okay, btw can we add extra network arguments in kohya?
okay, btw can we add extra network arguments in kohya?
Fyes
Xwhere? I couldn't find
Fcheck gui
Fthere are additonal arguments
MCan some check whether these inputs are crt
MThe generated image has up normal eyes
Fwell dont expect great results with 512 training
Fyou can inpaint face for some improvements
MOk whether the params are crt
Fi only have params for sd 1.5 dreambooth and sdxl dreambooth
Fthey are shared on patreon and you can see in this tutorial
FYouTubeSECourses
In this tutorial, I am going to show you how to install OneTrainer from scratch on your computer and do a Stable Diffusion SDXL (Full Fine-Tuning 10.3 GB VRAM) and SD 1.5 (Full Fine-Tuning 7GB VRAM) based models training on your computer and also do the same training on a very cheap cloud machine from MassedCompute if you don't have such compute...
MFi dont know crt param sadly
MWhether it give some things better
MJust saw ur videos and set this
Fwhich part can you remind me?
MOne trainer sd 1.5
MThsis ontr
Fwhich second minute
M37.39
MCan u kindly help me now ,, this is the last chance i have
Fi checked but what do you ask there i dont see ctr
MWhat params should i set
MWhether this params are crt
MWhether the learning is crt ??
Fwhat is crt?
MCorrect
NHas anyone compared dreambooth 1:1 aspect training vs bucket training yet for Flux? Please let me know your thoughts. ( alrdy know your opinion Dr Furkan 
)
)
�guys, say I have 1000 great photos of 1 character, is it always better to use more photos, or should I stick to 256 or fewer?
Xfor a person max 75
�oh really? how do you know
Xtrained 100s of loras
�ok, but I'm fine-tuning checkpoint, and the same applies there?
Xyes since its only one character
�thank you
�Can I dm you?
Xsure you can dm me @🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭
FDoc , how many images in your data set did you use to train this beauty ?
F
Fi plan to publish a good tutorial for this but for higher tier or sell based with dataset 
Fwhat matter is dataset and how you caption
Fbut our configs are 100% same
WI trained bucket from the beginning so far so good but I haven't trained 1:1 so dont know about compare result yet
AI repost also here... maybe it's the correct section:
Hi Guys... it's black-friday/cybermonday time... do you have any advice on what to buy to make flux/sdxl/pdxl models locally? I mean: what minimum requirements for a graphic card that can handle those kind of jobs... something cheap, as I do training only to understand, not for selling my works around, so I can bear also longest trainings... woud appreciate model cards or laptops adequately equipped advices, thanks to all!
Hi Guys... it's black-friday/cybermonday time... do you have any advice on what to buy to make flux/sdxl/pdxl models locally? I mean: what minimum requirements for a graphic card that can handle those kind of jobs... something cheap, as I do training only to understand, not for selling my works around, so I can bear also longest trainings... woud appreciate model cards or laptops adequately equipped advices, thanks to all!
DI went for cheapest CPU cheapest PC with 4070 Ti Super 16 GB and it's holding up. I'd go for 64 GB RAM now though because the latest offloading techniques by kohya and OneTrainer need lots of RAM.
everything can change though by tomorrow when a new model comes out. but for the current models this is a very cost-effective setup
everything can change though by tomorrow when a new model comes out. but for the current models this is a very cost-effective setup
Fso 100% 64gb definitely needed
Dquestion? or agreement?
Dbtw @Furkan Gözükara SECourses since you've complained about the OneTrainer UI on massed compute again: the cloud extension is very mature by now. a few people use it. you can run OneTrainer locally but train remotely. you might want to try it. it works best on runpod, but also works with any other cloud that gives SSH access
