LORA + Checkpoint Model Training GUIDE - Get the BEST RESULTS super easy

Рет қаралды 303,218

Жыл бұрын

This LORA + Checkpoint Model Training Guide explains the full process to you. Learn how to select the best images. How to key word tag the Images for Lora and Checkpoint Training. How may steps and Epochs to use in Training. How to Merge Models to get better results.
#### Link from my Video ####
Join my Discord: discord.gg/XKAk7GUzAW
Bulk Resize: bulkresizephotos.com/en
Kohya-ss Install: github.com/bmaltais/kohya_ss
Booru Dataset Tag Manager: github.com/starik222/BooruDatasetTagManager/releases/tag/v1.6.3
SD 1.5 Training Model: huggingface.co/runwayml/stable-diffusion-v1-5/tree/main
Support my Channel:
kzfaq.info/love/CKx8mAHiFus-XYQLy_WnaAjoin
Subscribe to my Newsletter for FREE: My Newsletter: oliviotutorials.podia.com/newsletter
How to get started with Midjourney: kzfaq.info/get/bejne/frd8oaVn1rLahZs.html
Midjourney Settings explained: kzfaq.info/get/bejne/oL-WiK-Unp-8eWw.html
Best Midjourney Resources: kzfaq.info/get/bejne/f5N1iq1psqyym6c.html
Make better Midjourney Prompts: kzfaq.info/get/bejne/p5eklLGDmLyadpc.html
My Facebook PHOTOGRAPHY group: groups/oliviotutorials.superfan/
My Affinity Photo Creative Packs: gumroad.com/sarikasat
My Patreon Page: www.patreon.com/sarikas
All my Social Media Accounts: linktr.ee/oliviotutorials

Пікірлер: 350

@OlivioSarikas Жыл бұрын

#### Link from my Video #### Join my Discord: discord.gg/XKAk7GUzAW Bulk Resize: bulkresizephotos.com/en Kohya-ss Install: github.com/bmaltais/kohya_ss Booru Dataset Tag Manager: github.com/starik222/BooruDatasetTagManager/releases/tag/v1.6.3 SD 1.5 Training Model: huggingface.co/runwayml/stable-diffusion-v1-5/tree/main

@yokipop9467 Жыл бұрын

make tutorial finetune on kohya please..

@tripleheadedmonkey6613 Жыл бұрын

Great video, but aren't HyperNetwork's also an option? Is there any reason why we'd use Lora's over Hyper Networks? So far I've gotten better results training HyperNetworks, but admittedly Lora's had only just arrived on the scene when I was experimenting.

@user-hs9ti5mk4n Жыл бұрын

everytime I paste the cmd i get ''fatal: could not create leading directories of 'kohya_ss.\setup.bat': Invalid argument'' can anyone help

@ima5ami416 8 ай бұрын

do you know how feasible it is to install Stable Diffusion on a Mac? for example Mac Mini M2 Pro? Will it work by running it on a virtual machine to windows or will it be better via bootcamp? or is there a Mac direct version?

@DivinityIsPurity Жыл бұрын

I like this guy, he's like a nerdy hugging bear man you wana hold and thank for making such cool helpful channel.

@sub-jec-tiv Жыл бұрын

Best comment of the day 🥇

@technoprincess95 10 ай бұрын

Sometimes i think he is AI

@Xanderfied 9 ай бұрын

"Hugging face guy" lol

@bargbikernes31 6 ай бұрын

Down bad

@user-uh7nz5wl3x 11 ай бұрын

This is the most comprehensive model training tutorial I've found on KZfaq. Thank you for making this video!

@thefablestudio 7 ай бұрын

Your guide on LORA and Checkpoint Model Training is a game-changer. The merging trick you shared is pure gold. Subscribed! 🙌

@user-ps6ns1sb4f Жыл бұрын

Thank you very much. Your detailed introduction is very rare, and many of the details have been very helpful to me.

@jakehajek7116 11 ай бұрын

Really love your content, thank you for taking the time to produce and share it!

@zimnelredoran9985 Жыл бұрын

I may have missed the Lora training, I followed the Kohya installation and the checkpoint training. Thanks for all the excellent content, Olivio!

