Software Engineering Courses (SECourses)•3y ago

To downgrade back to older Torch first delete venv, let it reinstall, then activate venv and run thi

To downgrade back to older Torch first delete venv, let it reinstall, then activate venv and run this command pip install -r "path_of_SD_Extension\requirements.txt"

SSeb i tried to follow this video https://www.youtube.com/watch?v=mnCY8uM7E50&list=PL...

Furkan Gözükara SECoursesOP•3/18/23, 2:07 PM

1 : xformers is included in another script now. dont worry about that

Furkan Gözükara SECoursesOP•3/18/23, 2:08 PM

2: doggy photos meaning that your prompt is not correct. show settings i can tell you

FFurkan Gözükara SECourses To downgrade back to older Torch first delete venv, let it reinstall, then activ...

CPI_MrRagingBull 🇬🇧•3/18/23, 2:18 PM

Sorry. You recommending this to my issue

FFurkan Gözükara SECourses 2: doggy photos meaning that your prompt is not correct. show settings i can tel...

Seb•3/18/23, 2:22 PM

Thank you for your quick reply!

This is the setting I have, followed almost exactly from your video:
!accelerate launch train_dreambooth.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--pretrained_vae_name_or_path="stabilityai/sd-vae-ft-mse" \
--output_dir=$OUTPUT_DIR \
--revision="fp16" \
--with_prior_preservation --prior_loss_weight=1.0 \
--seed=1337 \
--resolution=512 \
--train_batch_size=1 \
--train_text_encoder \
--mixed_precision="fp16" \
--use_8bit_adam \
--gradient_accumulation_steps=1 \
--learning_rate=1e-6 \
--lr_scheduler="constant" \
--lr_warmup_steps=256 \
--num_class_images=384 \
--sample_batch_size=4 \
--max_train_steps=2560 \
--save_interval=10000 \
--save_sample_prompt="photo of zwx dog" \
--concepts_list="concepts_list.json"

Seb•3/18/23, 2:23 PM

there are some errors that doesnt seems to appears on your video too:
The following values were not passed to accelerate launchaccelerate launch and had
To avoid this warning pass in values for each of the problematic parameters or run accelerate configaccelerate config.
2023-03-18 13:50:17.755195: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-03-18 13:50:20.351469: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib64-nvidia
2023-03-18 13:50:20.351702: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib64-nvidia
2023-03-18 13:50:20.351727: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
/usr/local/lib/python3.9/dist-packages/accelerate/accelerator.py:243: FutureWarning: logging_dirlogging_dir is deprecated and will be removed in version 0.18.0 of

Accelerate. Use project_dirproject_dir instead.
warnings.warn(

Seb•3/18/23, 2:23 PM

/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/paths.py:105: UserWarning: /usr/lib64-nvidia did not contain libcudart.so as expected! Searching further paths...
warn(
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')}
warn(
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-2rmy4vqcs4arz --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true'), PosixPath('--listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https')}
warn(
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}
warn(
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//ipykernel.pylab.backend_inline'), PosixPath('module')}
warn(
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...

CCPI_MrRagingBull 🇬🇧Sorry. You recommending this to my issue

Furkan Gözükara SECoursesOP•3/18/23, 2:24 PM

if your graphic card is now 2000+ yes

SSeb Thank you for your quick reply! This is the setting I have, followed almost exa...

Furkan Gözükara SECoursesOP•3/18/23, 2:24 PM

,your save sample is

Furkan Gözükara SECoursesOP•3/18/23, 2:24 PM

--save_sample_prompt="photo of zwx dog" \

Furkan Gözükara SECoursesOP•3/18/23, 2:24 PM

you see

FFurkan Gözükara SECourses if your graphic card is now 2000+ yes

CPI_MrRagingBull 🇬🇧•3/18/23, 2:24 PM

Im using RTX 3060 12GB with Auto1111

Furkan Gözükara SECoursesOP•3/18/23, 2:24 PM

also i have more up to date video that will help you tremendously : https://youtu.be/kIyqAdd_i10

YouTubeSECourses - Software Engineering Courses

Stable Diffusion Google Colab, Continue, Directory, Transfer, Clone...

Our Discord : https://discord.gg/HbqgGaZVmr. This is the video where you will learn how to use Google Colab for Stable Diffusion. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on

https://www.patreon.com/SECourses

Playlist of Stable Diffusion Tutorials, #Automatic1111...

