ULTIMATE SDXL LORA Training! Get THE BEST RESULTS!

Рет қаралды 195,476

Күн бұрын

In this video, I'll show you how to train LORA SDXL 1.0 using YOUR OWN IMAGES! I spend hundreds of hours testing, experimenting, and hundreds of dollars in cloud computing training to bring you the ultimate LORA training guide for complete beginners and experts alike. SDXL is incredibly easy to train as long as you know what you are doing with the right training parameters. And after this video, you’ll have the required knowledge to train anything you want with SDXL 1.0 LORA with the Kohya GUI tool.
What do you think of SDXL LORA training? Let me know in the comments!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
SOCIAL MEDIA LINKS!
✨ Support my work on Patreon: / aitrepreneur
⚔️ Join the Discord server: bit.ly/aitdiscord
🧠 My Second Channel THE MAKER LAIR: bit.ly/themakerlair
📧 Business Contact: theaitrepreneur@gmail.com
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✨ PATREON LINK: / aitrepreneur
Kohya ss GUI: github.com/bmaltais/kohya_ss
SDXL: huggingface.co/stabilityai/st...
Jup1t3R!
scale_parameter=False relative_step=False warmup_init=False
Runpod: bit.ly/runpodAi
Runpod Template: runpod.io/gsc?template=ya6013...
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
►► My PC & Favorite Gear:
i9-12900K: amzn.to/3L03tLG
RTX 3090 Gigabyte Vision OC : amzn.to/40ANaue
SAMSUNG 980 PRO SSD 2TB PCIe NVMe: amzn.to/3oBR0WO
Kingston FURY Beast 64GB 3200MHz DDR4 : amzn.to/3osdZ6z
iCUE 4000X - White: amzn.to/40y9BAk
ASRock Z690 DDR4 : amzn.to/3Amcxph
Corsair RM850 - White : amzn.to/3NbXlm2
Corsair iCUE SP120 : amzn.to/43WR9nW
Noctua NH-D15 chromax.Black : amzn.to/3H7qQSa
EDUP PCIe WiFi 6E Card Bluetooth : amzn.to/40t5Lsk
Recording Gear:
Rode PodMic : amzn.to/43ZvYlm
Rode AI-1 USB Audio Interface : amzn.to/3N6ybFk
Rode WS2 Microphone Pop Filter : amzn.to/3oIo9Qw
Elgato Wave Mic Arm : amzn.to/3LosH7D
Stagg XLR Cable - Black - 6M : amzn.to/3L5Fuue
FetHead Microphone Preamp : amzn.to/41TWQ4o
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Special thanks to Royal Emperor:
- Totoro
- TNSEE
Thank you so much for your support on Patreon! You are truly a glory to behold! Your generosity is immense, and it means the world to me. Thank you for helping me keep the lights on and the content flowing. Thank you very much!
#stablediffusion #sdxl #lora #aitraining #texttoimage #imagegeneration
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
WATCH MY MOST POPULAR VIDEOS:
RECOMMENDED WATCHING - All LLM & ChatGPT Video:
►► • CHATGPT
RECOMMENDED WATCHING - My "Tutorial" Playlist:
►► bit.ly/TuTPlaylist
Disclosure: Bear in mind that some of the links in this post are affiliate links and if you go through them to make a purchase I will earn a commission. Keep in mind that I link these companies and their products because of their quality and not because of the commission I receive from your purchases. The decision is yours, and whether or not you decide to buy something is completely up to you.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Timestamps:
00:00:00 - Train SDXL with LORA
00:00:41 - What is LORA?
00:01:20 - Koya SS GUI Installation
00:04:36 - Koya SS GUI Launch
00:05:29 - Image Dataset preparation
00:08:20 - SDXL LORA Training
00:09:28 - LORA Folder & Training Options
00:10:22 - Character Training Tips
00:12:54 - StarByFace & Celebrities Training
00:14:01 - SDXL Character Input
00:17:15 - Training Data & Image Captioning
00:19:44 - Kohya SS & Captioning Tips
00:21:58 - The right Training Parameters
00:24:33 - High batch size Model Comparisons
00:26:01 - Learning Rate for SDXL LORA
00:27:36 - Training Tips & LORA SDXL
00:28:31 - SDXL Image Resolution & Buckets
00:30:09 - LORA Network Rank & Network alpha
00:31:47 - Image Quality & Settings
00:32:53 - Training & VRAM Tips
00:34:37 - GPU Solutions & RunPod
00:36:09 - RunPod Setup for LORA Training
00:37:30 - Training Prep & Kohya Overview
00:39:43 - LORA Config & Data Setup
00:41:27 - Model & Captioning Setup
00:43:27 - Training Log & Model Saving
00:44:45 - Model Transfers & LORA Access
00:45:46 - Image Gen Settings & Tips
00:48:01 - How to select the right Model?
00:49:04 - Image Enhancement & Output
00:50:14 - Model Comparison & Saving
00:51:17 - Conclusion on LORA Training