@mastixmc Жыл бұрын

One of your best videos so far!!! And currently my favorite KZfaqr for SD. Greetings to Vienna from Stuttgart, Germany. Sascha

@planetfrog2 Жыл бұрын

Thanks Olivio, I was just thinking I needed a guide like this after getting tired of google colab. This will be invaluable - your're a super star!

@JustFeral Жыл бұрын

Dude I watch all your videos even if I already know what it's about just to bump your numbers. Same reason for this comment. You're killing it.

@electropentatonic 8 ай бұрын

Of everything I learned, you blew my mind with the f2 trick

@BernardMaltais Жыл бұрын

Fantastic job Olivio! I really appreciate the work you do!

@BrandosLounge Жыл бұрын

I've been waiting on a video like this for ages! Thank you so much

@1lllllllll1 4 күн бұрын

I am so grateful for your detailed tutorials, step by step instructions. A big thank you.

@beantacoai 10 ай бұрын

Thank you for this awesome guide! Anything about regularization images would also be fantastic.

@sebastianh.9211 Жыл бұрын

A really helpful and informative video. In addition, and I find this particularly important, your pronunciation is also really super. For me, as a non-native speaker, this is very important. In many videos, people just mumble to themselves, or you can not understand them so well for technical reasons. With your videos I found the first time someone I can really understand excellent and crystal clear. 😊

@user-zb9qe8qe3d Жыл бұрын

Super cool! Please continue describe this topic for us in your next videos, I am waiting for those

@dagrinde1 Жыл бұрын

Thanks for this informative video. I have been trying to figure this out for awhile, so this was right on time

@SaberOW Жыл бұрын

Lol I was just looking for an updated LoRA guide, great timing thank you!

@musikrausch2675 Жыл бұрын

Danke! :) Thanks Olivio for your many great explanation videos and tutorials and that you made the effort to really go through every step of the setup and first usage of kohya. I needed exactly this to get to a starting point of the mysterious journey of training my own models/loras and now I can finally experiment on my own.

@bobchang325 Жыл бұрын

Thank you very very much! This lecture has answered a lot of my questions.

@MrHuman002 7 ай бұрын

That tag manager is really cool, thanks for that.

@powerofpeople123 11 ай бұрын

You take your time, talk with no rush but also go straight to the point. Thanks a lot, really helping me now that most tutorials are outdated

@RompinDonkey-bv8qe 2 ай бұрын

Agreed, he gets the pace just right. Not easy to do, some people take too much time with no benefit, some too fast and hard to follow. The balance here is just right 👌

@jgodvliet Жыл бұрын

So cool, thanks for the indepth explanation 👍

@STSchwanitz 7 ай бұрын

Thank you for guiding me with this excellent video!

@N1ghtR1der666 Жыл бұрын

the taging changes a fair bit depending on if your trying to train a topic or a style or a specific person and it would be nice to show the differences there. i see in on another video they explained how you should tag everything you DONT want to be a part of your lora unless you are training for a single person or thing, and I wold like to see a more in depth dive into tagging and its effects

@Beltalowda55 Жыл бұрын

The tagging strategy is a pretty confusing. I've also seen tutorials that say you should tag only the things you DO want to be part of your lora/model. And some tutorials say to not use tags at all and let the AI figure it all out. And should you use a unique "keyword" tag to train it to that particular unique "keyword" to use in the prompts? I've tried different the approaches but didn't get any conclusive results. They were all pretty bad and didn't work as expected. 🤨 A video from Olivio covering just the tagging aspect with a demo for each approach would be awesome.

@fritt_wastaken Жыл бұрын

@@Beltalowda55 captions are what a model uses to try and predict what the picture should look like during training. Difference between predicted and actual image is used to adjust the model in the right direction. So it should be obvious that you want to describe everything that is not a part of the concept you're trying to learn, to help the model to make a correct prediction and narrow the direction for the learning. Keyword is added for the model to associate the concept with that keyword, that helps to preserve sanity. It sould be noted though that the training process does not actually differentiate what you're trying to learn in any way. All it does is it tries to match a predicted image with the actual image. That means it can associate to your concept any other or multiple tags you used in unpredictable ways, basically splitting the concept between them. To mitigate that, no tag except a keyword should be used too frequently (in my experience 30-50% is the limit)

@Gh0sty.14 11 ай бұрын

I don't even bother tagging anymore when training a person.

