxqb•9/10/24, 8:18 AM

using OT, without kohya model split?

Ddxqb using OT, without kohya model split?

Furkan Gözükara SECourses•9/10/24, 11:38 AM

i started ot trainings

Furkan Gözükara SECourses•9/10/24, 11:39 AM

and its interface sucks

Furkan Gözükara SECourses•9/10/24, 11:39 AM

https://youtu.be/hmu-7ycJ_E4

YouTubeSECourses

Interface is freezes on ubuntu OneTrainer

uisato•9/12/24, 5:40 PM

New experiments + FLUX & SDXL LORA! - https://www.youtube.com/watch?v=acB5gA9WyPQ

YouTubeuisato

Neo Ballet / Experiments [New SDXL & FLUX LORA | Available]

You can access this newly trained LORA [for both SDXL and FLUX] + 5 GB of images and videos with metadata [prompts and configs], plus many more project files and experiments, through my Patreon profile: https://linktr.ee/uisato

PS: Excited to see some of you next month during my travels. I’m still sorting out the details of where I’ll be, so fe...

Xcorpion•9/13/24, 10:37 AM

I got caption files with 300 tokens, so it wont train?

XXcorpion I got caption files with 300 tokens, so it wont train?

Furkan Gözükara SECourses•9/13/24, 10:38 AM

it will

Furkan Gözükara SECourses•9/13/24, 10:38 AM

but only 225

Xcorpion•9/13/24, 10:57 AM

is there any way to make it 300?

Xcorpion•9/13/24, 10:57 AM

sad

XXcorpion is there any way to make it 300?

Furkan Gözükara SECourses•9/13/24, 11:21 AM

what do you train sdxl?

papanton•9/13/24, 12:22 PM

@Furkan Gözükara SECourses for flux what is the best trainer currently? Konya, AI toolki, onetrainer, something - something else? Do you see OneTrainer catching up?

Ppapanton <@205854764540362752> for flux what is the best trainer currently? Konya, AI too...

Furkan Gözükara SECourses•9/13/24, 12:47 PM

onetrainer not good unless you have 40 gb gpu :d

Furkan Gözükara SECourses•9/13/24, 12:47 PM

it doesnt have fp8 yet

Furkan Gözükara SECourses•9/13/24, 12:47 PM

kohya works great

Furkan Gözükara SECourses•9/13/24, 12:47 PM

i didnt compare ai toolkit

papanton•9/13/24, 12:55 PM

how about training time on a A6000 - what should one expect for a 15 person picture Lora with your configs?

Ppapanton how about training time on a A6000 - what should one expect for a 15 person pict...

Furkan Gözükara SECourses•9/13/24, 1:11 PM

easy to calculate

Furkan Gözükara SECourses•9/13/24, 1:11 PM

lets say you used Rank_2_27700MB_4_85_Second_IT.json

Furkan Gözükara SECourses•9/13/24, 1:11 PM

it is 4.85 second / it

Furkan Gözükara SECourses•9/13/24, 1:11 PM

you need 3000 steps - assuming 200 epoch

Furkan Gözükara SECourses•9/13/24, 1:11 PM

3000 x 4.85 second

papanton•9/13/24, 2:04 PM

I see - thank you. By what factor does speed increase on mass compute multi GPU training ?

Ppapanton I see - thank you. By what factor does speed increase on mass compute multi GPU ...

Furkan Gözükara SECourses•9/13/24, 3:23 PM

almost linear

Furkan Gözükara SECourses•9/13/24, 3:23 PM

if you rent 8 gpu you get like 7x speed up maybe more

macba•9/13/24, 3:34 PM

@Furkan Gözükara SECourses congrats on the latest training article. Can you add something about captioning (if you used it, how you made it…)?

macba•9/13/24, 3:35 PM

I mean, how did the model learn what each expression was? What expression does it inherently know, as far as your dataset goes?

Mmacba <@205854764540362752> congrats on the latest training article. Can you add somet...

Furkan Gözükara SECourses•9/13/24, 3:35 PM

i added it actually :d

Furkan Gözükara SECourses•9/13/24, 3:35 PM

I didn't caption them only ohwx man since captioning reduces likeliness and doesn't bring improvements.

Furkan Gözükara SECourses•9/13/24, 3:35 PM

i updated article added more details

macba•9/13/24, 3:36 PM

The Patreon one?

Furkan Gözükara SECourses•9/13/24, 3:36 PM

yep

Furkan Gözükara SECourses•9/13/24, 3:36 PM

https://www.patreon.com/posts/111891669

Patreon

Training a FLUX LoRA with 256 Images Experiments So Far | SECourses...

Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon

macba•9/13/24, 3:37 PM

I haven't looked at the training dataset--as far as you can tell, does it look like Flux understand 100% of facial expressions? 50%?

Mmacba I haven't looked at the training dataset--as far as you can tell, does it look l...

Furkan Gözükara SECourses•9/13/24, 3:37 PM

it understand alls

Furkan Gözükara SECourses•9/13/24, 3:37 PM

i shared dataset too

Furkan Gözükara SECourses•9/13/24, 3:37 PM

but lower res

macba•9/13/24, 3:39 PM

Everything like "anxious"? Like, if you put in a picture of yourself looking worried about something (dunno if you're that good of an actor