MERGE A FACE & STYLE With LORA EXTRACTION In Stable Diffusion! NO TRAINING!

Поделиться
HTML-код
  • Опубликовано: 25 ноя 2024

Комментарии • 99

  • @Aitrepreneur
    @Aitrepreneur  Год назад +9

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

    • @Mandraw2012
      @Mandraw2012 Год назад +1

      I would love to use the kohya_ss ( gui or no gui ) but it just won't work on my machine :/

  • @hagwe
    @hagwe Год назад +5

    I can confidently say that the creator of Lora is a genius! It is easier to work with such models, and most importantly, they do not take up much space on the SSD.

  • @leafdriving
    @leafdriving Год назад +28

    You are the first to bring this method to my attention. Ahead of the pack as always. Thumbs up.

  • @magenta6
    @magenta6 Год назад +4

    Another first class video from the Ai_Overloard. Your content is part of the acceleration we are seeing with Ai development and enhancement.

  • @sethhaynes4652
    @sethhaynes4652 Год назад +6

    I would love a quick segment on what the benefit of loss of different models styles, like lora vs checkpoints.

  • @НикитаФелликс
    @НикитаФелликс Год назад +6

    I eagerly anticipate each of your videos, thank you for such invaluable content!

  • @OriBengal
    @OriBengal Год назад

    wow! I've been making a ton of 4GB files. You rock! This is perfection.

  • @StephenHarperRaptagon
    @StephenHarperRaptagon Год назад +1

    Liking the new thumbnail!

  • @RikkTheGaijin
    @RikkTheGaijin Год назад +4

    I mean, cool but tbh the likeness is not there at all.

  • @DJVARAO
    @DJVARAO Год назад +1

    This is a winner option 😁

  • @sinanisler1
    @sinanisler1 Год назад +1

    hmm everyone talking about this lora time to learn. :)

  • @flonixcorn
    @flonixcorn Год назад +1

    So Cool!

  • @ngocanhnguyenho6788
    @ngocanhnguyenho6788 Год назад

    Massively useful, effective, kudos [GENERATE].

  • @jreenhanced
    @jreenhanced Год назад +2

    Is there a google colab for this?

  •  Год назад

    Thanks for your teaching, master!!

  • @lolloll8781
    @lolloll8781 Год назад

    This is actually amazing. Thanks so much!

  • @freedomgaming9987
    @freedomgaming9987 Год назад +2

    The checkpoint merger does appear to be better however, as you said it comes a cost... A new SSD. lol

  • @ArisenProdigy
    @ArisenProdigy Год назад

    This is massively incredible!

  • @chubbydunkers78
    @chubbydunkers78 Год назад +1

    Hey, do you think you could do a video walking us through the Kohya lora training google colab? Thank you for your always amazing content!

  • @banzai316
    @banzai316 Год назад

    Very useful! Awesome

  • @poponium
    @poponium Год назад

    Thanks you !

  • @davitzeiro
    @davitzeiro Год назад

    nice! thank you!

  • @MyPrivacyAccount-lo5lf
    @MyPrivacyAccount-lo5lf Год назад +1

    thanks for the video. in my case, Network & Conv Dimension in LORA Extract are 128 by default, what is the difference between 8 & 128?

  • @artur_schutz
    @artur_schutz Год назад +2

    At this point I really need a broad overview of everything what I need to know about Stable Diffusion. I am really lost with all this different in-detail topics, because I do not even know where to start.

  • @ArkAlpha1
    @ArkAlpha1 Год назад

    This is really cool! Thank you! Also, what GPU do you have?

  • @ady-001
    @ady-001 Год назад +2

    So basically there is no need for large checkpoints since we can just use these Lora files with the base models ? This will save a lot of space and will make file transfer / downloads faster, even if storage is not a big deal, it helps.
    Did you do some tests, to see if the prompt with the extracted Lora is almost identical with the original, much larger, model ?