@hcfgaming401 9 ай бұрын

@@fritt_wastakenI wish you had some videos up to talk about this. I think I understand what you're saying but some of it is a little fuzzy. Thank you for the info nonetheless.

@zz-sf1bm 8 ай бұрын

lovely vid, keep on these good works!

@ScaryStoriesNYC 10 ай бұрын

Te trouble with all these tutorials is that when I spend an entire day following them, the software I see does not ever seem to match the software in the video. When I reach an error screen, I never know why and I have no comprehension of what to do about it. It's quite daunting for an artist who thought the only thing he would have to master in life was using a pencil and a brush. :(

@Whisper_InThe_Rain Жыл бұрын

this video helped me understand a lot for another project im working on for langague model to use LoRAs to beef and nudge the actual model.

@activemotionpictures 11 ай бұрын

Thank you for explaining very clearly all the concepts that apply to creating LORAs. I really appreciate the info in the video.

@MrGTAmodsgerman Жыл бұрын

This video was really needed. Thanks for that

@edmoartist Жыл бұрын

Thanks so much for this video! really appreciate it

@ShiroMev14 6 ай бұрын

THX! I learned so much! You are amazing

@DmitriySokhach Жыл бұрын

You are my hero today! ❤ I was searching for exact this topic weekly for last 2 months 😂 Last time was this morning. Not sure if I go to sleep now or give it a try 😅

@bloomandfly6687 Жыл бұрын

Allez dormir heureux si vous etes fatigué. Vous serez frais le lendemain pour rêvé éveillé.

@bgill7475 Жыл бұрын

Thank you so much for this ❤

@peterprutser3451 9 ай бұрын

Great stuff, thanks

@caseyj789456 4 ай бұрын

Thanks a lot I get more information about training now 😊

@burgerhattingh8625 5 ай бұрын

This is awesome, thanks. I think you did a great job on disseminating the critical information concisely, I wish more tutorials were done like this. I have a question, how would training for an illustration style, using real photos for face reference differ, if at all?

@MartinGall1 10 ай бұрын

Thanks for the F2 rename files trick... I didn't know about it, you just saved me hours of renaming 😄

@viplivesmatter 5 ай бұрын

6:33 Lora and Models 17:50 Lora Training: files and folders 18:53 KoyaSS: the software to train the models

@nikoleifalkon Жыл бұрын

24:08 the same when you said "512x512" is in the past, the same goes to folder structure, is not necessary to create 3 folders, only the image folder and the inside folder with your dataset, for model and log you can leave the main folder "Neon" and the files will be saved there with no problems, I discovered that by accident and no issues after.

@ysy69 Жыл бұрын

Excellent Tutorial!!!!

@robertzerkin4332 8 ай бұрын

Good evening Olivio, So I just followed your guide to create my first LORA but I find myself with 22 hours of training! I must have made a mistake somewhere ;-) However, I have an RTX 4070 TI and a Core I9 13900k. 120 photos of the same model in high quality (FHD) half are faces and the other is the full length model. I chose 10 steps, I think my concern comes from there. I'm still going to let it finish just out of curiosity. Thank you for the guide which will have nevertheless been very useful to me.

@danielbenson506 9 ай бұрын

Fantastic tutorial Olivio! Love all your AI videos. Can you use LORA to train other objects and keep them consistent? Using your technique, I've been trying to create a LORA of a specific baseball glove and a specific helmet, and apply it to an image of a baseball player in stadium. Most of the outputs I get are quite monstrous like 10 finger alien gloves. I've given it a ton of data like close up/medium shots of the glove from multiple angles, medium and wide shot of someone wearing the glove. Still nothing works. Any thoughts on how to train a LORA to keep something like a glove consistent? I'm using using SD v1.5 pruned, photon v1, realistic vision v40 as the checkpoints in A1111.

