Software Engineering Courses (SECourses)•6mo ago

Hey guys. I'm currently training a flux style finetune using kohya with a dataset consisting of arou

Hey guys. I'm currently training a flux style finetune using kohya with a dataset consisting of around 1800 images total. When leaving the max epoch to 0 (default) it was automatically set to 6. This seemed strange to me, I've never used a dataset this large. I'm using the "Batch_Size_7_48GB_GPU_46250MB_29.1_second_it_Tier_1" preset as provided by Dr. Furkan. Should I tweak another variable like learning rate for a dataset this big? I set max epochs to 10 and it says it will train for 20 hours on an A6000 GPU. I thought I'd ask before I have it train for 20 hours for it to end up being trash.

Llokitoxin Hey guys. I'm currently training a flux style finetune using kohya with a datase...

lokitoxinOP•7/20/25, 3:51 AM

Canceled it for now just in case someone more experienced tells me I've made a fatal error.

Llokitoxin Hey guys. I'm currently training a flux style finetune using kohya with a datase...

Furkan Gözükara SECourses•7/20/25, 9:28 AM

are these 1800 images are consistent?

Furkan Gözükara SECourses•7/20/25, 9:28 AM

for 1800 images i recommend train up to 15 epoch , take a checkpoint every epoch and compare later

FFurkan Gözükara SECourses are these 1800 images are consistent?

lokitoxinOP•7/20/25, 11:41 AM

Thanks for the response! They are high quality screenshots from a show with a unique art style, consistent in style only. All of them are uniquely captioned in the same format to describe the image, with a triggerword for the style at the start of the caption. I'll try as you suggested. One more question: Can I train 10 epochs, and with the resulting model, continue training for another 5 epochs in a separate instance (using the resulting model as a base) to get the same or similar result as if I were training 15 epochs from the start? A checkpoint per epoch would require me to regularly offload the models onto another server due to disk space, risking messing this up and epochs not saving.

lokitoxinOP•7/20/25, 11:44 AM

Also, although maybe not particularly relevant. They are actually 2 sets of the same 900 images in different aspect ratios, according to my own testing and other testing I've seen, training on different aspect ratios improves results. Particularly with style finetunes. Never tried it with this many images though.

FFurkan Gözükara SECourses it could be out of RAM

Le_Docteur•7/20/25, 3:16 PM

That was exactly it.

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 79.20 GiB of which 16.62 MiB is free. Process 2510593 has 79.18 GiB memory in use.,

training was successful on batch size=2 on h100 sxm
This thing is demanding indeed, consumed like 77gb vram

Llokitoxin Thanks for the response! They are high quality screenshots from a show with a un...

Furkan Gözükara SECourses•7/20/25, 3:31 PM

yes

Furkan Gözükara SECourses•7/20/25, 3:31 PM

with our config 10+5 = 15 from 0

Llokitoxin Also, although maybe not particularly relevant. They are actually 2 sets of the ...

Furkan Gözükara SECourses•7/20/25, 3:31 PM

well it should work decent

Furkan Gözükara SECourses•7/20/25, 3:31 PM

make sure to enable bucketing

LLe_Docteur That was exactly it. torch.OutOfMemoryError: CUDA out of memory. Tried to allo...

Furkan Gözükara SECourses•7/20/25, 3:32 PM

yes batch size 2 for dreambooth requires huge vram and ram

Furkan Gözükara SECourses•7/20/25, 3:32 PM

but lora works great

AiInfluence•7/20/25, 3:33 PM

what config should i use on H100 @Furkan Gözükara SECourses batch size 7 48gb or 48gb Q1? whats the best quality?

Le_Docteur•7/20/25, 3:33 PM

Is 20 images enough for dreamboothoing? or i need more ( i have 300)

AAiInfluence what config should i use on H100 <@205854764540362752> batch size 7 48gb or 48g...

Furkan Gözükara SECourses•7/20/25, 3:33 PM

q1 best

Furkan Gözükara SECourses•7/20/25, 3:34 PM

but if you want speed use batch size 7

AiInfluence•7/20/25, 3:34 PM

no i want quality

LLe_Docteur Is 20 images enough for dreamboothoing? or i need more ( i have 300)

Furkan Gözükara SECourses•7/20/25, 3:34 PM

more better

AiInfluence•7/20/25, 3:34 PM

so tier 1 ok thanks

Furkan Gözükara SECourses•7/20/25, 3:34 PM

definitely

AAiInfluence so tier 1 ok thanks

Furkan Gözükara SECourses•7/20/25, 3:34 PM

yes

Le_Docteur•7/20/25, 3:34 PM

repeats the same? 150-200 or i need to lower?

