[Tutorial] Create Your Own LoRA | Easy and Free! - Google Colab

Поділитися
Вставка
  • Опубліковано 9 січ 2025

КОМЕНТАРІ • 119

  • @OliviaMurray-c7q
    @OliviaMurray-c7q 11 місяців тому +8

    How to take the final step, but in foocus? Is it possible? Coolab disconnects all the time.

  • @daganmiller8604
    @daganmiller8604 6 місяців тому +1

    I've seen a few tutorials on Loras and I would always run into a problem along the way but your method is very smooth and easy to follow and have come out pretty good. The only thing I've struggled with is training at 768 size instead of 512, it seems to cause errors so I've just settled with 512 for now.

  •  9 місяців тому +2

    I am getting stuck in the Sample Lora (part 3): the log ends with 'ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor''. Seems to be an xformers and pytorch issue.. @MalverseAI any idea why? Is the Sample Lora in the link of your description still up to date?

    • @LuongNguyen-wk4lc
      @LuongNguyen-wk4lc 9 місяців тому

      I have the same problem

    • @mdken2198
      @mdken2198 6 місяців тому

      same problem

    • @mdken2198
      @mdken2198 6 місяців тому +1

      !pip install torchvision==0.15.0

    • @Fnotez
      @Fnotez 3 місяці тому +1

      @@mdken2198 this solved ur issue, can share ur code?

  • @DisgustingJustinAD
    @DisgustingJustinAD 7 місяців тому

    Dang man, I watched other youtube videos & they making me do everything the hard way. This seems like a much smoother method, I'm new to A.i. generation. Most of the time I never get any answers when I ask around about making LORAs.

  • @semihpaker3857
    @semihpaker3857 11 місяців тому +2

    Hey , when i writed x value and y value i see RuntimeError: Prompt S/R did not find -0.5 in prompt or negative prompt. how i can correct ? Thank you

  • @Faded_Fragger
    @Faded_Fragger Рік тому +5

    instead of creating lora for the face, can you create lora for a specific body? because face i can already face-swap. what im looking for is consistent body. And for that, would i get my dataset with photos with the face or just the body?

    • @michaelcorleone9989
      @michaelcorleone9989 Рік тому

      No one knows?!

    • @Showbiz_Stuff
      @Showbiz_Stuff 11 місяців тому

      I'd say the face can be on the dataset but you should fine tune your caption

    • @lauraknightart
      @lauraknightart 11 місяців тому

      Probably your prompt

    • @iamdihan
      @iamdihan 2 місяці тому

      maybe use a body weight slider Lora?

  • @Theanswer0000
    @Theanswer0000 Рік тому +2

    I'm not getting the link of Gradia, what's the fix?

  • @rioo3332
    @rioo3332 Рік тому +1

    I Big understand, where u got sampleLora??!!!!!

  • @RavierAlencar
    @RavierAlencar Рік тому +2

    What is the best configuration for "Anime Characters"? SD 1.5? Tags? Steps? Épochs? (I have 12 images)

  • @moderncapitalist
    @moderncapitalist Рік тому +1

    Hello, I'm getting a "AttributeError: 'ImageDraw' object has no attribute 'multiline_textsize'" error at the last phase of drawing the X/Y chart (11:30) in the video. The plot diagram does not output in Stable Diffusion. A brief google search shows that this may have to do with the Python version?

    • @moderncapitalist
      @moderncapitalist Рік тому

      hmmm, resolved this by unchecking the "Draw legend" box. I don't really know what this option does though...

  • @gaslightstudio3528
    @gaslightstudio3528 11 місяців тому +1

    great tutorial but please make soundtrack softer preferably instrumental since it clashes with your voice and it is so important to hear your details

  • @brunoribeiro1387
    @brunoribeiro1387 10 місяців тому +1

    Could I create a Lore with a character made by AI too ? If it could be possible can I take this Lora and use it on different Models too ?

  • @SahilDhimaan-yl4qr
    @SahilDhimaan-yl4qr 18 днів тому

    RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:
    size mismatch for conv_in.weight: copying a param with shape torch.Size([320, 9, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]).
    this is the issue i'm encountering in the second step :(

  • @edteach-b5v
    @edteach-b5v 4 місяці тому

    the lora i want to make is trained using pony model . Will your sample testing notebook work with pony too ?

  • @FM-zp2hl
    @FM-zp2hl Рік тому +2

    Hello how do you find the trigger word for each of those Lora's

    • @SmortSquirtle
      @SmortSquirtle Рік тому

      Did you find the answer? I’d like to know as well

    • @thejamesarnold
      @thejamesarnold Рік тому +2

      replace the contents of the text files to the trigger word like "margotrobbie001", "margotrobbienew", etc. make the trigger word unique especially for celebrities because "margot robbie" could be already trained in the model that you are using... You can also change the text file to describe the picture with the person for example "margotrobbie001 wearing pink dress", etc

    • @SmortSquirtle
      @SmortSquirtle Рік тому

      @@thejamesarnold ty fam 👍🏼

  • @Showbiz_Stuff
    @Showbiz_Stuff 11 місяців тому

    Good and simple. I wish you'd explain triggerwords and caption more, though

  • @ErikTavaresDosAnjos
    @ErikTavaresDosAnjos 10 місяців тому +1

    HI people,
    Did anyone have this error?
    RuntimeError: Prompt S/R did not find -05 in prompt or negative prompt.