@oaahmed7515 Жыл бұрын

Wow wow wow what a man. I was waiting for this video

@OlivioSarikas Жыл бұрын

Hope you enjoy it and it help you a lot :)

@oaahmed7515 Жыл бұрын

@@OlivioSarikas thx oli

@antoine-ce4oe Жыл бұрын

nice ive been waiting for this video !

@OlivioSarikas Жыл бұрын

Took me forever to record this ;)

@ens_lucis 7 ай бұрын

Hello Olivio! What Laptop you were using in this video? I have RTX 3050 Ti and it only has 4gb vram, it is interesting that your laptop has 16gb vram.

@ScreamToTheSkyS Жыл бұрын

was waiting on this update !

@Max-Blaze Жыл бұрын

Thank you for explaining

@PL-808 11 ай бұрын

Perfect tutorial. Thanks for your work 😊🙏 I have noticed there is now also LoHa, have you tested, compared? Otherwise I’m very happy to use this workflow

@pastuh Жыл бұрын

Video is super simple compared to others :)

@ghilesbardi Жыл бұрын

Thank you so much sir, I love your YT channel ! =)

@OlivioSarikas Жыл бұрын

Thank you :)

@ceelentzpotter2110 Жыл бұрын

Watch so many of your vids and I thought I've already subscribed to you. Until today I find out😅😅 Sub'ed anyways

@kallamamran Жыл бұрын

Great explanation!

@poponium Жыл бұрын

My hero ! many thanks

@huexley Жыл бұрын

Thank you so much !

@rudityasw.a1823 8 ай бұрын

Hai thanks for the videos I'm new on the AI generated field, so what is the difference with Checkpoint and LoRa?

@ForsgardPeter 9 ай бұрын

Thanks. This video helped a lot. However i do have aproblem with Kohya. All the buttons are not working so cannot really do anything. The is a warnig about LD Library in Terminbal. Am i missing some files or what is going on?

@farvardinmainyu1961 Жыл бұрын

Thank you Olivio.

@siriusrha Жыл бұрын

18:41....👀I didn't know that trick 👍🏻 Thanks

@caglisto Жыл бұрын

Thank you! Can you create the video with the colab as well? don't know if the old ones around still work, this things change so fast!

@user-xb4pu1cp6c 11 ай бұрын

Thank for sharing. 😁😁

@MaryBeeMusic Ай бұрын

Thank you!!

@ZhiwanCheung Ай бұрын

Great video Olivio! As I am watching this, I wonder what goes into the "log" folder and "model" folder? I didn't see what those are for. Also, do we need regularization images? If so, how many?

@ima5ami416 8 ай бұрын

@oliviosarikas do you know how feasible it is to install Stable Diffusion on a Mac? for example Mac Mini M2 Pro? Will it work by running it on a virtual machine to windows or will it be better via bootcamp? or is there a Mac direct version? Thanks

@gattaplayer 11 ай бұрын

Hi Olivio, thanks for this guide, it's a bundle of usefull informations. I have a question: at 30:56, when there's your Kohya full screen, I read "Learning rate: 0.00001", the default should be 0.0001, is this correct?

@DeFirm- 8 ай бұрын

with my rtx3050 8gb vram, it take 88hours to train (15 image x 20 train x 10 epoch ) / 1 train batch size = total 3000 steps i'm using max resolution 768,768 even if i change the resolution to 516x516 it still take a longer time if i use lora, to train same size steps it take 12 hours is it mean i need to upgrade my VGA, or are there still a way to fast the train? I really wanted to make my own check point, i saw on another YT, they train their own model using like google colab, i never used that before, or any other cloud base, but can i download the checkpoint to use on my computer later after train in cloud? Edit : I change the train batch size to 4 and max resolution to 516x516, now my total steps are 750 and i still need time 23 hours to finish the training :")

@erans 8 ай бұрын

Can we merge a lora model made with the SDXL base 1.0 with something like realistic vision?

