will check thanks
will check thanks
Fcan you give link
SVery interested in your feedbacks before trying a full kra finetune. How many images for your test ?
Djust went through your video on the sdxl lora training with one trainer.. im new to one trainer.. barely a week old... i wanna pay for your patreon and wanted to ask if you updated the presets you mentioned.. i have about 60 images i wanna train them for a person but i cant find regularization images for a female.. so im abit stuck there
Fpublished
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Fdataset published too
F
Fsdxl presets are updated at the moment
Fyou can see updates without subscription i just made that change : https://www.patreon.com/posts/96028218
Patreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Dawesome... will just follow the step by step instructions in the video
Dthanks so much.. this is a great help
Fnot a cherry pick
Fflux krea dev
F
Fat some prompts it works better than flux dev at some prompts worse
F
SMan thank you so much I got confused by the many negative feedbacks regarding krea training. From your tests it seems to be a huge improvement over flux.dev. Do you think it would do well with larger datasets as well (200 images ?)
Athere is
Adont listen to what they say about krea
Fwell it should i think. i trained flux dev with 256 images
SI feel like its harder with makin more dramatic lighting
Fyes it is biased to certain realism
SYour training at LR 2e-6 is also quite good, on a fence between this one and the base 4e-06
Fthis kl_optimal is also nice scheduler
F
Fi will post grids
Skl-optimal is my absolute favorite, especially in combinaison with gradient estimation
Fwhich sampler it works best with? with IPNDM not very good
Fi guess i have to test
Ftesting right now
JAwesome!
Will you publish the lora or dataset you made of yourself too?
Will you publish the lora or dataset you made of yourself too?
Falso published comparison results on patreon post for dreambooth
CVery funny.
SIt works best with uni_pc and gradient estimation
Fi am making a very big comparison
F
Fand comparing with our best
CNot sure there's much point in me posting my LoRA results anymore. Seems they serve better as comedy material, anyway 
AWell i dont think he made fun of you
Arather than the "easy" available alternative
Jit's a playful joke or nod on how I wanted to train a lora, and it seems a dataset just appeared
I like your lora's, and I like your posts.. I appreciate you
I like your lora's, and I like your posts.. I appreciate you
Ai like your contribution too cyberbol
SYou gotta have more faith in yourself – be strong
SWhat's your take on buckets ? Do you notice better results without ? I use different ratios so I tend to keep them on
Kanyone trained wan 2.2 in msubai trainer , particularly in h100 80gb
if you are trained on it
how can i speed up the traning time ?
if you are trained on it
how can i speed up the traning time ?
CI've been testing several samplers and schedulers for the FLUX KREA model, and it's hard to choose just ONE that is the best. It really depends on your creative goal.
However, I think these combinations are definitely worth using:
Sampler: DPM++ 2M
Scheduler: bong_tangent (New)
Sampler: Euler
Scheduler: Beta / beta57
Sampler: dpmpp_2m or ipndm
Scheduler: Beta / beta57
I'm currently running a small test comparing a few options. When it's ready, I'll share the results. However, I'm also waiting for @Furkan Gözükara SECourses comparison, as it will surely be more comprehensive.
However, I think these combinations are definitely worth using:
Sampler: DPM++ 2M
Scheduler: bong_tangent (New)
Sampler: Euler
Scheduler: Beta / beta57
Sampler: dpmpp_2m or ipndm
Scheduler: Beta / beta57
I'm currently running a small test comparing a few options. When it's ready, I'll share the results. However, I'm also waiting for @Furkan Gözükara SECourses comparison, as it will surely be more comprehensive.