btw, how big of a quality difference are we talking about when it comes to direct lora draining vs f
btw, how big of a quality difference are we talking about when it comes to direct lora draining vs full checkpoint training + extraction?
Jat least with my datasets i get the best results with full checkpoint training + extraction. How big the difference? i can see it, if extraction is 10 then i would give a 6 or 7
FHello! I would like to ask for some advice. How can I achieve the best settings for training SDXL Lora on OneTrainer, and what should I pay attention to? The training set consists of approximately 80-150 images of artist’s works with inconsistent aspect ratios. Thank you! 
NThe L40 & L40S are very similar to the 6000 ADA. We have a few of those available right now.
The L40 & L40S have a better server CPU and Ram as well.
The L40 & L40S have a better server CPU and Ram as well.
Mi think in terms of pricing with runpod both the l40 and 6000ada are quite cheap 79cents per hour
but on massed compute its 1.15 for the l40
but on massed compute its 1.15 for the l40
NApples to apples would be secure cloud pricing on runpod.
Fit shouldnt be case
Flast time i tested 128 rank lora was very close
Fi think a lot
Fextraction was way better for me
Fi dont have best hyper configuration for lora training
Fit requires some research
Fyou need to find best learning rate and other parameters
Fbut you can use our fine tuning parameters
Fand extract lora after training if necessary
Jthank for the info, i will try the same dataset training on different SDXL Models to see if there is a difference.
AMake the threshold lower. For me 0.0001 at most.
Ftrue make sure that diff limit low
Flike 0.000001
Jok i trained on the standard SDXL Model now, Epoch around 150 Model is really good, but the LoRA export still not close to the finetuning, i tested different threshold settings, 0.001 - 0.000001 it didn't helped. i will try later different ranks (128), do i need to change both rank and alpha to the same value?
Mare you training the text encoder as well? --train_text_encoder --learning_rate_te2 0 ??
Fi think give it a try
Fi cant test right now but i plan research and a video for this
Jonly Text Encoder 1
Mtry an older version of kohya
Mlike 22.6.2
Juh ok, i first need to learn how to rollback, never tried before
Mgit checkout 5d77bf409ff6a238aa2da94cf7910f97b8f1f1e9
Mor download the zip and make a extra copy of kohya
Mkohya_ss-22.6.2.zip7.47MB
Jok thax for the help, will try when at home later tonight!
FYouTubeSECourses
Welcome to the Pillars of AI Application Libraries: How to Install Tutorial! 
Are you ready to embark on a journey of installing AI libraries and applications with ease? 
In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. 
We'll also show you ho...
Are you ready to embark on a journey of installing AI libraries and applications with ease? In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. We'll also show you ho...F18:18 How to do a git checkout to switch different branches such as dev branch
Fthe lo
Flogic is same for versions
BCreate an original character LoRA in one shot following this tutorial. https://everlyheights.tv/stablediffusion/create-an-original-character-lora-with-everly-heights-character-maker-free-template/
SI'm seeking an expert in Generative AI to create a text-to-image generation model prototype for me. Here are the key outcomes I'm expecting:
- The AI model must create cartoon-style images. A specialist with experience in this area will be a great fit. Knowledge in digital art or animation is a plus.
- The model should be fine tunes with images of mascots of different brands like McDonalds, Amul etc and final output should of genAI generated different images of the mascots
- The images should be small in size, less than 500x500 pixels. Experience with condensed data optimization and high-quality rendering is desired.
- I want the generated images to be in color. Proficiency in the standard RGB color model will be essential to meet this requirement.
Fi sent dm to you
Jhello, i tested with Kohya_ss 22.6.2 and the first results are promising. But i will do more tests over the weekend with different Models. Thanks for the Info!
Mglad to know, i think their is an issues with the new kohya because they intrduced many news options like huber schedule and other settings that the lora is not extracting properly
Fi just updated my config
Fit was broken again and was training text encoder 2
M@Furkan Gözükara SECourses have you noticed that style prompts are much harder to do without training the 2nd text encoder ?
Fstylized character output is harder i agree
Finstantid is better actually for stylized outputs
Myeah i noticed that quite a bit
MFwhat generates that? which tool?
Jthx, but what config, what do i need to dl ? not sure
FPatreon
Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon
Fdue to error of bmaltais it was training text encoder 2 with high LR