@KiWelten Жыл бұрын

Hey Olivio, what tool are you using to record your videos, i like the zoom on several parts of the video, but don´t know how you do it :)

@lechefski 10 ай бұрын

Is there an option to set the set the gradients to 'None' in Kohya? That's a recommendation for 12GB vram and smaller GPUs from the DreamBooth documentation, but I can't find that option in the UI... And as always, thanks for always breaking things down for the layman Olli!

@___x__x_r___xa__x_____f______ Жыл бұрын

Hey Olivio, great vidio. Really go deep and surface all in one. I have a question. The style model I want to use is Dreamlike Photorealistic, from the same people as realisticvision. In your case you trained with sd15 in Kohya-Dreambooth (with captions for training dataset), but your video is entitled Lora. With Lora I usually use class dataset and Training dataset. Not sure if that was intentional. But more to the point, should i train with SD15 and merge to Dreamlike, go apply that style? Should I also use captions? I am doing Lora,thought. Thanks

@bautibunge737 11 ай бұрын

If I understand correctly, the merge is just a weighted average of the model weights, so the shapes of the models must be the same. So you should merge your LoRA with another LoRA that fits the style you like

@SaRa1000Channel Жыл бұрын

Nice VDO as usual. You mentioned in the VDO that you will cover both Dreambooth & Dreamboot LoRA; however, there has been no Dreamboot LoRA covered. I am not sure whether both Dreambooth & Dreamboot LoRA will have the same process & pretrain model or not? For art painting style training using Dreamboot LoRA, could you please suggest an appropriate Pretrained Model, and min. total step for each Epoch. I tried 100 Steps for sample 20 images (2000 in total) but when I tested with text prompts used in the training, the results were still far from original images. Also tried with LyCORIS/LoCon but with no success. I would be very appreciated if you could demonstrate how to train a painting style like Van Gogh painting style (though it is already available in some models) showing that the result from prompts used in the training process can reproduce images used in the training.

@BubbleTea033 11 ай бұрын

Dreambooth doesn't make LORAs. It trains a model, then you can extract a LORA from that by comparing the original base model and the trained model. You can see the tabs for that in the video when he's looking over the Dreambooth GUI.

@blackvx 11 ай бұрын

Thank you so much, Olivio! Is the training feature on Automatic1111 still broken?

@aearone 11 ай бұрын

Hi Olivio! I would like to know how much regularization images are needed when training a game character (in my case Rogue from Cyberpunk 2077), as she has a slightly off-topic appearance, punk clothes, hairstyle and cyberimplants. And I don't understand if I need to use regularization images when training the model. And if so, what token to use to classify this game character... It's very hard to understand. I would also like to know if I'm training LoRA at 768x768 resolution on an SD 1.5 model, and if I do need to use regularization images, what resolution should I take them in when training at this resolution? Should I use 512x512 or do I need 768x768?

@DioHard Жыл бұрын

Awesome video! Big thanks. I am starting to think that my hardware might be not up to this... whenever I run the kohya gui bat it just closes itself.

@susankosti 3 ай бұрын

Hey Legend! I fell in love with your tutorials! I have a question: this is not working on my laptop and on my server as well :( I have 2080 RTX in both. Can this be the reason? In my server there are 2x2070... do you have any other method to train models for stable diffusion?

@audiogus2651 Жыл бұрын

Would love to see something like this but from the perspective of objects, not portraits.

@jackyngan3251 10 ай бұрын

Same

@touchdownchef Жыл бұрын

I watched the video and it was very helpful. Could you provide additional explanation about learning in DreamBooth? There is no detailed explanation about additional learning in DreamBooth on KZfaq. I tried to learn by adding clothing styles after making the model myself, but the model's face gets distorted due to additional learning. I don't know what the problem is. It would be very helpful if there were video lectures about additional learning in DreamBooth. By the way, I'm using the PC version. Thank you.

@polipano 5 ай бұрын

Thank you Olivio for this tutorial as well as for all your others. Great help. When I run my LORA models on my Automatic 1111, I get “ValueError: not enough values to unpack (expected 2, got 1)”. How can I fix that? Thanks for your help.

