Software Engineering Courses (SECourses)•5mo ago

have you tried creating character checkpoints from krea? I'm at 10000 steps and the model is clearly

have you tried creating character checkpoints from krea? I'm at 10000 steps and the model is clearly ruined by now: all stylized outputs became blurry mangled and photorealistic

TimsonOP•8/19/25, 5:24 PM

no comparable character similiarity was reached like with flux-dev

TimsonOP•8/19/25, 5:25 PM

I'll try with different datasets but I don't think this process works with krea like with flux dev.

EElli_Oaken Hi Furkan, I want to confirm something about your captioning theory. For a small...

Furkan Gözükara SECourses•8/19/25, 5:25 PM

i think you dont need detailed captions

Furkan Gözükara SECourses•8/19/25, 5:25 PM

with flux detailed captions makes sense only at general fine tuning with multiple concepts

Furkan Gözükara SECourses•8/19/25, 5:26 PM

and it is not doable with flux dev

Furkan Gözükara SECourses•8/19/25, 5:26 PM

but with qwen i am hopeful

TTimson have you tried creating character checkpoints from krea? I'm at 10000 steps and ...

AiInfluence•8/19/25, 5:26 PM

200epoch and 4000 and you should be good timson

AAiInfluence 200epoch and 4000 and you should be good timson

TimsonOP•8/19/25, 5:27 PM

4000 what?

TimsonOP•8/19/25, 5:28 PM

I mean it's kinda working but the result is much much worse than flux dev for me in both character similarity and model creativity

AiInfluence•8/19/25, 5:37 PM

steps

AiInfluence•8/19/25, 5:38 PM

idk guys im getting good results

AAiInfluence idk guys im getting good results

skyrrr•8/19/25, 7:18 PM

me too actually, krea is my new go-to for finetunings

Sskyrrr me too actually, krea is my new go-to for finetunings

cyberbol•8/19/25, 7:54 PM

I did so far just Lora. Not trained yet full model dreambooth

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/19/25, 11:26 PM

ok i'll do krea next for comparison. doing my first fine tune locally, done loads on massedcompute. got 5090 and 128gb ram. went with the 24gb config. 25 pics, 200 epochs looks like its going to be around 6h.

skyrrr•8/20/25, 8:27 AM

hey @Dr. Furkan Gözükara, could you give me some advice i have a big checkpoint to train (220 epochs with 300+ images) and it would take 88hours with a L40S. Is there a gpu I can rent what would significantly speed up the training (without going multi gpu, i read here that it impacts the quality of the training) ? Thanks

Sskyrrr hey @Dr. Furkan Gözükara, could you give me some advice i have a big checkpoint ...

Furkan Gözükara SECourses•8/20/25, 8:28 AM

well 220 epoch is too big for 300 images

Furkan Gözükara SECourses•8/20/25, 8:28 AM

it is a single concept right?

Furkan Gözükara SECourses•8/20/25, 8:28 AM

there isnt much you can do to speed up even batch size wont help much

Furkan Gözükara SECourses•8/20/25, 8:28 AM

unless multiple gpu

skyrrr•8/20/25, 8:30 AM

@Dr. Furkan Gözükara It's for an editorial style model so the dataset isn't very homogenous... I went with 220 because i'm training for flux krea

skyrrr•8/20/25, 8:31 AM

would multiple gpu hurt the quality of the training ?

Sskyrrr @Dr. Furkan Gözükara It's for an editorial style model so the dataset isn't very...

Furkan Gözükara SECourses•8/20/25, 8:35 AM

i see

Sskyrrr would multiple gpu hurt the quality of the training ?

Furkan Gözükara SECourses•8/20/25, 8:35 AM

you can do this

Furkan Gözükara SECourses•8/20/25, 8:35 AM

4 gpus

Furkan Gözükara SECourses•8/20/25, 8:35 AM

batch size 1

Furkan Gözükara SECourses•8/20/25, 8:35 AM

it will minimally impact

Furkan Gözükara SECourses•8/20/25, 8:35 AM

so your total batch size will be 4

Furkan Gözükara SECourses•8/20/25, 8:35 AM

make learning rate = learning rate * 2

skyrrr•8/20/25, 8:42 AM

Ok @Dr. Furkan Gözükara thanks a lot. Is there a patreon post where you explain how to set up multiple gpu for runpod ?

Sskyrrr Ok @Dr. Furkan Gözükara thanks a lot. Is there a patreon post where you explain ...

Furkan Gözükara SECourses•8/20/25, 8:46 AM

yep

Furkan Gözükara SECourses•8/20/25, 8:46 AM

https://youtu.be/-uhL2nW7Ddw

YouTubeSECourses

Blazing Fast & Ultra Cheap FLUX LoRA Training on Massed Compute & R...

Unlock the power of FLUX LoRA training, even if you're short on GPUs or looking to boost speed and scale! This comprehensive guide takes you from novice to expert, showing you how to use Kohya GUI for creating top-notch FLUX LoRAs in the cloud. We'll cover everything: maximizing quality, optimizing speed, and finding the best deals. With our exc...

skyrrr•8/20/25, 8:48 AM

you're the best

FFurkan Gözükara SECourses make learning rate = learning rate * 2

skyrrr•8/20/25, 1:38 PM

Just to make sure, I was using 4e-06, what would that make x2 ?

Sskyrrr Just to make sure, I was using 4e-06, what would that make x2 ?

Furkan Gözükara SECourses•8/20/25, 1:39 PM

4e-06 is 2x of 2e-06

skyrrr•8/20/25, 2:23 PM

THanks

skyrrr•8/20/25, 2:38 PM

@Dr. Furkan Gözükara there are no 4xGPU config file in the latest kohya zip file

Sskyrrr @Dr. Furkan Gözükara there are no 4xGPU config file in the latest kohya zip file

Furkan Gözükara SECourses•8/20/25, 2:39 PM

not for dreambooth

Furkan Gözükara SECourses•8/20/25, 2:39 PM

it needs 80gb+

Furkan Gözükara SECourses•8/20/25, 2:39 PM

lora has it

Furkan Gözükara SECourses•8/20/25, 2:39 PM

Furkan Gözükara SECourses•8/20/25, 2:40 PM

but you can follow logic of lora and test

skyrrr•8/20/25, 2:40 PM

ok will do thanks

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/20/25, 3:07 PM

my first image was ok, the 2nd one looked like this, why?

1705001-A20full-body20shot20of20ohwx20woman20posing20co-goth-fluxkrea-1-000100.png

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/20/25, 3:09 PM

hmm, maybe 16bit enabled with the t5xxx_enconly caused it?

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/20/25, 3:52 PM

or this happens, normal image fine, yolo face segment gets pixelated. whats wrong

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/20/25, 3:54 PM

first pic ok, except for face, next pic with exact same settings and prompt, not even normal pic is fine

AiInfluence•8/20/25, 3:54 PM

youre doing something wrong

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/20/25, 4:02 PM

obviously. been fine-tuning since september last year and i always use swarmui for grid-comparisons. first time i see this problem. does it have to do with flux krea? am i supposed to use different clips or smth?

AiInfluence•8/20/25, 4:02 PM

what are you settings

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/20/25, 4:02 PM

same as flux dev

have you tried creating character checkpoints from krea? I'm at 10000 steps and the model is clearly

Similar Threads