Пікірлер: 519

@Aitrepreneur 10 ай бұрын

HELLO HUMANS! Thank you for watching & do NOT forget to LIKE and SUBSCRIBE For More Ai Updates. Thx

@Sandel99456 10 ай бұрын

This is a stupid guide for lazy people ..nothing more .. also, cropping is better, just not with brime .. also, dont use token unless you are planning on using sdxl only for your Lora

@TheCriticalMastermind 10 ай бұрын

Thank you for this explanation, I just wish the stable diffusion community would try Training more models on objects like plastic parts and craft objects like more every day objects we see in product design and also more animal models and nature. There are so many female characters when you go on these model websites and when you look for trained models more object based and like more animal and landscape based I feel the community is getting lost in the home made female characters. Please guys please can we start training some more object and crafts and tools and 3d models so we can start getting concepts for ideas for being more productive.

@jamesclow108 10 ай бұрын

@@Sandel99456 what would be non-lazy way?

@Sandel99456 10 ай бұрын

@jamesclow108 non lazy would be reading all about every setting in kohya and choosing settings based on knowledge rather than copying some stupid bot json file into ur pc 🙄

@jamesclow108 10 ай бұрын

@@Sandel99456 At least it's a reasonable way for folk to start off becoming familiar with the concepts. I bit like buying pre-made Pizza dough rather than making the dough yourself. Sure, in the long run if you want to have more control over the end pizza, you'll probably want to learn how to make the dough, but pre-made will at least enable a few concepts to be learned in a hands on way. Can you post links to the documentation you recommend that explains all of the settings, so folks can go to that if they have any questions after the video?

@mactheo2574 10 ай бұрын

Give a man a Lora, and you feed him for a day. Teach a man to train Lora, and you feed him for a lifetime. Much appreciated K!

@0AThijs 10 ай бұрын

Yep, been training without luck for months now 🥲

@prismglider5922 6 ай бұрын

Lora is a training method tho. Should be saying SDXL.

@MysteryGuitarMan 10 ай бұрын

Thank you @Aitrepreneur! I love that this tutorial dispels some myths about LoRAs. Especially the random token thing... starting all the way back from "sks", now to "omhw" - when you take Lensa and other apps like that into account, think of how many millions of GPU-hours have been wasted (they could have started from "person" or "portrait"). Only one thing to mention: You don't need regularization images unless you plan on merging in your LoRA into your checkpoint. Or some other pretty specific use cases, like de-overfitting a specific person / character / etc. That should speed up your training even more.

@Aitrepreneur 10 ай бұрын

Absolutely! Thank you so much for your help! ;)

@OriBengal 10 ай бұрын

@@Aitrepreneur @MysteryGuitarMan - I ran some tests side by side.... HUGE difference in how many steps were saved by using your celeb trick (which you taught, but with less certainty, back in the day). No Reg images. Superb results. Also... nice to know now that I look like Patrick Dempsey :)

@jamesclow108 10 ай бұрын

I just don't understand how omhw is the go-to rare token to use if you want to use a rare token. I started looking for a list of rare token that can be used with SDXL and found nothing :-(.

@OliNorwell 10 ай бұрын

@@jamesclow108 It dates back to the SD 1.5 days when it was shown to be a rare token, not sure there's any evidence out there that it's a rare token for SDXL necessarily.

@plejra 10 ай бұрын

Thanks a lot! I was also a little bit confused with regularization data. Anyway I'm looking for way to optimize settings for my old GTX 1080 Ti with only 11GB of VRAM

@BruceDailey 10 ай бұрын

Thank you. I've been trying to get a lora to work for months. This is the first video that worked. The link for an awesome runpod template was really appreciated.

@TransformXRED 10 ай бұрын

Edit : chapters are here now ---- Don't get me wrong... I'm very grateful for your videos. But you need to add chapters, especially for long videos like that. People will come back more easily to it multiple time to check the tutorial... Double win.