    • @FightClubGarmz
      @FightClubGarmz 7 місяців тому

      Sounds like the weight of your lora is not in the correct format. Typically it would read as “” for exg. Keep the “.” In between the numbers “1.4”, or “2.1” this indicates the strength of the lora as the “x/y/z” testing indicates in the tutorial in SD1111.

  • @rbdesignguy
    @rbdesignguy 8 місяців тому

    Typically I just use roop and get some of the best looking faces when combing actor face.. but this probably gives more blended and less photoshop feeling

  • @mohammedmahboob6908
    @mohammedmahboob6908 Рік тому +3

    My colab also gets disconnected

  • @kiwiranda
    @kiwiranda Місяць тому

    getting ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'
    any help?

  • @thewebheadgt
    @thewebheadgt 10 місяців тому +3

    Is cropping to 512x512 mandatory?

    • @j4m3s35
      @j4m3s35 10 місяців тому

      i was gonna ask the same question

  • @Ricky-d3e
    @Ricky-d3e Рік тому +3

    Thank you so much for this video. You're a life saver.

    • @raistar72
      @raistar72 Рік тому

      I am getting error at middle you are using colab pro?

    • @СлесарьЛеха
      @СлесарьЛеха Рік тому

      @@raistar72 free

    • @raistar72
      @raistar72 Рік тому

      @@СлесарьЛеха what is the reason for error "balance: 0"

    • @EveryBeardHasAStory
      @EveryBeardHasAStory 7 місяців тому

      What part of stealing someone's identity is so vital to your existence that you consider this tutorial a life saver? Lmao...

  • @shanehudson88
    @shanehudson88 Рік тому

    I dunno what you did at 11:00 in but you already had an image generated in stable diffusion. You dont explain how to add in the prompts your own lora that youve created. This is where I am stuck

    • @Showbiz_Stuff
      @Showbiz_Stuff 11 місяців тому

      This step is just for testing the epochs and weights. Just write your own prompts

  • @FM-zp2hl
    @FM-zp2hl Рік тому +2

    Nice video there, I keep getting this error: The model you selected is invalid or corrupted, or couldn't be downloaded. You can use a civitai or huggingface link, or any direct download link."
    I have used many link to different models but still not working

  • @Aro_2002
    @Aro_2002 6 місяців тому

    Amazing video

  • @chaitanyamore8786
    @chaitanyamore8786 10 місяців тому

    Google colab giving me gpu backnd error after downloding model is it bug?

  • @housejones
    @housejones Рік тому +1

    TYSM for sharing it was very helpful.

    • @MalverseAI
      @MalverseAI  Рік тому +1

      No problem 😊

    • @raistar72
      @raistar72 Рік тому

      I am getting error at middle you are using colab pro?

  • @matthewhurd1272
    @matthewhurd1272 Рік тому +1

    How do you load the notebook it doesnt come up on mine

  • @nya4336
    @nya4336 Рік тому +1

    can i try all 10 at once?

  • @anon3253
    @anon3253 7 місяців тому

    i cant install kohya bc my python version is 3.12 :(

  • @jonaskilian6143
    @jonaskilian6143 Рік тому

    works fine until the step where I want to open stable diffusion. I copy the prompt etc and then it gives me an error because the GPU on collab has disconnected. Any suggestions?

    • @user-rw6pq6un7o
      @user-rw6pq6un7o Рік тому +2

      Google have started banning the use of sd web ui

  • @shanehudson88
    @shanehudson88 Рік тому

    After clicking the Gradio link it says No interface is running right now..... How do i fix this??

    • @shanehudson88
      @shanehudson88 Рік тому

      It worked the second time because I didnt stop the colab like you suggested.

  • @uwb33
    @uwb33 Рік тому

    Thank you that works

    • @raistar72
      @raistar72 Рік тому

      Pro colab or normal google colab

    • @uwb33
      @uwb33 Рік тому

      i use pro colab @@raistar72

  • @kopiamazon
    @kopiamazon Рік тому

    the best the best the bestttttt i love you

    • @raistar72
      @raistar72 Рік тому

      I am getting error at middle you are using colab pro?

  • @icyberta
    @icyberta 6 місяців тому +2

    sample doesn't works, Collab stops it

  • @MuhsinKP
    @MuhsinKP Рік тому

    Hello
    i'm getting this error
    curl: (23) Failure writing output to destination
    cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory
    cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory
    cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory
    cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory
    cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory
    cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory
    python3: can't open file '/content/launch.py': [Errno 2] No such file or directory
    could you please help

  • @tmoblak
    @tmoblak Рік тому

    I somehow cannot get past the steps/epochs training step. All I get is "Error. Your total steps are too high. You probably made a mistake. Aborting..." and thats it. I tried to use as many steps what you recommended. I also tried lower number - still getting the same error.