    • @ady-001
      @ady-001 Год назад +1

      to answer my question.. It kind of works but is not the same as using the original model. You have to fiddle with the weight and with the Network Dimension, which is 128 by default now, and can go up to 1024. But like in the video, higher values give artifacts and a larger file size.
      Also, some Lora models are trained on different models, not on the standard 1.5, so you need that model downloaded, otherwise it won't work.

  • @Loopa21
    @Loopa21 Год назад

    damm tnx man

  • @DESIGNISTASTY
    @DESIGNISTASTY Год назад +1

    Is there any google colab notebook to make lora extraction?

    • @DanielAlmozara
      @DanielAlmozara Год назад

      Did you find any? Thanks in advance, I want to do this but I use colab for Stable Diffusion.

  • @diego.spirit
    @diego.spirit Год назад

    Hello everything is fine? Great video! what version of stable diffusion do you use for this tutorial? 1.5?

  • @831digital
    @831digital Год назад +3

    How would you have 2+ characters in a scene using this technique?

    • @ShawnFumo
      @ShawnFumo Год назад

      You can use the composable lora and latent couple extensions

  • @Vigilence
    @Vigilence Год назад

    Would love to learn how to train art styles! 🎉

  • @Xaddre
    @Xaddre Год назад

    can you make a video on a list of the best ai tools you know about like chat gpt or other ai's that you know about

  • @MrBlitzpunk
    @MrBlitzpunk Год назад

    i do hope this doesn't need much vram so that i can extract the lora locally and use the extracted loras with google colab

  • @michaelli7000
    @michaelli7000 Год назад

    May i ask what is the difference between lora method and previous textual inversion embedding? thanks a lot

  • @eduardoalvarado1375
    @eduardoalvarado1375 Год назад

    Dude, can you do a video training the Trending dinosaurs with professions or jobs? xD hahaha thanks!

  • @stan-kk2sf
    @stan-kk2sf Год назад +1

    I want to know is there any way to incorporate lora into the big model?
    For example luna_lora + sd1.5 merge to luna_sd_model

    • @SuperDao
      @SuperDao Год назад

      Did u got an answer?

    • @SuperDao
      @SuperDao Год назад

      @@stan-kk2sf so it’s possible to merge a train face of ourselves and a style?

  • @slashkeyAI
    @slashkeyAI Год назад

    I posted a style training guide on Civitai questions section and my own model there. hope it helps some folks. Really huge gaping hole among RUclips creators where style training tutorials should be.

  • @namdoyle
    @namdoyle Год назад

    Can this method extract inpaint model to a lora file as well🤔, so that we can use inpaint model in "lora way"?

  • @cinemantics231
    @cinemantics231 Год назад

    Is there any way to rollback Stable Diffusion to version 1.5? They've discontinued using several artists in prompts which is proving to be quite a challenge for my work.

  • @HogwartsStudy
    @HogwartsStudy Год назад +2

    trigger words? ugh. The LoonyLL embedding TI needs no trigger...

  • @T1500C
    @T1500C Год назад

    why fp16? float is not more precise?

  • @Endangereds
    @Endangereds Год назад +1

    can we change/customize Trigger word at this point?

    • @Aitrepreneur
      @Aitrepreneur  Год назад

      No trigger words are choosen during the training

    • @Endangereds
      @Endangereds Год назад

      ​@@Aitrepreneur as we are able to extract the changes including the trigger words. May be there should be a way to unpack a .safetensor to a diffuser or some format, where we can change/customize trigger words. Programmers who know about how data is saved and handled can help.

    • @hajiamano22
      @hajiamano22 Год назад +1

      @@Endangereds That unfortunately isn't how this works. The trigger word isn't "saved". Text gets turned into a bunch of numbers called vectors. Those vectors gets turned into a text embedding. Those numbers then get added as a step in the diffusion process when training in association with the object being described. All-in-all, once you have trained the model to associate the object with that word, you cannot untrain it to associate with that word. Maybe, in textual inversions case you may be able to create a textual inversion to create a text embedding that looks for the embedding you created in dreambooth in latent space. However, i'm not sure how accurate that would be. It's worth a shot though.