@SteveGamesOnline 10 ай бұрын

you mean time stamps?

@TransformXRED 10 ай бұрын

@@SteveGamesOnline Video chapters is how youtube call the feature. It's the same thing ;)

@noeltock 10 ай бұрын

Assuming he wants to increase engagement/time duration

@TransformXRED 10 ай бұрын

@@noeltock That's the only important metrics for a video to perform well on KZfaq. And "youtubers" want their videos to be watched, shared, by many people. I only stated that because chapters are beneficial for the creator too. Chapters are the best thing added to youtube. Aitrepreneur as a really good channel, I watch almost everything posted here. But I generally don't come back if there is another tutorial out there on the same subject, even if it's less polished... If the other videos have them (that's me, but I know others do that too). Same for podcasts. I watch it in full, but I never come back if I can't easily navigate (roughly) to the part I would like to listen again.

@MrGTAmodsgerman 10 ай бұрын

The video does have chapterts...

@aiviistudio 10 ай бұрын

Thank you @Aitrepreneur! I really love your contents. You have very deep knowledge about what you are doing and explain them very well. Can’t wait for your checkpoint training video ☺️

@Aitrepreneur 10 ай бұрын

I appreciate that! ;)

@DromaticGnome 6 ай бұрын

Thank you! I just joined your Patreon - looking forward to digging through all that you've created!

@SooNmus 10 ай бұрын

Thank you immensely for your insights 🙌. We previously approached some of these parameters from a distinct perspective. However, after implementing your suggestions, the outcomes were genuinely remarkable. Interestingly, several of our projects faced setbacks due to resolution concerns, and it never occurred to us that cropping was the culprit. Exceptional video content! 🌟

@graylife_ 10 ай бұрын

thanks man! I really appreciate the hard work. You've done an incredible job. I like how much you progressed since a year. Keep the good work going on.

@robxsiq7744 10 ай бұрын

from frustration to making amazing loras...thanks man!

@ScottTheis 10 ай бұрын

Missed you. Good to have you back. Thanks for all you work.

@kofteburger 10 ай бұрын

I've been looking forward to this.

@chuckbets8490 10 ай бұрын

Best results I have gotten ever with this tutorial Amazing stuff

@kallamamran 10 ай бұрын

Great video! As allways, BUT.... Focus is still on persons. This is greatly limiting since most models are allready great at creating images of persons, specific or non-specific. What I miss is a training video on how to train styles like "my own art style" or poses like "yoga/contorted/laying down poses" or maybe actions like "playing football/fishing/linedancing" and such... Just training a person (portrait/likeness) is what everyone and her mother has been doing since training has been introduced.

@EH21UTB 9 ай бұрын

Exactly, that's what I want also

@LonelionZK 7 ай бұрын

Same here. All I see is training on faces

@vokuh 10 ай бұрын

haha just 2 days after joining your patreon, you saved me 10 hours of work

@iamCryptobulls 10 ай бұрын

Such an amazing video! This has been so confusing so this video was very helpful!

@bobdelul 10 ай бұрын

Ok thats it. I've become a patreon now. Have access to your example Lora's will safe me tons of time figuring out what works and what not. Such a good idea!

@velly027 10 ай бұрын

Great work! Really helpful 👌

@bartmeeus9033 10 ай бұрын

Thanks for the in depth explanation and the hard work to create this video!

@AgustinCaniglia1992 10 ай бұрын

Amazing work. Thank you.

@mistercapitale 10 ай бұрын

This is a fantastic video. I will be a Patreon supporter just because of this video. Very smart. The marketing is strong with this one.

@doingtime20 4 ай бұрын

The best guide for Lora training, thanks!

@ejaykniep 10 ай бұрын

Can't wait! 😁

@CronoBJS 10 ай бұрын

I missed you Aitrepreneur! This is one of the most needed videos!

@elias9725 10 ай бұрын

Wow this video did not feel like ~1 hour - thanks for making such a comprehensive guide K!

@Aitrepreneur 10 ай бұрын

Glad you enjoyed it! It definitely felt like an eternity making it 🤣

@Ecker00 10 ай бұрын

wait... it was that long? I was so absorbed! Awesome research

@elias9725 10 ай бұрын

@@Aitrepreneur Haha I can imagine! 😂😂

@Always.Smarter 10 ай бұрын

ai generated comment

@MariusBLid 10 ай бұрын

Great work!

