Software Engineering Courses (SECourses)•14mo ago

I used these steps in the terminal at kohya_ss folder, still the same issue

RRockerx <@205854764540362752> one question for understanding. why would 16GB config be s...

Furkan Gözükara SECourses•11/18/24, 4:24 PM

even kohya couldnt find it

Furkan Gözükara SECourses•11/18/24, 4:24 PM

it is a weird thing

RRockerx so for v14 it is necessary to use the bat file fix ? or is it only if this error...

Furkan Gözükara SECourses•11/18/24, 4:25 PM

yes but bmaltais fixed

Furkan Gözükara SECourses•11/18/24, 4:25 PM

latest version should work now

RRockerx also. 3rd question. do we still need Windows_update_kohya_and_fix_FLUX_Step2 ? o...

Furkan Gözükara SECourses•11/18/24, 4:25 PM

not atm but in future maybe

SShamsi I used these steps in the terminal at kohya_ss folder, still the same issue

Furkan Gözükara SECourses•11/18/24, 4:25 PM

try latst version

Furkan Gözükara SECourses•11/18/24, 4:25 PM

maybe now works

Furkan Gözükara SECourses•11/18/24, 4:25 PM

he made an update

FFurkan Gözükara SECourses try latst version

ShamsiOP•11/18/24, 4:56 PM

Sorry, what do you mean latest version? I'm V44 files from a day ago.

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭L40S, got it, thanks!

CMatias•11/18/24, 6:56 PM

L40S and A100 PCIe, are my first choices.
L40S is very polyvalent and has a good speed.
I use A100 PCIe when I don't want to loose time about searching for the parameters limits and fall into Out Of Memory problems.

SShamsi Sorry, what do you mean latest version? I'm V44 files from a day ago.

Furkan Gözükara SECourses•11/18/24, 8:12 PM

i mean run updater bat file

Furkan Gözükara SECourses•11/18/24, 8:12 PM

kohya gui fixed error

FFurkan Gözükara SECourses i mean run updater bat file

ShamsiOP•11/18/24, 8:18 PM

i'm running ubuntu on massed

SShamsi i'm running ubuntu on massed

Furkan Gözükara SECourses•11/18/24, 8:20 PM

then run installer

Furkan Gözükara SECourses•11/18/24, 8:20 PM

it will update

Furkan Gözükara SECourses•11/18/24, 8:20 PM

our installer from zip file

FFurkan Gözükara SECourses our installer from zip file

ShamsiOP•11/18/24, 8:59 PM

link please doc

Furkan Gözükara SECourses•11/18/24, 9:01 PM

https://www.patreon.com/posts/112099700

Furkan Gözükara SECourses•11/18/24, 9:02 PM

use massed compute instructions

ShamsiOP•11/18/24, 9:23 PM

ty ty doc!

FFurkan Gözükara SECourses https://www.patreon.com/posts/112099700

ShamsiOP•11/18/24, 9:26 PM

I'm creating Loras

ShamsiOP•11/18/24, 9:26 PM

it is the same?

SShamsi I'm creating Loras

Furkan Gözükara SECourses•11/18/24, 9:37 PM

yes

Furkan Gözükara SECourses•11/18/24, 9:37 PM

uses same files

ShamsiOP•11/18/24, 9:38 PM

ok thank you again doc

Rockerx•11/18/24, 9:54 PM

thanks for the responses.

Rockerx•11/18/24, 9:55 PM

@Furkan Gözükara SECourses can we train FP8 models as well using same configs? or do I need to select fp8 in the training parameters. Atm I can train lora on FP8 using your fp8 config.

RRockerx <@205854764540362752> can we train FP8 models as well using same configs? or do...

Furkan Gözükara SECourses•11/18/24, 10:01 PM

yes

Furkan Gözükara SECourses•11/18/24, 10:01 PM

but there is no fp8 training for fine tuning

Furkan Gözükara SECourses•11/18/24, 10:01 PM

kohya doesnt support

FFurkan Gözükara SECourses but there is no fp8 training for fine tuning

Rockerx•11/18/24, 11:29 PM

I was asking for the dreambooth tab. so fp8 is only for lora

RRockerx I was asking for the dreambooth tab. so fp8 is only for lora

Rockerx•11/18/24, 11:31 PM

@Furkan Gözükara SECourses do you know what is used for fp8 finetune ? do other tools like onetrainer support it ? or is the only option to do full training and then save as fp8

RRockerx <@205854764540362752> do you know what is used for fp8 finetune ? do other tools...

