Software Engineering Courses (SECourses)•11mo ago

https://youtu.be/FvpWy1x5etM?t=4719 here at this part its said something that you cannot update koh

https://youtu.be/FvpWy1x5etM?t=4719

here at this part its said something that you cannot update kohya with the updater but should use installers instead? is this still the case? thx!

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...

FFurkan Gözükara SECourses good question i never saw anyone did

ghstoic•2/8/25, 11:59 PM

Reckon it's something you'd be interested in taking a swing at? A nice wrapper would make things so much easier, but that's beyond me

Ruairi Robinson•2/9/25, 12:27 AM

https://youtu.be/WrK_DUKXMyY

YouTubeRuairi Robinson

WHICH SIDE ARE YOU ON

AI is coming for your job. Which side are you on?
Music: Pete Seeger.
Directed by Ruairi Robinson
Made using Veo 2

Ruairi Robinson•2/9/25, 12:27 AM

made another thing with VEO 2

VioletAntOP•2/9/25, 12:46 AM

@Furkan Gözükara SECourses in flux finetuning I saw you used 100 epochs for 256 images. so if you have for example 350 images, then what epochs should you choose? or should you reduce images to amount of 256?

RRuairi Robinson https://youtu.be/WrK_DUKXMyY

VioletAntOP•2/9/25, 12:55 AM

very cool stuff. how long does it take you to create such a video?

VVioletAnt https://youtu.be/FvpWy1x5etM?t=4719 here at this part its said something that y...

Furkan Gözükara SECourses•2/9/25, 1:10 AM

yes still not in main branch

VVioletAnt @Furkan Gözükara SECourses in flux finetuning I saw you used 100 epochs for 256 ...

Furkan Gözükara SECourses•2/9/25, 1:11 AM

probably max 50

Furkan Gözükara SECourses•2/9/25, 1:11 AM

or 75

FFurkan Gözükara SECourses probably max 50

VioletAntOP•2/9/25, 1:33 AM

ahhh ok I think I understand. more images higher quality and less epochs needed

VioletAntOP•2/9/25, 1:36 AM

@Furkan Gözükara SECourses batch size 1 is better quality? how much percent do you guess?
but its worse in stylized? what is actually stylized?

I looked at the comparison sets but dont see any differences

VioletAntOP•2/9/25, 1:56 AM

@Furkan Gözükara SECourses with batch size 1 and fine tuning can both GPUs be used? seems like it is not used

VVioletAnt very cool stuff. how long does it take you to create such a video?

Ruairi Robinson•2/9/25, 9:08 AM

this was 2 days

RRuairi Robinson this was 2 days

VioletAntOP•2/9/25, 11:52 AM

2 days? what is all involved in such a process and steps is most time spent?
what do you think about this tool or gen AI in general? (because I saw in your channel you do movies)

AiInfluence•2/9/25, 12:26 PM

@Furkan Gözükara SECourses SOS

I need suggestions for good lip sync

VioletAntOP•2/9/25, 1:32 PM

@Furkan Gözükara SECourses
in video you say epoch 100 is good for 256 images... but after you mention that epoch 50 is best?

what I dont understand yet... so while training you can already move the generated checkpoints to some different place because these are kind of finished states of the trained model and will only be needed for training in case the training fails. which would mean you could then use the checkpoint as new starting point? is this correct?

1nfern0•2/9/25, 5:24 PM

I've read some comments about using a clip interogator to filter out similar images from a dataset. Has anyone used this technique or know of a tool that could do this?

Vexmachina•2/9/25, 5:39 PM

Is anyone aware of a platform that offers the ability to train a flux lora and then use something like adetailer/udetailer to fix the face on inference, like out of the box or with minimal setup?

Not looking to set up my own thing from scratch on something like runpod, hoping for something more plug and play like Replicate

AIGambino•2/9/25, 8:09 PM

https://xh9998.github.io/DiffVSR-project/

DiffVSR

..tarkan Little comparison to see the improvement side by side.