@rogerioshigo6751 10 ай бұрын

you are the best man keep the good work😄

@osojii 5 ай бұрын

Thank you so much! This tutorial helped me immensely :)

@mckachun 10 ай бұрын

masterclass~!! thanks for sharing~!!

@jacquesbynens3816 7 ай бұрын

You are a true sensei... infinite thanks for all these tutorials. U da man!

@maxp7984 10 ай бұрын

Very useful and detailed! Thanks a lot.

@Aitrepreneur 10 ай бұрын

Glad you enjoyed it!

@spookywaves 10 ай бұрын

Great video!

@keller2me 10 ай бұрын

Thank you very much. Your videos are fantastic and very detailed in content. If I may make a request, if it's in your plans or possible, could you do a little insight into the "Themes" as well as the characters in the picture training. It would be great to understand if there are substantial differences and I think the public would be grateful to you (at least I would be). Congratulations again for the excellent job in explaining everything and see you next time.

@ChrisR88 5 ай бұрын

I've tried so many tutorials in order to create a LoRa and the results were always subpar. With your guide and settings, I finally managed to make a proper Lora that works (almost) flawlessly! It isn't very flexible in terms of styles (it keeps it photographic, realistic) and with a net rank of 256 comes at 1.7gb, but it's the 1st actual LoRa that perfectly reproduces the face in +90%% of times, which is amazing! Thank you, @Aitrepreneur! Also, the runpod template was a time saver!

@TheKuzmann 10 ай бұрын

From my experience captions should be used in the following situations and in the following manner: use them in cases where you want to generate a specific scene, subject or concept. This of course depends on the dataset you're training on - if you're training an item, you need the dataset to consist only of that item with different backgrounds. If you are training a person's face or half body and want to generate images of that person, for example, dancing, training a model with captions that do not mention a person is dancing (or standing in a pose that implies movement, so the captions are written with the mention of it's hands in the air, describing a movement, etc.) will make it much more difficult or impossible for the model to generate a trained person dancing. On the other hand, if your dataset consists of images of a person dancing, using captions will make a desired "concept" (implying a certain person dancing, i.e. standing in a pose that implies movement etc) become a variable (I've seen that for it also a term "pruned" caption is used) which is easy to call up. On the other hand, in terms of style: training text encoder is undesirable, because you want to transfer a visual identity to the model, and most importantly, you want it to be "printed" on every possible prompt. In that case, only the class (style or aesthetics) is trained. The most common mistake is to train a style with regularization images plus text encoder (which I did for an absurdly long time training styles in dreambooth). Such a model is literally unusable and generates random images. Even training textual inversion for style using captions can make it less flexibile. I'm writng all this from my personal experience and from all the possible tutorials that exist on internet and KZfaq, and I've gone through ALL of them - including yours :-) I can't even mention how many failed models I've trained, and that's necessary to learn how to train a neural network.

@HestoySeghuro 10 ай бұрын

Styles+captions works. Styles+no captions you need to dissable t.e.. styles+regs is something I never tried.

@khush7233 9 ай бұрын

The important points are as follows: 1. Captions should be used strategically in training models for generating specific scenes, subjects, or concepts. 2. The effectiveness of using captions depends on the nature of the dataset. For example, training on a dataset with images of a person dancing requires captions that explicitly mention the person's actions to achieve desired results. 3. Using captions can make a desired concept (e.g., a person dancing) more accessible for the model to generate. 4. Training a text encoder for style is discouraged because the goal is to transfer visual identity and ensure it works with various prompts. 5. Combining style training with regularization images and a text encoder can result in an unusable model that generates random images. 6. Even training textual inversion for style using captions can reduce flexibility.

@MarcSpctr 10 ай бұрын

although, SD team are right about training being faster and easier with regular tokens rather than RANDOM TOKENS, it becomes useless if you want to use the trained Loras on different base model. So say tomorrow RealisticVision or similar base model is released for SDXL, using these Loras will result in inferior quality as compared to Loras that are trained FROM SCRATCH. So I would suggest if you plan to use other Base Models (which ofc everyone does), use RANDOM TOKENS like ohwx, ab12 or anything random stuff.

@jaoltr 10 ай бұрын

This is a really good point. HOWEVER: Are you speculating or do you have real world results? If you're speculating, it would be great if someone who has done some testing could weigh in and confirm or refute the assertion...