Furkan Gözükara SECourses•11/18/24, 11:39 PM

it only converts base model into fp8

Furkan Gözükara SECourses•11/18/24, 11:39 PM

training is still done as fp16

Furkan Gözükara SECourses•11/18/24, 11:39 PM

kohya said me that he doesnt know how to make training in fp8

ShamsiOP•11/18/24, 11:53 PM

@Furkan Gözükara SECourses I did the updates as suggested and played with the repeat and epoch numbers. still it won't go past 1600 steps and 10 epochs (I've set it to 200). is this normal or am i missing something?

SShamsi <@205854764540362752> I did the updates as suggested and played with the repeat ...

Furkan Gözükara SECourses•11/18/24, 11:57 PM

yes you need to enter max steps count

Furkan Gözükara SECourses•11/18/24, 11:57 PM

in the gui look for it

FFurkan Gözükara SECourses yes you need to enter max steps count

ShamsiOP•11/19/24, 12:16 AM

Yes sirr

. Had to override the default =0.

SShamsi Yes sirr 🫡 . Had to override the default =0.

Furkan Gözükara SECourses•11/19/24, 12:20 AM

yep

FFurkan Gözükara SECourses yes you need to enter max steps count

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•11/19/24, 6:54 AM

Perfect, just what I was gonna ask too

Got my answer quickly here. Thanks

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•11/19/24, 10:21 AM

Here's a challenge I want to complete. I have a fine-tuned checkpoint for my character, but I want my characters body to be taken from another character. So I trained a lora using pics of the other character, but the lora also includes that characters face. What do you guys suggest I do to get best result? I don't want my face changed because of this lora. So is using the <segment...> syntax in swarmui a way to go, or should I change the training images such that the head is cut off?

Appreciate this community so much, I learn something every day!

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭Here's a challenge I want to complete. I have a fine-tuned checkpoint for my cha...

Furkan Gözükara SECourses•11/19/24, 10:45 AM

i dont think it will work

Furkan Gözükara SECourses•11/19/24, 10:45 AM

you can inpaint face of another character

Rockerx•11/19/24, 11:46 AM

@Furkan Gözükara SECourses reporting 2 things.

now when I install v44 or v14 scripts it does update kohya and I am getting correct step count.
in your lora configs you are using additional parameters for block swap. this throws an exit 0 error and training exits. the UI in lora in latest kohya now has block swap option in UI. if I manually set it to what your config has and remove the additional parameter the training works but not sure if as the UI option says (use with fused back pass) which is not available in UI. but the training works with block swap if I set in UI and remove your addition parameters setting.
Can you fix the configs so that it works for lora ? have not tested the finetune in new config but see if that also needs update etc.

wardensc2•11/20/24, 1:57 AM

hi @Furkan Gözükara SECourses I just download dreambooth v15 few days ago now you already uploaded v16. Is there something new in this new version ?

wardensc2•11/20/24, 2:05 AM

And I also have a question about training full dreambooth checkpoint @Furkan Gözükara SECourses . Since you said training person with dreambooth should separate into 2 part of training. Part 1 to take the epoch which is flexible to style. Part 2 is train new epoch with the base is flexible style model from part 1.
What is the different with continue training compare with separte with 2 parts like this. since we used constant learning rate.
For example: Part 1 - I choose epoch 30 to use as based model to retrain. Part 2 - I train 100 more epoch with based model in Part 1. But that just similar to train 130 epoch from Part 1 right ? Because we use constant learning rate.

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•11/20/24, 8:54 AM

So as a general rule, the more training images you have of 1 character, the less epochs you would need to get good result. Am I getting the logic right? So 300 pics you might get good result with 10 or 20 epochs, but with 15 pics, you will need more epochs, like 100-200.

Wwardensc2 And I also have a question about training full dreambooth checkpoint <@205854764...

Furkan Gözükara SECourses•11/20/24, 10:11 AM

yes both should be same continue

Wwardensc2 hi <@205854764540362752> I just download dreambooth v15 few days ago now you alr...

Furkan Gözükara SECourses•11/20/24, 10:12 AM

no changes for fine tuning only dowgnrade torch to 2.5.0

I used these steps in the terminal at kohya_ss folder, still the same issue

Similar Threads

Similar Threads

Similar Threads