AiInfluence•7/20/25, 3:35 PM

btw doctor for multitalk very good and stable results gives the default t2v lighxv2 rank 32

LLe_Docteur repeats the same? 150-200 or i need to lower?

Furkan Gözükara SECourses•7/20/25, 3:35 PM

lower

Furkan Gözükara SECourses•7/20/25, 3:35 PM

for 300 images do like maximum 100 epoch and compare

AAiInfluence btw doctor for multitalk very good and stable results gives the default t2v ligh...

Furkan Gözükara SECourses•7/20/25, 3:35 PM

well i didnt test to many times

FFurkan Gözükara SECourses well i didnt test to many times

AiInfluence•7/20/25, 3:37 PM

im closing my h100 soon

AiInfluence•7/20/25, 3:37 PM

get ready to test

AiInfluence•7/20/25, 3:37 PM

thanks

Furkan Gözükara SECourses•7/20/25, 3:38 PM

so your h100 failing at sage attention?

Furkan Gözükara SECourses•7/20/25, 3:38 PM

or what error you getting

AiInfluence•7/20/25, 3:38 PM

no h100 good but c10 error

AiInfluence•7/20/25, 3:38 PM

on first launch

AiInfluence•7/20/25, 3:38 PM

underdog•7/20/25, 11:42 PM

@Furkan Gözükara SECourses Hello,

I was wondering if you have a python code that I can refer/modify for finetuning instead of using the kohya gui? I want to load the parameters and train without having to open the interface and load the parameters all the time.

Uunderdog <@205854764540362752> Hello, I was wondering if you have a python code that I c...

Furkan Gözükara SECourses•7/21/25, 12:49 AM

gui runs cmd code literally

Furkan Gözükara SECourses•7/21/25, 12:50 AM

pay attention to cmd

underdog•7/21/25, 1:09 AM

Yeah, I tried it, but the results I get vary. However, from the GUI, I get good results. I’ll check if the code uses the correct parameters again.

Uunderdog Yeah, I tried it, but the results I get vary. However, from the GUI, I get good ...

Furkan Gözükara SECourses•7/21/25, 1:20 AM

ye kohya is based on cmd command

Furkan Gözükara SECourses•7/21/25, 1:20 AM

so you need to make it accurate

underdog•7/21/25, 2:33 AM

I was able to get it working.

Also kohya does not support chroma finetuning do you know any other open source model that supports chroma finetuning?

Uunderdog I was able to get it working. Also kohya does not support chroma finetuning do...

Furkan Gözükara SECourses•7/21/25, 9:36 AM

check this out : https://github.com/ostris/ai-toolkit

GitHub

GitHub - ostris/ai-toolkit: The ultimate training toolkit for finet...

The ultimate training toolkit for finetuning diffusion models - ostris/ai-toolkit

Furkan Gözükara SECourses•7/21/25, 9:36 AM

i am not sure though

Uunderdog I was able to get it working. Also kohya does not support chroma finetuning do...

Furkan Gözükara SECourses•7/21/25, 9:36 AM

also make a reply here

Furkan Gözükara SECourses•7/21/25, 9:36 AM

https://github.com/kohya-ss/sd-scripts/issues/2081

GitHub

Chroma Support ? · Issue #2081 · kohya-ss/sd-scripts

With the FLUX.1-schnell based Chroma model gaining popularity is there any chance of it being added, for lora trainng ?

underdog•7/21/25, 9:37 AM

I tried ai tool kit but I could only find lora training. I will check again.

underdog•7/21/25, 9:48 AM

"I’d like to support this request. It would be beneficial if the developers could add support for the Chroma model.

Chroma is an 8.9B parameter model based on FLUX.1-schnell. More information can be found here: huggingface.co/lodestones/Chroma

Additionally, ai-toolkit and the diffusion-pipe project at github.com/tdrussell/diffusion-pipe already supports Chroma. (LoRA/fine-tuning).

Thank you for the fantastic sd-scripts project; your work is greatly appreciated!"

I came across this comment by blackmagix24. I will give diffusion pipe a shot. if you happen to test it in the future, I would love to see a video from you for chroma fine tuning along with a comparison with flux dev

Uunderdog "I’d like to support this request. It would be beneficial if the developers coul...

Furkan Gözükara SECourses•7/21/25, 9:50 AM

it is just weaker

Furkan Gözükara SECourses•7/21/25, 9:50 AM

what makes flux different is that it is literally built to make money

Furkan Gözükara SECourses•7/21/25, 9:50 AM

so it is really good

Hey guys. I'm currently training a flux style finetune using kohya with a dataset consisting of arou

Similar Threads

Similar Threads

Similar Threads