CCPI_MrRagingBull 🇬🇧Im using RTX 3060 12GB with Auto1111

Furkan Gözükara SECoursesOP•3/18/23, 2:24 PM

use torch 2 better

FFurkan Gözükara SECourses use torch 2 better

CPI_MrRagingBull 🇬🇧•3/18/23, 2:25 PM

So that is what i am using but should my TI be learning at the slow rate?

FFurkan Gözükara SECourses also i have more up to date video that will help you tremendously : https://yout...

Seb•3/18/23, 2:26 PM

ok thanks, will give it a try again!

AlaBeat•3/18/23, 2:28 PM

hi when i try to update to torch 2 i get this ERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'C:\Users\me\stable-diffusion-webui\venv\Lib\site-packages\~orch\lib\asmjit.dll'
Check the permissions.

CCPI_MrRagingBull 🇬🇧So that is what i am using but should my TI be learning at the slow rate?

Furkan Gözükara SECoursesOP•3/18/23, 2:30 PM

so your TI slower with torch 2? interesting maybe it is because automatic1111 still didnt move torch 2 yet

AAlaBeat hi when i try to update to torch 2 i get this ERROR: Could not install packages ...

Furkan Gözükara SECoursesOP•3/18/23, 2:31 PM

run cmd as administrator

Furkan Gözükara SECoursesOP•3/18/23, 2:31 PM

also i would install web ui directly into C drive not inside users folder

AlaBeat•3/18/23, 2:32 PM

problem is i already running out of space and will delete sd folder at some point and move it to another directory, but until my new ssd arrives i will still keep it there

FFurkan Gözükara SECourses so your TI slower with torch 2? interesting maybe it is because automatic1111 st...

CPI_MrRagingBull 🇬🇧•3/18/23, 2:33 PM

Yep. after watching your new video I updated to the new torch 2.0. I am using the learning rate of 0.005:200, 0.002:500, 0.001:3000, 0.0005.

CCPI_MrRagingBull 🇬🇧Yep. after watching your new video I updated to the new torch 2.0. I am using th...

Furkan Gözükara SECoursesOP•3/18/23, 2:33 PM

i didnt try such learning rate. the constant one was good for me

FFurkan Gözükara SECourses i didnt try such learning rate. the constant one was good for me

CPI_MrRagingBull 🇬🇧•3/18/23, 2:34 PM

I will try with the default 0.005 learning rate and see if that makes a difference

FFurkan Gözükara SECourses i didnt try such learning rate. the constant one was good for me

CPI_MrRagingBull 🇬🇧•3/18/23, 2:43 PM

Ok it was the learning rate. 0.005 seems to have done the trick

CCPI_MrRagingBull 🇬🇧Ok it was the learning rate. 0.005 seems to have done the trick

Furkan Gözükara SECoursesOP•3/18/23, 3:02 PM

it is also official rate used by the paper authors

FFurkan Gözükara SECourses also i have more up to date video that will help you tremendously : https://yout...

Seb•3/18/23, 3:30 PM

is it normal to run the training for 48hrs?
i followed through the guide in the 2nd video you provided, and using the same setting as your teach on video one
after almost an hr
Generating class images: 2% 218/12596 [49:33<46:40:49, 13.58s/it]

SSeb is it normal to run the training for 48hrs? i followed through the guide in the ...

Furkan Gözükara SECoursesOP•3/18/23, 3:36 PM

generate class images through txt2img tab

Furkan Gözükara SECoursesOP•3/18/23, 3:36 PM

it will be much much faster like 20x more maybe more

FFurkan Gözükara SECourses generate class images through txt2img tab

Seb•3/18/23, 3:39 PM

what do you means by that? i am just trying to use the colab and generate the avatar.
last time when it shows doggy it takes around 1hrs to generate the file
and i use the new dreambooth by that new link and it 48 times the time
I am just not sure what i did wrong here

SSeb what do you means by that? i am just trying to use the colab and generate the av...

Furkan Gözükara SECoursesOP•3/18/23, 3:41 PM

ah you are on colab

Furkan Gözükara SECoursesOP•3/18/23, 3:41 PM

how many training images you have?

FFurkan Gözükara SECourses ah you are on colab

Seb•3/18/23, 3:42 PM

32, just trying through exactly what you did in video

SSeb 32, just trying through exactly what you did in video

Furkan Gözükara SECoursesOP•3/18/23, 3:45 PM

how many classification images you set?