@leucome 10 ай бұрын

@@jaoltr Just logic seriously. If you use a token that exist your lora is going to be built on top of that. If this token look different in an other model then the lora will also look different. I had some real issue with the token vio turning my character into a violin or violet color on certain checkpoint. So now I dont take any chance and use weird rare token like bnhanlwx to avoid ending up with a broken lora.

@MysteryGuitarMan 10 ай бұрын

@MarcSpctr - that's not right, unless you use a very common token like "orange" or even worse a word fragment like "vio". "ohwx" will also exist in RealisticVisionXL or whatever XL community models come out. Since you started so much father away from your final target, you run an even higher risk of having to retrain your LoRA.

@leucome 10 ай бұрын

@@MysteryGuitarMan Yeah if everybody use the same rare token then it not rare anymore I had no issue with this yet but it is also likely.

@jaoltr 10 ай бұрын

@@leucome Thank you for sharing your experience, that's what I was looking for. I see the logic (that's why I thought it was a good point). But logical only means you have a hypothesis that needs to be tested. It doesn't mean you found truth. Concluding that something is true because it's logical is both a trap and a paradox since it's an illogical method to reach such a conclusion. As Deming said "In God we trust. All others must bring data."

@lumaceon3863 10 ай бұрын

I shudder to think how many hours I wasted cropping images manually. Thanks, this is insanely helpful!

@HO-cj3ut 10 ай бұрын

thank you so muchh , I liked this channel , the best

@testales 10 ай бұрын

The deprecated section is probably labeled that way because training with regularization images is more or less obsolete or has very specific use cases only. The model already has learned millions of things and proably can take a few images more. For concepts you may even be unable to generate regularization images in first place because the concept is not yet known. By overriding training of a celebrity you are damaging the model intentionally which regularizitation is supposed to prevent. But because the Lora is applied only temporary this doesn't matter anyway.

@CrazyCat-RU 10 ай бұрын

I'm writing through a translator - but in my opinion the regulation folder is greatly underestimated. I tried in SD1.5 in dataset to give a photo of children playing in the park, and in the regulation folder a photo with steam locomotives. ;-) As a result, lora drew a great children's railroad in the park and children playing with steam locomotives. :-)

@David-Codes 7 ай бұрын

But then how do you give your new person a new codename like zwx person

@itzpaco5539 10 ай бұрын

Thank you K ❤

@EpochEmerge 10 ай бұрын

I very much approve of the work done, I myself also tested different parameters and understand how much time it takes. The only remark I would like to make about the Seed (19:39, next to cache latents) parameter. If you need to test different parameters, they should be tested with a single seed, otherwise the training will be different every time. You can check it by making two loras with the same settings but different grains.Otherwise great video as well

@coulterjb22 9 ай бұрын

Simply amazing. 🤯

@ayanechan-yt 10 ай бұрын

Thank you, I was looking for a way to train a character with SDXL! This renewed my interest in Stable Diffusion :-)

@Aitrepreneur 10 ай бұрын

Great to hear!

@ayanechan-yt 10 ай бұрын

By the way, I have been meaning to ask... Are there any differences in picture quality between using a Lora vs using a fine-tuned model?

@ericruffy2124 10 ай бұрын

Thank God you're BACK... 😙

@amin5127 10 ай бұрын

Hey it would be nice to see a style training guide for SDXL 1.0

@Aitrepreneur 10 ай бұрын

What I show in this video should be enough but I could make a specialized video just for this

@think.feel.travel 10 ай бұрын

Yes it would be very appreciated as I suppose that Lora could be way more useful than replicating a celebrity (I don't really know why one should use Lora to do that ahah) 😂 Thank you a lot for your videos! @@Aitrepreneur

@lennylein 10 ай бұрын

Yes please 😊

@natsuschiffer8316 10 ай бұрын

When SDXL Dreambooth!! Thanks for the video!

@jamesclow108 10 ай бұрын

Thank you, thanks to this video I've been able to take my first step in lora training. I decided to try my first attempt with your Margot Robbie set and a batch size of 2, as I have 24GB VRAM and wanted to see the speed. Looking at about two and a half hours and 17.6GB VRAM. It's gotten me curious though about the level of detail, and the best way to maximize the possible level of detail. The training images and regularization images are jpg. If you wanted to get the highest quality possible, would it be better to use png or would the difference be so negligable that it isn't worth it. Reason I ask is that I've noticed the trend of waxy looking low skin detail people images generated out there and wondered if only using training and regularization images with decent skin detail would solve that issue?

