Software Engineering Courses (SECourses)•10mo ago

It seemed to have saved this time. What do I put if I only want to save the 160th epoch in the "Save

It seemed to have saved this time. What do I put if I only want to save the 160th epoch in the "Save every N epochs" .

Screenshot_2025-03-21_at_10.36.02_PM.png

Joshua AOP•3/22/25, 2:39 AM

this is what the config file has loaded minus the save every n epoch number. I added 160.

FFurkan Gözükara SECourses i already did and full dreambooth on flux works as low as 6 GB GPUs

hau•3/22/25, 2:51 AM

amazing --- where are you doing full dreambooth? which script in kohya does that.... not seeing it in the video

hau•3/22/25, 2:55 AM

there doesn't seem to be any script in kohya that lets you do dreambooth with flux

FFurkan Gözükara SECourses ye try it

Joshua AOP•3/22/25, 2:59 AM

I went with the 16gb config file and its working. it looks like there was something that was causing it to fail at 24gb.

I don't know if this matters but I am getting this during the training. however this was also happening during the 16gb training too.

2025-03-22 02:58:21.761881: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.

Hhau there doesn't seem to be any script in kohya that lets you do dreambooth with fl...

hau•3/22/25, 3:01 AM

this script will let you do full flux finetuning on low vram GPUs

https://github.com/kohya-ss/sd-scripts/blob/sd3/flux_train.py

but there is no script that does dreambooth training? so it seems like the video you posted is not using dreambooth -- please correct me if i am wrong

@Furkan Gözükara SECourses

GitHub

sd-scripts/flux_train.py at sd3 · kohya-ss/sd-scripts

Contribute to kohya-ss/sd-scripts development by creating an account on GitHub.

hau•3/22/25, 3:03 AM

unless this line implies using dreambooth: https://github.com/kohya-ss/sd-scripts/blob/sd3/flux_train.py#L88

GitHub

sd-scripts/flux_train.py at sd3 · kohya-ss/sd-scripts

Contribute to kohya-ss/sd-scripts development by creating an account on GitHub.

hau•3/22/25, 3:03 AM

wardensc2•3/22/25, 3:26 AM

Hi @Furkan Gözükara SECourses I just download your config for SDXL training. For training dreambooth for character how many regulation images from your database you think we need to use train to get good dreambooth character model

sai_150•3/22/25, 8:07 AM

Hi @Furkan Gözükara SECourses , I've 33 images of me. can you suggest how many repeats I should consider(config has 40 repeats and 1 epoch, that gives 1320 steps).

sai_150•3/22/25, 8:11 AM

what model should I use for the best results sdxl base or any custom model from Civitai (like realvis). Is this the best method for generating images of a specific person?

JJoshua A It seemed to have saved this time. What do I put if I only want to save the 160t...

Furkan Gözükara SECourses•3/22/25, 12:02 PM

my config doesnt have save every 160 epooch

Furkan Gözükara SECourses•3/22/25, 12:02 PM

save like every 10 15

Hhau amazing --- where are you doing full dreambooth? which script in kohya does that...

Furkan Gözükara SECourses•3/22/25, 12:03 PM

video is here : https://youtu.be/FvpWy1x5etM

YouTubeSECourses

FLUX Full Fine-Tuning / DreamBooth Training Master Tutorial for Win...

If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...

JJoshua A I went with the 16gb config file and its working. it looks like there was someth...

Furkan Gözükara SECourses•3/22/25, 12:04 PM

ignore it

Wwardensc2 Hi <@205854764540362752> I just download your config for SDXL training. For trai...

Furkan Gözükara SECourses•3/22/25, 12:04 PM

using maximum is best

Furkan Gözükara SECourses•3/22/25, 12:04 PM

so lets say 50 train images and we have 5000 reg images so repeating 100 and make like 2-3 epochs

Ssai_150 what model should I use for the best results sdxl base or any custom model from ...

Furkan Gözükara SECourses•3/22/25, 12:05 PM

for 33 images

Furkan Gözükara SECourses•3/22/25, 12:05 PM

do repeating 150 and train 1 epoch at least but it may not be sufficient

Furkan Gözükara SECourses•3/22/25, 12:05 PM

you can also make repeat 100 and train 2 epochs

FFurkan Gözükara SECourses hey your trigger word is wrong. it is many multiple words combination

umrfarooq•3/22/25, 12:42 PM

Thanks for the response. Here my questions:

Do you think this will fix the color issue (like the exact shade) and will this also solve different body type problem?
What can I do so I can try on different body type as well?
What are your tips on bad hands?
Do you think full dreambooth training is good choice or not for this use case, as we need exact pattern of the dress?

