we use single sided image planes for that stuff
we use single sided image planes for that stuff
AYep, that's alpha trees + triplanar shaders.
Fwell normally you should be able do with minimal invasion. however with FLUX it is very easy to get broken. so not working atm
Fbut with SDXL if you properly train with reg images it should work decent
Fhowever quality of FLUX is many levels better
AThanks - it seems I might have misunderstood your posts then.
AI was the opinion Dreambooth is finetuning the model itself.
AWhat is the result then if I use dreambooth instead of the lora creation?
A(Or the AI toolkit...)
AI refer to your patreon post: Kohya FLUX Fine Tuning (Full Checkpoints) Training Full Tutorial For Local Windows and Cloud RunPod and Massed Compute
New
9 hours ago
New
9 hours ago
AI was the opinion I get a new checkpoint after the training 
CYou will have a new checkpoint which you can use instead of the base model you trained on, or you can extract a lora from it to use in combination with the base model, but it will still have turned every 'man' into some version of you (if you were training yourself)
Fdreambooth / fine tuning way better than lora
Fcurrently we use dreambooth tab but we are doing fine tuning
Fsince we dont use any reg images
AWill try to get it running.
CI attempted using the 24gig config file for finetune on my 4090 but it estimated around 700 hours.. is this normal?
Fnope you must be using shared vram.
Fincrease number of blocks to swap or reduce your vram usage
Falso make a fresh kohya installation if still fails
CI basically force quit everything I could except kohya. It is a fresh install
Fi tested and even on my RTX 3060 works great :d
Fso how much VRAM used before starting did you check?
Caround 0.6
CI do suspect something else on my system or hardware though. Even running base flux1-dev in forge is super slow.
Fi think should work
Ftry 16 gb config
Fand report me back speed
Cwill do, thank you
Falso check how much shared vram used
Falways a possibility
Fyou should get over 2 it second with 4090 on swarmui with --fast
AHmm, I have installed Visual Studio (2017 and 2022 CE) , but it seems that I get a problem with XFormers (not installed) after installing Windows_Install_Torch_2_5_Dev_Huge_Speed_Up.bat... any clue?
A(2017 is needed for other projects )
)Fxformers not available yet
Ffor torch 2.5
Fi am waiting
Fso on windows we use SDPA
Fon linux you can use torch 2.4.1 and xformers 0.0.28.post1
AAh thanks
AIt drove me crazy^^
AI have win 11 here and any linux on runpod...
ADo you already have a quick tut for Dreambooth? I used kohya some times ago however only for sd 1.5 lora tests...
AIf not, it will happen through learning by doing, where “doing” is the sound that is made when I hit my face with my hand much too hard. 
Fdid you watch lora?
Fit is exactly same
Fjust load config into dreaambooth tab
FYouTubeSECourses
Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please wat...
FYouTubeSECourses
Unlock the power of FLUX LoRA training, even if you're short on GPUs or looking to boost speed and scale! This comprehensive guide takes you from novice to expert, showing you how to use Kohya GUI for creating top-notch FLUX LoRAs in the cloud. We'll cover everything: maximizing quality, optimizing speed, and finding the best deals. With our exc...
AAh!
ANow I see the beauty of kohya