Macsalim•2/9/25, 9:17 PM

Thank you for the Flux workflow, it looks promising. But I have a question I keep getting a "mat1 mat2 mismatch" error for Clip_G looks like I'm using the wrong version, can you share the link to the clip file you're using?
Also, it would be nice if you can share the generation data for one of your images, just for me to check if everything is working correctly.

MMacsalim Thank you for the Flux workflow, it looks promising. But I have a question I kee...

.tarkan•2/9/25, 10:19 PM

Here the clip g model. https://huggingface.co/stabilityai/stable-diffusion-3.5-large/resolve/main/text_encoders/clip_g.safetensors?download=true

Mido•2/10/25, 2:52 AM

Hello

Mido•2/10/25, 2:53 AM

Whenever i train kohyass lora on a flux model, i get error "returned non-zero exit status 1."

Mido•2/10/25, 2:53 AM

other models it works perfectly fine

Aragon•2/10/25, 12:59 PM

I'm getting two additional options for Kohya that don't appear on the exapmle image on the guide on Patreon - "Conv Dimension" and "Minimum Difference". Should I leave them with default values?

VVioletAnt ahhh ok I think I understand. more images higher quality and less epochs needed

Furkan Gözükara SECourses•2/10/25, 1:52 PM

yes batch size 1 is best

AAiInfluence @Furkan Gözükara SECourses SOS 🚨🚨 I need suggestions for good lip sync

Furkan Gözükara SECourses•2/10/25, 1:53 PM

i dont know good one atm

VVioletAnt @Furkan Gözükara SECourses in video you say epoch 100 is good for 256 images......

Furkan Gözükara SECourses•2/10/25, 1:53 PM

the logic is like this

Furkan Gözükara SECourses•2/10/25, 1:53 PM

we do up to 200 epochs

Furkan Gözükara SECourses•2/10/25, 1:53 PM

and we compare and find best one

Furkan Gözükara SECourses•2/10/25, 1:53 PM

but if you have too many images

Furkan Gözükara SECourses•2/10/25, 1:53 PM

it is becoming redundant

11nfern0 I've read some comments about using a clip interogator to filter out similar ima...

Furkan Gözükara SECourses•2/10/25, 1:53 PM

we have image similarity app you can try

VVexmachina Is anyone aware of a platform that offers the ability to train a flux lora and t...

Furkan Gözükara SECourses•2/10/25, 1:54 PM

our massed compute image has swarmui

Furkan Gözükara SECourses•2/10/25, 1:55 PM

just click updat first

Furkan Gözükara SECourses•2/10/25, 1:55 PM

then ready

AAIGambino https://xh9998.github.io/DiffVSR-project/

Furkan Gözükara SECourses•2/10/25, 1:55 PM

github not found https://github.com/xh9998/DiffVSR

MMido Whenever i train kohyass lora on a flux model, i get error "returned non-zero e...

Furkan Gözükara SECourses•2/10/25, 1:56 PM

hard to know without seeing everything

AAragon I'm getting two additional options for Kohya that don't appear on the exapmle im...

Furkan Gözükara SECourses•2/10/25, 1:56 PM

you want to extract flux lora?

Furkan Gözükara SECourses•2/10/25, 1:56 PM

that is inaccurate tab

Furkan Gözükara SECourses•2/10/25, 1:56 PM

click this

Furkan Gözükara SECourses•2/10/25, 1:56 PM

FFurkan Gözükara SECourses click this

Aragon•2/10/25, 1:57 PM

Oops, my bad

. Thanks

AiInfluence•2/10/25, 1:59 PM

@Furkan Gözükara SECourses do you think to have 2 Lora people in one picture it's best to do face inpainting or regional prompting on Swarm? what will achieve best results

AAiInfluence @Furkan Gözükara SECourses do you think to have 2 Lora people in one picture it'...

Furkan Gözükara SECourses•2/10/25, 2:00 PM

probably face inpainting

FFurkan Gözükara SECourses probably face inpainting

AiInfluence•2/10/25, 2:01 PM

with yolo segmentation or individual swarm masking using flux inpaint model?

FFurkan Gözükara SECourses hard to know without seeing everything

Mido•2/10/25, 2:14 PM