read here : https://medium.com/@furkangozukara/20-new-sdxl-fine-tuning-tests-and-their-results-bette
Medium
I have been keep testing different scenarios with OneTrainer for Fine-Tuning SDXL on my relatively bad dataset. My training dataset is…
Fbut flux reg images doesnt help
Fyet
RAlright thx
MHey Doc, question about training if you please… In the OneTrainer mega-tutorial (awesome, BTW) you repeatedly mention that, in each epoch, regularization images should be as many as the training images. This makes a lot of sense. However, in the Kohya tutorial (also great) we end up setting the same amount of repeats (1, if I'm not mistaken) for reg and training; still, if I'm not mistaken, you don't say in the Kohya tutorial that we should only use as many reg images as there are training images. The net result is that there's an imbalance of reg vs. training images.
Is it me who didn't understand the Kohya tutorial, or is it just an oversight?
Is it me who didn't understand the Kohya tutorial, or is it just an oversight?
Fin kohya we simply cant use as many as
Fbecause kohya doesnt have 1 to 1 system
Fwe have to use repeat
Fbut still we aim to use
F1 reg image for every step
Fso lets say 200 epochs 15 images requires 3000 steps
Fso we need 3000 reg images
MSo you just select the first 3000 from your (again, super-awesome) 5200-pack?
MBTW, an article you pinned on qwen-flux-wan-such insists that we should always use repeat 10. Do you agree with that? (I know you say rep 1 in the videos…)
Fit uses first 3000
Flogic is
F200 repeat 15 train images
Fit fetches first 3000
Fnope no such thing
Fi dont know where they come such ideas
MIt's actually the second pinned article in the channel, but I do see your point
https://blib.la/blog/mastering-lora-style-training-a-comprehensive-guide
https://blib.la/blog/mastering-lora-style-training-a-comprehensive-guide
Discover the secrets of LoRA style training for AI art. Learn dataset selection, optimization, and detailed captioning for stunning AI-generated art.
Fi explained in latest video why kohya implemented repeating
Fit was for balancing inbalanced multi concept datasets
Fbut he made it poorly that we cant set 1 to 1 reg images like we can in onetrainer
Fbut one trainer doesnt have dreambooth with prior loss rate so not exactly same 
HI followed your tutorial on dreambooth for runpod using automatic installation files on patreon. But now I cannot find extensions such as civitai browser+ on extensions download tab
Fcan you link me which tutorial
HYouTubeSECourses
With following this video you can install and use famous Automatic1111 SD Web UI DreamBooth extension on RunPod for full DreamBooth training. Installer scripts are here : https://www.patreon.com/posts/runpod-auto-of-84716845
Click to download scripts
https://www.patreon.com/posts/runpod-auto-of-84716845
SECourses Discord To Get Full Support...
Click to download scripts
https://www.patreon.com/posts/runpod-auto-of-84716845
SECourses Discord To Get Full Support...
HI also want all the controlnets and latest updates on a1111 but maybe it's not possible if I want dreambooth together with it on the same pod
Fdreambooth is broken
Fi dont suggest it anymore
Fuse kohya or onetrainer
Fyou use runpod?
Hyes
Fok so use kohya
Fyou wanna train sdxl or sd 1.5?
Hdo you suggest I use a1111 on runpod for generation and then something else for dreambooth training?
Hsd 1.5 but probably sdxl in future
Fyes you are both right
Fnow i will link you few tutorails
Fif you watch all
Fyuo can do all
Hok thank you!
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...
F1:00:05 Training SDXL and SD1.5 models using Kohya GUI
1:03:20 Using regularization images for SDXL training
1:05:30 Saving checkpoints during SDXL training
1:06:15 Extracting LoRAs from SDXL models
1:03:20 Using regularization images for SDXL training
1:05:30 Saving checkpoints during SDXL training
1:06:15 Extracting LoRAs from SDXL models
FBest SDXL and SD 1.5 Configs
For SDXL and SD 1.5 config we use reg images (improves quality a lot) : https://www.patreon.com/posts/87700469
Best updated SDXL config for Kohya SS GUI : https://www.patreon.com/posts/89213064
Best updated SD 1.5 config for Kohya SS GUI : https://www.patreon.com/posts/97379147
If you need LoRA for SD 1.5 or SDXL, do a full fine-tuning / DreamBooth with above configs and extract LoRA as shown here : https://www.patreon.com/posts/108634568
For SDXL and SD 1.5 config we use reg images (improves quality a lot) : https://www.patreon.com/posts/87700469
Best updated SDXL config for Kohya SS GUI : https://www.patreon.com/posts/89213064
Best updated SD 1.5 config for Kohya SS GUI : https://www.patreon.com/posts/97379147
If you need LoRA for SD 1.5 or SDXL, do a full fine-tuning / DreamBooth with above configs and extract LoRA as shown here : https://www.patreon.com/posts/108634568
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...
F46:30 Transition to RunPod: Setting Up FLUX Training and Using SwarmUI/Forge Web UI