    • @Endangereds
      @Endangereds Год назад

      @@hajiamano22 I saw a reply which reads
      "In theory you should be able to. In the vocab.json file where your model is (model/tokenizer/vocab.json, you should be able to change any of the words to your own, and the word will reference the embedding vector.
      So looking at the 1.5 checkpoint it would be like:
      Original: "sks": 48136
      New: "my_word_here": 48136
      Then just merge the model with the LoRA as you normally would."

    • @hajiamano22
      @hajiamano22 Год назад

      @@Endangereds Well, if that's the case and I am wrong (which I can be) editing a json file isn't difficult. You can open it in a text editor like notepad++ or visual studio code and edit it yourself. Test it, and see what if it's true.

  • @xiaohongcook
    @xiaohongcook Год назад

    Hi, anyone knows how to train lora which support mask?

  • @rodrigomenam
    @rodrigomenam Год назад

    Excelent video, I am currently facing an error: KeyError: 'time_embed.0.weight' when tying to extract the LoRA from my safetensors file, unluckily I have not found any solution online.
    Is someone else facing the same problem?

  • @Alkindly
    @Alkindly Год назад

    how to become pro in Stable Diffusion? I see a lot of beautiful anime pictures, but how do they make it?

  • @gkp1990
    @gkp1990 Год назад

    I'm really confused i don't have the show extra purple button? ive updated diffusion multiple times now and still dont have that button any reason why?

  • @svenandersson6306
    @svenandersson6306 Год назад

    Interesting but as you probably know Luna Lovegood doesn't need a Lora to start with. If you just put it in the prompt you'll get very good results with most models...

  • @HestoySeghuro
    @HestoySeghuro Год назад

    Not sure about the DIM 8 extraction... why not 128 or 32?

  • @manueloliva9306
    @manueloliva9306 Год назад

    i dont find the page where you can extract lora, where is "utilities"? thank you

  • @Tcgtrainer
    @Tcgtrainer Год назад

    ¿can i use my own face to do this ?

  • @digidope
    @digidope Год назад +1

    Can't get LoRA to train anything as it claims no xformers found while dreambooth works just fine with xformers.

    • @camclare
      @camclare Год назад

      Auto1111 is turning into a dogs breakfast with all its extensions etc. different cuda/ Python versions doesn’t help either.

    • @digidope
      @digidope Год назад +1

      @@camclare Different Cuda/Pytorch/Python versions combined with random extention needs makes the system rather un-stable.

  • @GarethLee-u1u
    @GarethLee-u1u Год назад

    Hi im getting an error : KeyError: 'time_embed.0.weight'
    Do you know how to fix it?

  • @ketorami9183
    @ketorami9183 Год назад

    Now I can train face but I have a new problem. I want to train clothes Or even rings, bracelets, I can't train it. When I Generate Pictures, It show only the shirt/rings but no face. I've been looking for a solution all week but I'm out of options. Can you help me?

  • @TobinatorXXL
    @TobinatorXXL Год назад

    I use linux how do I start Kohya GUI?

  • @owndesires
    @owndesires Год назад

    when i do that i get this error: KeyError: 'time_embed.0.weight'? you know why?

  • @METALSKINMETAL
    @METALSKINMETAL Год назад +1

    Hi, so if you install Kohya SS on you system does it replace Automaic 1111 as the gui? or how do the two interact together? I am using Automatic 1111 with SD atm but i want to try out LoRA also but don't want to change my current setup as i am very new to AI. Thanks!

    • @LeKhang98
      @LeKhang98 Год назад

      It's just another extension, similar to any other extension. I'm not sure about your PC, but based on my experience, it will open a new Chrome tab (different from the Chrome tab that I used to interact with SD). Nothing changes. Although it may require some software update or downgrade.

  • @galnart5246
    @galnart5246 Год назад

    Will all the lawsuits poping up effect stable diffusions development negatively?

  • @roseydeep4896
    @roseydeep4896 Год назад

    colab tut plssss

  • @Philson
    @Philson Год назад +1

    How to do the reverse? Merge a Lora into a Checkpoint file?