@c0nsumption 10 ай бұрын

This man is the GOAT

@OriBengal 10 ай бұрын

Glad to see you doing visual stuff again, not just LLM's. I support you pursuing all your passions, of course - but you were one of the best at creating really useful visual tutorials.

@odawgthat3896 10 ай бұрын

Thats what I told him lol, good to get back to SD

@OriBengal 10 ай бұрын

@@odawgthat3896 K was one of the best.... IS one of the best... as this video clearly demonstrates! :)

@odawgthat3896 10 ай бұрын

@@OriBengal Yeah 100%

@celebAIdance 10 ай бұрын

Can someone answer this? If i am generating full body photos, i also need full body photos during lora training or its only the face that matters?

@abdelhakkhalil7684 10 ай бұрын

You know, you can keep the less trained LoRa as your main LoRA and use the more trained one in the positive prompt for ADetailer. This way, you get both flexibility and details.

@technocore1591 10 ай бұрын

Big thanks! I joined your patreon for the files!!! THE FILES!!!! Lol thanks, dude. What does dreambooth for SDXL look like?

@augustolacerda3560 10 ай бұрын

Mr.(?) K, your videos are always amazing. I'd like to suggest some more in depth content on the minor things related to training. Like assembling a set of regularization images. I have also been looking for information on training models for text AI (Oobabooga models and so on) but I couldn't find the text AI community or information related to training.

@OriBengal 10 ай бұрын

Hey K - Great tutorial. I've been watching a bunch of Lora tutorials recently.... You've definitely simplified it. Question for you-- Where did that Runpod Khoya image come from? They don't have that listed on their pull down of images. This is way better than manually installing it, etc.

@AYAhigheye Ай бұрын

super like man!

@aimademerich 7 ай бұрын

Phenomenal 🎉

@jrobertsz71 10 ай бұрын

All I can say is Wow!

@juggz143 10 ай бұрын

@Aitrepreneur I just wanted to point out 2 settings that it seems you may have misunderstood. At around @30:00 you mention that the "cache text encoder outputs" option is broken and suggest not to use it for now, then later at @32:50 you mention the parameter "--network_train_unet_only" and how the difference is negligible and suggest people not to use it either, BUT if you use the "--network_train_unet_only" command it fixes the "cache text encoder outputs" command. Together they use significantly less vram and makes training much faster. So the difference is negligible and the training is way faster if you use them in combination. Give it a try and you may recommend the opposite of your conclusions testing them separately.

@ESGamingCentral 10 ай бұрын

is it normal for a 4090 to do 2.45s/it ? I'm trying this tutorial but I was expecting the card to be faster.

@HO-cj3ut 10 ай бұрын

olabilir

@nikoleifalkon 10 ай бұрын

he has 3090 not 4090 @@ESGamingCentral

@tazztone 9 ай бұрын

@@ESGamingCentral mine is pretty fast now (1.5sec/it) with 3090 (9 training images) Network Rank (Dimension): 128 added --network_train_unet_only and checked "cache text encoder outputs"

@ESGamingCentral 9 ай бұрын

@@tazztone what drivers?

@yoniattlan3870 Ай бұрын

Perfect ! Thank you ! Can i install Kohya GUI tool with a macbook ?

@bricenuzzo7747 10 ай бұрын

This is pure gold, thank you and congratulations, you won my patreon subscription !

@marcelschuberth9709 6 ай бұрын

just a little hint since reopening the file to check the status is pretty annoying and inefficient, use tail -f instead, it prints the last 10 lines (by default, can be specified with -n ) of a file and -f sets the flag for it to update whenever new lines are added. it even handles progress bars correctly instead of printing a new line for each update

@Gardiance 10 ай бұрын

Thank you, Bro. Loads of hours and $ used to create this video. You always do a good job ❤

@Aitrepreneur 10 ай бұрын

Much appreciated!

@touchdownchef 5 ай бұрын

The video was very helpful. Thank you. If there are any differences between working on LoRa and checkpoint models, even slight ones, what would those differences be? Additionally, do you have plans to upload a video tutorial on creating checkpoints for the SDXL version? There seems to be no related tutorials on KZfaq, and it would be greatly beneficial.

@wndrflx 9 ай бұрын

Is there a reason for selecting the original image folder when captioning, or could we select the Kohya structure image folder and caption from there so you wouldn't need to move the txt files?