@thediydaddy Жыл бұрын

Would definitely like a online workflow video

@gmartinez1981 11 ай бұрын

mostly installation instructions very clear but not what I was expecting

@619Shippo 10 ай бұрын

The Kohya page and download isn't the same as in this video and the setup.bat file has been updated. It doesn't ask me the same questions as it does him in the video. How did you get it to work?

@shadowtest Жыл бұрын

Hi, thanks for the amazing video, I learned so much! - I was curious, when configuring the model training, what if you set the base "pretrained" model as the one you end up using in the checkpoint merger instead of SD 1.5? Is there a difference? - Do you plan on covering on how to configure the LoRA training, or is it the same thing?

@shadowtest Жыл бұрын

on second thought, a benefit I see from using the pre-trained model as SD 1.5 is that you can checkpoint merge with other models to fit your liking if you want to change styles

@pastuh Жыл бұрын

yes, better start with SD1.5, later mix based on your style

@edwardlee670 Жыл бұрын

great video, but is there any low vram setting? I am on 3060 with 8G but no luck getting the training started.

@garrickgreathouse 10 ай бұрын

Just once I would like one of these tutorials to actually work and properly correspond to what I see when following the steps.

@addermoth Жыл бұрын

A little tip, when installing python make sure to check the box that adds pip to environment variables, for some reason mine did not by default.

@LaBAdochnicht Жыл бұрын

mine also. I just uninstalled Python and reinstalled it over the Microsoft store. It will install pip correctly

@PlatteLive 10 ай бұрын

how would I know if I installed it without checking the box?

@addermoth 10 ай бұрын

@@PlatteLive Try installing and running SD, and watch for the error in the console, It will give you a pretty noticeable verbose error saying Pip is not installed. If so just run the python install again and make sure to tick the box to install pip in the menu. Hope that helps.

@PlatteLive 10 ай бұрын

@@addermoth appreciate it man. Also, I'm only seeing "gui.bat" in the "kohya_ss" folder, and not "user gui.bat", but it still seems to launch it fine. And I can't tell if it installed cudnn, I put the cuddn_windows into kohya_ss, ran the command to install it, but it never said "done" or anything.

@LaBAdochnicht Жыл бұрын

Hi, thanks for your amazing videos. But I had a lot of problems. first, the setup: you didnt show us all the ssettings in the cmd, i was really confused, second the picture tagging: it just spit out some errors. and I am really stuck at this point. So I couldnt train any modells :(

@garciabete137 7 ай бұрын

I have been following the steps of a tutorial on how to use LORA and stable difussion, but your file is safetensors and mine is a Json, does anyone know why?

@fingerprint8479 7 ай бұрын

Hi, just installed Kohya_ss version v21.8.10 and it looks very different fro the one in the video and I cannot find how to generate caption. Have you got any tutorial on that new version? Thanks

@jasondulin7376 7 ай бұрын

I completed my first training of a LORA based on close to 300 images. When it's finished, I'm left with all my epochs being close to 9mb and the LORA seems to have no effect when tried in ComfyUI. Am I missing something incredibly obvious?

@user-gn9oe3je8b Жыл бұрын

Thanks!

@OlivioSarikas Жыл бұрын

Thank you very much 🥰👍

@cyrusbastankhah576 11 ай бұрын

THANK YOU! LOOK INTO LoRA MERG FEATURE!!

@markelturku6971 4 ай бұрын

Great job Daddy :) I would like to thank you as someone who can explain such a difficult to understand subject so well.

@angloland4539 8 ай бұрын

❤

@BoHorror 9 ай бұрын

Please make one for online but with the same idea, like the idea of full resolution

@Raketenclub 8 ай бұрын

you are awesome. internet is getting better bcs of u 🎉

@boya8719 Жыл бұрын

Your awasome

@xellostube Ай бұрын

Thanks! Very helpful

@matthewmounsey-wood5299 10 ай бұрын

Hey Olivio! I love this tutorial! Do you have any plans to update it? Have a great day!

@Zettelaeum3030 11 ай бұрын

Thank you for the video! You mentioned you could do one with an online server, please, pleeeeeeease would you be so kind as to show us how to train a LORA step by step with RunPod ? 😭😭😭