yes, i did found them just now (sooo many tutorials) thankz
yes, i did found them just now (sooo many tutorials) thankz
FYou are welcome. This grid is amazing
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=40)
DDoc do u have shares in Swarmui and Massed compute lol
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=16)
Fthey give 10% if you use my link , 10% of what you spend 
Dusing OT, without kohya model split?
Fi started ot trainings
Fand its interface sucks
F
UYouTubeuisato![Neo Ballet / Experiments [New SDXL & FLUX LORA | Available]](https://cdn.answeroverflow.com/embeds/1283844624787439761/0/thumbnail.jpeg)
You can access this newly trained LORA [for both SDXL and FLUX] + 5 GB of images and videos with metadata [prompts and configs], plus many more project files and experiments, through my Patreon profile: https://linktr.ee/uisato
PS: Excited to see some of you next month during my travels. I’m still sorting out the details of where I’ll be, so fe...
PS: Excited to see some of you next month during my travels. I’m still sorting out the details of where I’ll be, so fe...
XI got caption files with 300 tokens, so it wont train?
Fit will
Fbut only 225
Xis there any way to make it 300?
Xsad
Fwhat do you train sdxl?
P@Furkan Gözükara SECourses for flux what is the best trainer currently? Konya, AI toolki, onetrainer, something - something else? Do you see OneTrainer catching up?
Fonetrainer not good unless you have 40 gb gpu :d
Fit doesnt have fp8 yet
Fkohya works great
Fi didnt compare ai toolkit
Phow about training time on a A6000 - what should one expect for a 15 person picture Lora with your configs?
Feasy to calculate
Flets say you used Rank_2_27700MB_4_85_Second_IT.json
Fit is 4.85 second / it
Fyou need 3000 steps - assuming 200 epoch
F3000 x 4.85 second
PI see - thank you. By what factor does speed increase on mass compute multi GPU training ?
Falmost linear
Fif you rent 8 gpu you get like 7x speed up maybe more
M@Furkan Gözükara SECourses congrats on the latest training article. Can you add something about captioning (if you used it, how you made it…)?
MI mean, how did the model learn what each expression was? What expression does it inherently know, as far as your dataset goes?
Fi added it actually :d
FI didn't caption them only ohwx man since captioning reduces likeliness and doesn't bring improvements.
Fi updated article added more details
MThe Patreon one?
Fyep
FPatreon
Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon
MI haven't looked at the training dataset--as far as you can tell, does it look like Flux understand 100% of facial expressions? 50%?
Fit understand alls
Fi shared dataset too
Fbut lower res
MEverything like "anxious"? Like, if you put in a picture of yourself looking worried about something (dunno if you're that good of an actor 
), do you think the model would pick it up and be able to reproduce it when the prompt asks for it?
), do you think the model would pick it up and be able to reproduce it when the prompt asks for it?Fmodel has great internal captioning system
Xyeah yeah, anime style lora
Fi dont have a very good config for sdxl lora atm
Fbut training sdxl dreambooth / fine tuning and extracting lora works great
Dwhat are they offering here?
Fsomething very inferior i guess
Fprobably high batch size, high LR low step
Deven if all that and even if they train only some layers of the model, 5 min and only 1 epoch seems extreme. They must have found something new?