@ashish-lk9lx 10 ай бұрын

having regularization images at 768x768 or 1024x1024 is important beacuse i have random image of very high resolution so can i use random sizes?

@jdietzVispop 10 ай бұрын

Legend

@wholeness 10 ай бұрын

This whole tutorial was legendary. Became a Patreon member without hesitation and never looked back. These one click installs are incredible!

@theboyjohnny123 9 ай бұрын

Thanks for the great tutorial! What should be the ideal number of classification images ? (i have 22 training images)

@swordfish949 10 ай бұрын

Quick question about the cropping part. Would you say the same goes if you are making a style lora? Is cropping to a 512x512 better or worse for styles?

@NeonXXP 10 ай бұрын

Haven't played with stable diffusion in months. Thought I'd hit you up and see if there were new fast and easy ways to train on specific people.

@BlueScorpioZA 10 ай бұрын

As far as flexibility is concerned with LoRA models, one could always use a model that has more training, which has a photo realistic look when used at full strength, but simply reduce the strength of that LoRA when attempting to apply a non photo-realistic style to it. Eg. would look like a photo but or even lower would still give you a good resemblance to your character but would also be flexible enough to allow non-photorealistic styles applied to it.

@TheRemarkableN 10 ай бұрын

You are doing the AI gods’ work 🙏. Thank you good sir. You also have excellent taste in celebrities.

@ApexArtistX 10 ай бұрын

Capital G is wrong grammar

@TheRemarkableN 10 ай бұрын

@@ApexArtistX Thanks! 👍

@ccelik97 10 ай бұрын

> "You also have excellent taste in celebrities." History repeats itself I guess lol. E.g. "Lenna".

@damasoroma 6 ай бұрын

Hi, Thanks a million for your efforts and your tutorial, I watched so many tricks thanks to your video! I was wondering I could I create a specific part of a body I would like to focus on man's chest (muscles and hair) and I was wondering if I need to takejust chest training images or the full body pictures of a man. And what about regularization pics? Should I take just chest or face or the full body? I'm a bit confused. Thanks a million!

@spearcy 10 ай бұрын

Your hugest YT vid ever!

@Proveloski 10 ай бұрын

Hi @Aitrepreneur ! Love the video! Could you make a video on how to use these models in Stable Warp Fusion? I want to make an animation like the Corridor Crew did with Anime Rock Paper Scissors using the SDXL LORA I made with this tutorial, but I'm not a warpfusion expert, especially with SDXL.

@wndrflx 9 ай бұрын

If you have a 4090, do you still use the Adafactor optimizer, with the additional arguments, or is that only for those with lower vram?

@Kujamon 5 ай бұрын

Does this still install every file into the local windows drive, no matter where you run it from? I couldn't use it before because there was not enough space on the windows drive.

@exiacyn4621 3 ай бұрын

Fantastic video, I'd really love to see a tutortial on how to do Lora training using One Trainer which seems to have a way better interface and more useful features like masking.

@camprey 10 ай бұрын

Hi! While in runpod, the runtime of my pod started but the fourth link (the one with jupyter) says "HTTP Service [Port 8888] Not Ready". Is that normal? Or do i just have to wait it out? Edit: I terminated the pod and started a new one. That fixed it

@TheKuzmann 10 ай бұрын

33:33 ...for style training, what you definitely don't want is for certain words (tokens) in the captions to be associated with the data set, and for images from the data set to pop up with those words in the prompt. for this reason style training is done with little or no text encoder tuning, and really smart captions

@chuckbets8490 6 ай бұрын

Could you re-do this training. it seems something have changed on the runpod side.

@GavrikCat 10 ай бұрын

linked runpod template doesn't seems to work, even after I terminated the pod

@ElGalloUltimo 4 ай бұрын

On my first try, I just dumped 56 images in the training folder thinking it would help. I had 22000 training steps it was going to take 14 hours on a 4090. After figuring out how long it was going to take, I promptly went back and followed the video's advice to the letter with only 12 images and had a similar training time to the video.