I already watched the video and learned a lot. Infact I watch it whenever I get confused anywhere. Can you please share resources to learn more so I can try doing some research on the image generation and if possible create a video in detail for parameters that can impacts the training results?

Uumrfarooq Thanks for the response. Here my questions: 1. Do you think this will fix the ...

Furkan Gözükara SECourses•3/22/25, 12:53 PM

1 : get better dataset train on flux

Furkan Gözükara SECourses•3/22/25, 12:53 PM

2 : get better dataset train on flux

Furkan Gözükara SECourses•3/22/25, 12:53 PM

3 : get better dataset train on flux

Furkan Gözükara SECourses•3/22/25, 12:53 PM

4 : well dreambooth is most powerful training atm. better than lora. i cant say it is exactly use case or not but if you want highest quality probably

Furkan Gözükara SECourses•3/22/25, 12:54 PM

undertanding better dataset only happens through experience. you have to do different trainings compare and improve

umrfarooq•3/22/25, 12:58 PM

Thank you @Furkan Gözükara SECourses . By the way, I am a Python developer and if you need any help regarding maintaining your softwares I would love to do it for you. Thanks again

Uumrfarooq Thank you <@205854764540362752> . By the way, I am a Python developer and if you...

Furkan Gözükara SECourses•3/22/25, 1:42 PM

thanks a lot

wardensc2•3/22/25, 2:35 PM

Hi @Furkan Gözükara SECourses I have another question, can I train multi characters in one dreambooth checkpoint together using different active keywords and caption ?

FFurkan Gözükara SECourses you can also make repeat 100 and train 2 epochs

sai_150•3/22/25, 2:54 PM

Should I use any other model instead of sdxl base?

Uumrfarooq Thanks for the response. Here my questions: 1. Do you think this will fix the ...

sai_150•3/22/25, 5:12 PM

Have you tried the Catvton model ? It takes model and clothing images as input and generates model wearing the input clothing

Ssai_150 4. Have you tried the Catvton model ? It takes model and clothing images as inpu...

umrfarooq•3/22/25, 5:19 PM

No, I haven't tried. Thanks for sharing. I will try it now. How was your experience with it? Does it work well with different lightning conditions?

sai_150•3/22/25, 5:34 PM

I've tried Simple Catvton workflow. It may not produce exact matching clothing sometimes(color/pattern mismatch). I've seen videos using some advanced workflow to get an exact clothing match. I haven't tried it yet.

Uumrfarooq No, I haven't tried. Thanks for sharing. I will try it now. How was your experie...

sai_150•3/22/25, 5:35 PM

Please let me know about your experience if you implement it for your usecase

Ssai_150 Please let me know about your experience if you implement it for your usecase

umrfarooq•3/22/25, 5:37 PM

Sure, I will update you after trying it. Thank you.

Wwardensc2 Hi <@205854764540362752> I have another question, can I train multi characters ...

Furkan Gözükara SECourses•3/22/25, 9:46 PM

they bleed

Furkan Gözükara SECourses•3/22/25, 9:46 PM

https://medium.com/@furkangozukara/thoroughly-experimented-with-fine-tuning-dreambooth-training-of-flux-dev-de-distill-pixelwave-13fab8c625bf

Medium

Thoroughly experimented with Fine-Tuning / DreamBooth training of F...

Thoroughly experimented with Fine-Tuning / DreamBooth training of Flux-dev-de-distill, PixelWave v03, Verus Vision and base FLUX Dev model…

Ssai_150 Should I use any other model instead of sdxl base?

Furkan Gözükara SECourses•3/22/25, 9:46 PM

of course you can use

Furkan Gözükara SECourses•3/22/25, 9:46 PM

especially a model that already can generate similar quality / resembling images of what you want

Joshua AOP•3/23/25, 12:33 AM

@Furkan Gözükara SECourses I am using a 48GB to create some finetuning. I used the 48 config and the learning rate is set at: 0.000004. That seems really low. It's taking about 7 hours on 4500 steps.

FFurkan Gözükara SECourses they bleed

wardensc2•3/23/25, 4:15 AM

I mean I train using SDXL not Flux i already saw some lora contain many characters