    • @tmoblak
      @tmoblak Рік тому

      ..nevermind, i had to change epochs to steps in drop-down menu, my bad!

  • @bigguybruno5991
    @bigguybruno5991 Рік тому

    when I put the numbers for the x type prompt it gives me an error that there isnt (number) in the prompt

    • @MalverseAI
      @MalverseAI  Рік тому

      check on your drive which are the correct numbers, or just test 1 by 1 the Loras

  • @enesalcatraz4470
    @enesalcatraz4470 10 місяців тому

    colab doesn't support gradio webui anymore but its still a good tutorial

  • @Nazukio
    @Nazukio 11 місяців тому

    And what do I do when the Model is corrupted?

    • @FightClubGarmz
      @FightClubGarmz 7 місяців тому

      When downloading through a url, models can not download correctly, to fix this manually download the model locally and then upload to your notebook.

  • @atruereview7298
    @atruereview7298 Рік тому

    Can you please help me with making one

  • @D3coify
    @D3coify Рік тому +1

    Do I need a better google collab plan? I was in the a1111 ui and got disconnected from collab saying something about credit and time

    • @Emsyaz
      @Emsyaz Рік тому

      Free plan doesnt work

    • @D3coify
      @D3coify Рік тому

      @@Emsyaz ok ty,

  • @Theanswer0000
    @Theanswer0000 Рік тому

    I run into an issue. how do i install gradio?

    • @thejamesarnold
      @thejamesarnold Рік тому

      google is banning gradio and other web UI.

  • @jacquelynecarmen
    @jacquelynecarmen 8 місяців тому

    runtime disconnected

  • @ridajaved861
    @ridajaved861 Рік тому +1

    when i run simple lora ipynb it does not complete and end the runtime any solution for that ?

  • @Theanswer0000
    @Theanswer0000 Рік тому

    Now this helped me out. Big thanks!

    • @MalverseAI
      @MalverseAI  Рік тому +1

      No problem!

    • @Theanswer0000
      @Theanswer0000 Рік тому

      How do i fix this error:
      Warning: such file or directory
      0 225k 0 994 0 0 768 0 0:05:01 0:00:01 0:05:00 768
      curl: (23) Failure writing output to destination
      cp: cannot create regular file '/content/microsoftexcel/models/Lora': No such file or directory

    • @raistar72
      @raistar72 Рік тому

      I am getting error at middle you are using colab pro?

  • @yogiwirawan861
    @yogiwirawan861 Рік тому

    Why my google colab keep disconeting”

    • @raghulmanikandan
      @raghulmanikandan Рік тому

      You need pro

    • @bluecity8152
      @bluecity8152 11 місяців тому

      @@raghulmanikandan If i upgrade to pro, then I can run the sample_lora? thank you

  • @black_kuromi
    @black_kuromi 10 місяців тому

    GPU DATA ID NOT FREE!!!

  • @mekkicharfi5454
    @mekkicharfi5454 8 місяців тому

    vous n'avez pas lu mon message , donc je le supprime !

  • @the_meridian
    @the_meridian 11 місяців тому +5

    "Easy" lol...

    • @lilith2754
      @lilith2754 10 місяців тому

      Well, it is ... Lol

  • @JarppaGuru
    @JarppaGuru 9 місяців тому

    free? last time i test something. space was not enought xD. we can do FREE on local. ldets not give our files to google?

  • @selfmasterytv
    @selfmasterytv 7 місяців тому

    all this effort, it didn't catch the essense of the person at all though, thanks though

  • @abhishekpatra7954
    @abhishekpatra7954 Рік тому +1

    Hello, sir. Could you please, if you don't mind, train an actress, let's say Alexandra Daddario original to pose using controlnet or any other tool you might know, to make her sniffing her armpits? Like i wanna see how far one can train SD to show an output like that?

  • @mdken2198
    @mdken2198 6 місяців тому

    everyone has a problems and you dont any respond. DELETE Video. WHAT a waste of a time!

  • @TheSoleProprietor
    @TheSoleProprietor 9 місяців тому

    You are going through the tutorial too fast. I can't keep up with you!

  • @AnnaBichinashvili
    @AnnaBichinashvili 6 місяців тому

    I'm currently on the Lora training (after creating the dataset with 31 images, that's gone well), but the result of running gives me this: KeyError: 'time_embed.0.weight

  • @AstaIllum
    @AstaIllum 8 місяців тому

    Anyone getting :
    "ModuleNotFoundError:
    No module named 'torchvision.transforms.functional_tensor'" ?

    • @Fnotez
      @Fnotez 3 місяці тому

      me too, i tried with different versions of torchvision , didnt work

  • @LetiferTV
    @LetiferTV 8 місяців тому +1

    colab ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

    • @Fnotez
      @Fnotez 3 місяці тому

      same error , u found a way around ?

  • @yolocrayolo1134
    @yolocrayolo1134 Рік тому

    no such file direcotory appears to me i will try later