@AlterMax24-YouTube 7 ай бұрын

This is strictly amazing. I have a little question. Is XL necessary? Or does it work with SD1.5? Same question for objects and clothing LoRa! THANK YOU'

@joepark81 8 ай бұрын

First of all, there is no sufficient explanation on configuration files. It seems the only way to get them, is to be your patron. Your customized configuration files for your patrons, well that's okay. But this whole video could have been much more useful if you mentioned where to get other configuration files, or at least how to make one. Second, the gui version you are using must be outdated, -or-, it must have some addon that you didn't mention. I've just done a fresh install of Kohya ss and THERE IS NO DEPRICATED TAB UNDER LORA - TOOLS!!! And I've just found out that in my GUI the tab is named, "Dataset Preparation."

@phily8020 7 ай бұрын

It's like a half cooked tutorial

@vilainsinge5282 4 ай бұрын

ever heard of "updates" my friend ?

@mixxfish 4 ай бұрын

Did you ever get an answer?

@kishirisu1268 22 күн бұрын

He just a pathetic unskilled amateur scammer..

@OttoMaticInc 10 ай бұрын

K! Brother, your work is amazing, not just here but in general. I have been learning next to everything I know about AI from you and just when I think I must be in the top 10% of AI users, you come along and shatter this limit again. Thank you so much, this was exactly what I needed to proceed with my own work here on KZfaq. Also just now I doubted the concept of tutorial style videos being a solid game plan for the KZfaqs and yet here you are, crushing it again! Know you have my respect and please do keep going. Cheers!

@ssjgokillo 10 ай бұрын

This was really helpful, but I wish you had also included information on settings for Styles (like what instance/class prompts to use). Also what if we're doing a LORA based on a cartoon character that there isn't a celebrity likeness for?

@thedesigngraphik 10 ай бұрын

I feel your pain, over a year now of many great videos from stable diffusion KZfaqrs, but its always, and yes 100% always, about training people. It's like nobody is using AI with their own artwork as the training source?

@BlackMita 10 ай бұрын

Truuue

@anonymousanonim7615 10 ай бұрын

@@thedesigngraphik i want to create a clothing style for training, now i'm still stuck at sd 1.5 lol

@renssjjee 6 ай бұрын

when i input the downloaded folders into the lora folder I don't see them inside stable diffusion, i can put them inside models/stable-diffusion and use them as checkpoint...dit i put a setting wrong?

@MathisDaudebourg 10 ай бұрын

Thank you for this very comprehensive tutorial. I have a question, I have a pc not powerful enough to generate LORA with Kohya. So I used the Pods method to be able to generate my Lora. Once the work is done on Kohya, do we still need the Pod system on Stable Diffusion or not?

@stanpikaliri1621 10 ай бұрын

I personally would just train it in CPU mode only with hight parameters because I have 128GB of ddr ram. It also should be much simpler with less stuff to setup and I don’t need RTX card or runpod. To be honest I expected to see how to do it in this video but he only show us how to do it by using GPUs.

@flonixcorn 10 ай бұрын

Yes let's goo finally a good lora tut 🎉❤

@Jensemann099 7 ай бұрын

Could you may make another video for lora concept training like "superhuman strength"?

@-Belshazzar- 8 ай бұрын

Thank you for this tutorial, my only problem is that if I use a different celeb name for the instance prompt, that is kind of counter intuitive, since now i am using a name of a different person to create the images of my character. And what happens if I want later to use the celeb character in it's own model? his name is already taken for my character. Also, I want the prompt to be the ACTUAL name of the person I am training.

@tds_FrankOfficiel 8 ай бұрын

the setup does not find python and it is impossible to install visual studio because it cannot find the file "vc_runtimeAdditional_x64.msi" and the solutions found on Microsoft support do not work, I have already had this problem for months

@MacLarenT1337 9 ай бұрын

Amazing, so much information for free. Thank you so much and will definitely be supporting on Patreon!

@HestoySeghuro 10 ай бұрын

Ok.. so if I want to custom train peter mohrbacher style do I need to use regs images AND petermohrbacher as instance?

@sherlockholmes3454 10 ай бұрын

you are the best

@ackiamm 10 ай бұрын

Thanks

@eladbelleli3489 7 ай бұрын

I'm running into problem when trying to train with runpods, i do exactly as it is in the video but when the first epoch starts it just breaks down. i chose the right vram settings and all the parameters are exactly as the videos suggests. any help with that?

@CrazyCat-RU 10 ай бұрын

Data set 40photo - in the REG folder 100 photos - when running in the REG folder created files with extension .NPZ - but only for the first 40 photos - the rest seem to be unused. Where in the settings to enable that in the regulation folder could be used more photos than in the dataset?