Hi Laura. Slightly off topic, but have you tried the 'Lora-Training-in-Comfy' node? I would love to see what you have to say about it, in a video of course. I will now continue watching this video.

@LaCarnevali Ciao Laura, grazie per questo fantastico video! Non riesco a creare il file .ckpt in huggingface. Come posso fare? Si può prendere un modello qualsiasi o deve avere delle caratteristiche particolari= graxzie mille

the line drawing preview icon does not show on my UI, how would i activate it?you click at it at 6:22

can you do a video on making a photo realistic LORA of yourself (kohya SS or DRAW THINGS app in mac), and doing a Haut Couture (Alexander McQueen or Miu Miu, or DIOR) Fashionshoot with this LORA of yourself for VOGUE ITALIA in the style of Photographer Paolo Roversi ? (solo per rimanere un po in italia con tutto questo) ? Graaaazie Mille.... ;)

Contolnet lineart seesm to only work for sd1.5 and not for sdxl , right?

It's great that you show different settings, and especially extreme settings. It paints a clear picture of the options. Thanks for your efforts!

thanks you so much for the video, i created my own lora with base model SD 1.5 successfully, however there are many sampling method, DPM++ 2M, 3M, euler, heun...etc, how do i know which sampler work best with my lora?

Hey there great videos , and easy to follow. Thanks! could you take a look at Storydiffusion or any extension that does the same on Automatic11111.Thanks again, great content!

During test the trained model I'm getting the following error: Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/aiohttp/client_reqrep.py", line 70, in <module> import cchardet as chardet ModuleNotFoundError: No module named 'cchardet'

link ?

TypeError: 'NoneType' object is not iterable Time taken: 4.6 sec. Traceback (most recent call last): File "D:\Program\MATRIXXX\Packages\stable-diffusion-webui-forge\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) TypeError: 'NoneType' object is not iterable

Saya sudah mengikuti semua cara di video ini, akan tetapi hasilnya error

Hello, when I take the download link of some models like Juggernaut XL from civitai and put the link in the MODEL_LINK, I get an error for downloading(HTTPError: HTTP Error 401: Unauthorized ), how can I fix it? I'm sorry if I didn't convey my meaning well, I'm not an English speaker :)

Does anyone get this error, " ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor' " when testing the trained model? How do you fix this?

If I want to run online, I have to add the -listen command

Thank you so much Mam

Hey Laura, thank your helpful tipps in the video! Do you think it makes sense to train a model for realistic peoples, with transparent background?

Dang, you looking fresh today

this is surprisingly a good video explaining how to use stable diffusion even if its only about Loras

Thank you.

👋

Great stuff Laura, I love your tutorials.

That was very interesting and well explained. Thank you.

very good

I followed all the instructions step by step and everything went perfect with the installation process. Then it came to actually generating images where I was met with the message"AttributeError: 'NoneType' object has no attribute 'lowvram'". I don't know how to fix it or why it's happening

Can these be used on mobile iPhone or iPad?

Thank you Laura, much appreciated, buen dia ;-)

Hello! Thanks for great tutorial! I have a problem on the step Upload Model to Hugging Face. Google colab deletes the runtime and displays a message that it does not support this action (apparently, loading the model on hugging face). Could anyone help me fix this error, please? 🙏

Hi Laura, I have quick question. On a i Mac M3 should I follow he same procedure described on this vid? Thanks!

this is what i was looking for! thank u so much!

Thank you! 2024 and it still works!

I’m getting a crush on you. Lol! Sherrrr. Thanks for always posting great content to learn from!

Great video - very informative. There's been a few changes with the newer version of Kohya_SS, and while the fundamentals are pretty much the same, a deeper dive into the newer version would be awesome if you can ever find the time. Thanks. 🙂

should it be in /models/StableDiffusion? not /models/Lora?

What is the best settings to improve velocity of work for Mac M1?

Thank you for explaining that the Lora's need the correct model. Been trying to do cartoonlike tutorials, but the Lora just does messy graffiti or noise as output.

Thank you!

Dear Laura, We would like to hire you to set up Comfy UI flow to edit home made photos to simple backgoung portraits with watercolor vibrant elemets of left/right side of people

Hello Laura, really enjoyed the video! I tried following what you did step by step however when I launched the "Test the trained model" cell, I got a traceback error message which prevents me from testing the model. Do you have any advice or is there an updated version of the notebook I should download? (I got colab pro)

Great video, thanks! But none of the caption tools worked for me. I had the error: "Python\Python310\python.exe: can't open file 'C:\\kohya_ss-master\\sd-scripts\\finetune\\make_captions.py': [Errno 2] No such file or directory" There is indeed no files in that folder. I googled but couldn't find a working solution. Any help would be highly appreciated.

Thanks!

wow miss carnevali! i learned more from you in 22 mins then the last 6 months!

Hi, I'm pretty new to generative stuff and I have difficulties to get a good framing. Could LoRa be a way to teach SD some filmmaking vocabulary? If so, how would you set a training? Many trainings one after another, each with a bunch of pictures with a specific shot, then another specific shot, and another, etc. Or goods captions could be enough for one big training?

Hey Laura :) I'm so happy to stumbled upon your channel. Your explanations and energy are beautiful as you are. I'm in love 🥰Take care and keep shining bright <3

Thank you so much. It works without a problem.

Hi, has someone the link with the second part? I want to know how to continue with the training if Colab doesn´t allow me to continue using the GPU. Thanks for the video Laura!!

Eyebrows

best tutorial for lora training , by far, thanks

Hello Laura, can one pay for a one on one session with you?