Error in Mac with terminal

You should make a new version of this video with flux... please 😍🥰

Thanks for the video. How can i train a local Lora for SDXL? I havr. 4090 with 24Gb of RAM and is allways going over that limit? Is it possible at home or only for SD1.5 and small resolutions

How can we get multiple such subjects added(trained) into the same model? is there a way to combine individually trained models or should we use previously trained model one subject to train the second subject and so on?, or simply put the images of all subjects with different names and train them all at the same time

Тебя случайно не Лора зовут ? 😅

it took me a week to get to this video. It seems everything I click is paid these days

the checkpoints I downloaded from GitHub aren't working when I open SD with Forge UI. Are the models different for automatic 1111 than for forge? Thank you :)

win + v for quick copy paste

i guess you gave up on your discord help channel...

Try one trainer it is 3 time faster and result are great!

Thanks for the video. I have a question, should I still install version 1.5 or should I upgrade to 1.10? Thank you Laura <3

Can you make a tutorial on how to install stable diffusion on windows please

Hiii its not working I get the error "RuntimeError: Failed to import transformers.modeling_utils because of the following error (look up to see its traceback): cannot import name 'computed_field' from 'pydantic' (/usr/local/lib/python3.10/dist-packages/pydantic/__init__.cpython-310-x86_64-linux-gnu.so)" I did same as the video can anyone please help me with this

Thank you so much for the video, you're the best!!

Thanks 😊

Hi i was using your notebook ever since you shared it but suddenly it stopped working. Any advice on how to fix this?

Hi Laura, thank you so much for the tutorial. Does it work on an iPad Air?

Thank you for this set of tutorials. Once again, you've come through for us. I've avoided using comfy for a long time even though I've worked on your channel and others. Now that I've decided to use it, your tutorials are invaluable. I'm now a new patreon member.

You ar SOO good!

I've already installed it, and worked fine! Thank you Laura!

thank you for that PoseMyArt website

I’ve gotten installed. But it won’t generate any image. It just keeps giving me errors in the terminal

Grazie Laura

ComfyUI vs Automatic1111 which one is better, easier to work with?

Nice explanation, thanks!

Thank you!

Omg! I just started learning about AI art AND training muay thai haha. You're awesome!!!

Your tutorial is my solution. Thank you!

Can you use multiple loras for one project ?

Thank you so much for this straightworward tutorial. Just wondered how to update files as new versions would be released

Thank you for this video! I am using Collab Pro I have this error during the training, for both dump_only_textenc and train_only_unet: Traceback (most recent call last): File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 803, in <module> main() File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 640, in main accelerator.init_trackers("dreambooth", config=vars(args)) File "/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py", line 1067, in init_trackers tracker.store_init_configuration(config) File "/usr/local/lib/python3.10/dist-packages/accelerate/tracking.py", line 152, in store_init_configuration self.writer.add_hparams(values, metric_dict={}) File "/usr/local/lib/python3.10/dist-packages/torch/utils/tensorboard/writer.py", line 330, in add_hparams exp, ssi, sei = hparams(hparam_dict, metric_dict, hparam_domain_discrete) File "/usr/local/lib/python3.10/dist-packages/torch/utils/tensorboard/summary.py", line 270, in hparams ssi.hparams[k].string_value = v File "/usr/local/lib/python3.10/dist-packages/google/protobuf/internal/containers.py", line 70, in __getitem__ return self._values[key] TypeError: list indices must be integers or slices, not str Traceback (most recent call last): File "/usr/local/bin/accelerate", line 8, in <module> sys.exit(main()) File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate_cli.py", line 43, in main args.func(args) File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py", line 837, in launch_command simple_launcher(args) File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py", line 354, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['/usr/bin/python3', '/content/diffusers/examples/dreambooth/train_dreambooth.py', '--image_captions_filename', '--train_only_unet', '--save_starting_step=500', '--save_n_steps=0', '--Session_dir=/content/gdrive/MyDrive/Fast-Dreambooth/Sessions/carefour_0.1', '--pretrained_model_name_or_path=/content/stable-diffusion-v2-512', '--instance_data_dir=/content/gdrive/MyDrive/Fast-Dreambooth/Sessions/carefour_0.1/instance_images', '--output_dir=/content/models/carefour_0.1', '--captions_dir=/content/gdrive/MyDrive/Fast-Dreambooth/Sessions/carefour_0.1/captions', '--instance_prompt=', '--seed=942876', '--resolution=512', '--mixed_precision=fp16', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--use_8bit_adam', '--learning_rate=2e-06', '--lr_scheduler=linear', '--lr_warmup_steps=0', '--max_train_steps=1500']' returned non-zero exit status 1. Something went wrong could you help me?

How did you generate image in the thumbnail?

i have error and not started.

was almost finished and then NO SUCH FILE OR DIRECTORY

Thank you! Your video is super helpful!

i did this trying to add a man to my picture and it makes a picture of the man as big as the full image and then just inpaints the little bit that i masked (so for example i masked a little bit to the right of the screen, and it generates a full sized image of the man and then inpaints his arm into the masked area XD)

Will the same method work on Stable Diffusion Forge?

Clearest and most thorough explanation of LoRAs and their creation on YT. Thanks so much.

I love how you explain things. This was so useful.

How do you create venv for Kohya? I'm unable to use my Forge UI with newer version of python required by Koyha. I've heared you can somehow make venv folder so kohya uses localized python, but I have no idea how to do it.

After setting this up when you go to your recent tab in your drive theres a millions files and photos of ppl dogs, anime, etcetera, why is that? is that the training data this program used? can i delete those? its also concerning that setting this up just downloads thousands of unknown images to your drive. anyone understand this better than me?

Selamat Loren

You are Italian aren't you? I looove the accent

Thank you for providing the tutorial and sharing your workflow.

Thanks for the video. Can you do another one on dreamshaper flux finetuning? 😅🥲

Volume in your videos is so low. It's like 30% of normal volume. I guess you just plugin in your microphone to your PC, without using pre-amp/dedicated sound card? I see the same issue in your latest video. You really need to fix it for your audience.

i always have the lines from the openpose model in my images, any ideas ? :(

I want to train on my data and my friends for example Jony, Lisa,.. on the same model is that possible?

Where are you?

As a newby I had to have a few goes at this to get it to work. Deleting the sd folder and starting fresh each time prevented errors. Also, my screen displayed a 'Download LoRA' cell which I ignored and it still worked.