Furkan Gözükara SECoursesOP•3/18/23, 3:45 PM

12596 is too many

Furkan Gözükara SECoursesOP•3/18/23, 3:45 PM

select classification image count like 24

Furkan Gözükara SECoursesOP•3/18/23, 3:45 PM

so enter total 32*24

Seb•3/18/23, 3:46 PM

ah ic. i know what i did wrong there. is there a way to stop the process and restart it?

Seb•3/18/23, 3:46 PM

nvm i got it now! thanks heaps!

Seb•3/18/23, 3:49 PM

i am also trying out the your other video on my own pc
https://www.youtube.com/watch?v=mfaqqL5yOO4
however, after the installed the dreambooth extension, and restart both ui and the stable diffusion, the dreambooth tab hasnt appear at all? is there a way to fix it?

YouTubeSECourses - Software Engineering Courses

How To Do Stable Diffusion LORA Training By Using Web UI On Differe...

Our Discord : https://discord.gg/HbqgGaZVmr. Ultimate guide to the LoRA training. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on

https://www.patreon.com/SECourses

Playlist of Stable Diffusion Tutorials, #Automatic1111 and Google Colab Guides, DreamBooth, Textual In...

SSeb i am also trying out the your other video on my own pc https://www.youtube.com/w...

Furkan Gözükara SECoursesOP•3/18/23, 4:00 PM

yes

Furkan Gözükara SECoursesOP•3/18/23, 4:00 PM

first welcome

Furkan Gözükara SECoursesOP•3/18/23, 4:00 PM

here the newest dreambooth install video

Furkan Gözükara SECoursesOP•3/18/23, 4:00 PM

https://youtu.be/pom3nQejaTs

YouTubeSECourses - Software Engineering Courses

How To Install New DREAMBOOTH & Torch 2 On Automatic1111 Web UI PC ...

Discord : https://bit.ly/SECoursesDiscord. Torch 2 / Pytorch 2 is now supported along with new DreamBooth Automatic1111 Web UI extension. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on

https://www.patreon.com/SECourses

In this video, I am explaining how you can man...

AlaBeat•3/18/23, 4:07 PM

after installing torch 2 i get this in my cmd when i run sd, everything works but i get this C:\Users\me\stable-diffusion-webui\venv\lib\site-packages\torchvision\transforms\functional_tensor.py:5: UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be removed in 0.17. Please don't rely on it. You probably just need to use APIs in torchvision.transforms.functional or in torchvision.transforms.v2.functional.
warnings.warn(

AAlaBeat after installing torch 2 i get this in my cmd when i run sd, everything works bu...

Furkan Gözükara SECoursesOP•3/18/23, 4:14 PM

if working just ignore it

Furkan Gözükara SECoursesOP•3/18/23, 4:18 PM

working on style video

Furkan Gözükara SECoursesOP•3/18/23, 4:18 PM

Furkan Gözükara SECoursesOP•3/18/23, 4:18 PM

style + myself

AlaBeat•3/18/23, 4:33 PM

ok now when i try to use loras i get this Error running process_batch: C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\additional_networks.py
Traceback (most recent call last):
File "C:\Users\me\stable-diffusion-webui\modules\scripts.py", line 427, in process_batch
script.process_batch(p, *script_args, **kwargs)
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\additional_networks.py", line 209, in process_batch
network, info = lora_compvis.create_network_and_apply_compvis(du_state_dict, weight_tenc, weight_unet, text_encoder, unet)
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 102, in create_network_and_apply_compvis
state_dict = network.apply_lora_modules(du_state_dict) # some weights are applied to text encoder
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 289, in apply_lora_modules
state_dict = LoRANetworkCompvis.convert_state_dict_name_to_compvis(self.v2, du_state_dict)
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 193, in convert_state_dict_name_to_compvis
compvis_name = LoRANetworkCompvis.convert_diffusers_name_to_compvis(v2, tokens[0])
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 182, in convert_diffusers_name_to_compvis
assert cv_name is not None, f"conversion failed: {du_name}. the model may not be trained by sd-scriptssd-scripts."
AssertionError: conversion failed: lora_unetdown

AlaBeat•3/18/23, 4:35 PM

none of my loras work

To downgrade back to older Torch first delete venv, let it reinstall, then activate venv and run thi

Similar Threads