  • @j5545
    @j5545 Год назад +1

    Bro pease help us make a dteambooth that works even with Joe penna the old dreams booth video you made is broken 💀😭😭

  • @jameshughes3014
    @jameshughes3014 Год назад

    i'm kinda stupid today from lack of sleep, could someone explain like i'm five, what does this do exactly? Does it mean that if we extract a lora from one of these models , we get all the advantages of that custom trained model with less size? are there downsides?

    • @ShawnFumo
      @ShawnFumo Год назад

      Less size and you can use it on top of multiple models (and in conjunction with other LoRAs). I'm guessing there may be some quality implications of using LoRA vs Dreambooth (not sure the specifics), but at least some of the Dreambooth checkpoints are because that was because LoRA wasn't a thing yet.

    • @jameshughes3014
      @jameshughes3014 Год назад

      @@ShawnFumo Yeah i was having a slow brain day lol. thanks for answering.

  • @Thozi1976
    @Thozi1976 Год назад

    But, to be clear, this does NOT produce identical results for identical prompts?! An image created with i.e. Analog Diffusion V1.0 will look different from (identical prompt and settings) SD15 with extracted LORA from said Analog Diffusion V1.0 Checkpoint.
    I'm just verifying here - so I can stop trying to make them match and thinking I'm doing something wrong when extracting the LoRA Data. Thx.

  • @kallamamran
    @kallamamran Год назад

    So basically the extracted LORA-file is the same as using a Textural Inversion embedding file trained on a subject. So you could just do that... Right?!

    • @tetsuooshima832
      @tetsuooshima832 Год назад

      This is about extracting datas from existing models. Sure you can make embeddings by yourself but that takes hours, it's up to you

    • @kallamamran
      @kallamamran Год назад

      @@tetsuooshima832 So basically it's about extracting other peoples training data :P I get it :)

    • @tetsuooshima832
      @tetsuooshima832 Год назад +1

      @@kallamamran yes it is. And there's nothing wrong with that (don't think I didn't see your ironic tone here lol).
      Stable Diffusion is about sharing everything to make great stuff; we share the tech, the prompts, everything except the money some of us make from it lol

  • @OriBengal
    @OriBengal Год назад

    Not sure this is the right place to send "requests" - but - speaking of merging things together.... Have you tried "Multi-subject-render" Extension? Control net lets you more easily have multiple people now... but I'm still having a heck of a time describing each person separately- e.g. 1 man, 1 woman, 1 child, wearing different styles and colors, and are all different ages and ethnicities. SD gives me some scary results (everyone wearing dresses, or everyone's got boobs) - yada yada. Another thing that might be the key to this- but I think the world needs an easy to understand overview from our AI overlord is ComfyUI -- Node Based SD.... Something Invoke is working on, but hasn't released yet.

  • @artist.zahmed
    @artist.zahmed Год назад

    how to merge 2 lora models

  • @casualtake1497
    @casualtake1497 Год назад +1

    do you have complete tutorial for beginner with no coding background?

  • @s6yx
    @s6yx Год назад

    This is the bootleg version of LoRA. If you’re extracting a LoRA from a checkpoint, make sure it’s truly from a sd 1.5 base other wise you’re wasting space on your pc

  • @dailyfunnytv358
    @dailyfunnytv358 Год назад

    i dont understand. why not just download a lora?

    • @ShawnFumo
      @ShawnFumo Год назад

      There might not be a LoRA available. Dreambooth came earlier, so a lot of trainings were done with that instead (and there probably is still some quality advantages of Dreambooth, though I'm not sure). This also lets you borrow some of the style of another full model/mix without making your own carefully tuned mix.

  • @salemameri
    @salemameri Год назад

    intro hello msk a wododo

  • @SALLI.E
    @SALLI.E Год назад

    Super video... thnx for this... I like you and your videos... your first AI fan @SALLI.E

  • @pol3055
    @pol3055 Год назад

    KeyError: 'time_embed.0.weight' , I get that when I try to extract the lora. Any idea why that is ?