Software Engineering Courses (SECourses)•3y ago

New RunPod template available for Stable Diffusion Web UI: https://runpod.io/gsc?template=ya6013lj5

New RunPod template available for Stable Diffusion Web UI:

https://runpod.io/gsc?template=ya6013lj5a&ref=w18gds2n

Includes:

Ubuntu 22.04 LTS
CUDA 11.8
Python 3.10.6
Automatic1111 Stable Diffusion Web UI 1.3.0
Dreambooth extension (dev branch)
Deforum extension
ControlNet extension v1.1.206
Torch 2.0.1
xformers 0.0.20 (disabled by default)
v1-5-pruned.safetensors
vae-ft-mse-840000-ema-pruned.safetensors

And can now also be used with Network Volumes in Secure Cloud.

ashleyOP•6/1/23, 2:29 PM

Torch 2.0.1 is working fine, been training Dreambooth with it all day.

ashleyOP•6/1/23, 2:31 PM

Just be weary of the Facebook Dadaptation optimizers. They have very specific learning rate settings compared to the others, and especially

Adan Dadaptation

Adan Dadaptation

because it requires about 36GB of VRAM from my testing. The others weren't quite as intense though.

ashleyOP•6/1/23, 3:02 PM

Its actually very easy to set up Kohya_ss on RunPod:

apt update && apt install apt-utils
wget https://raw.githubusercontent.com/bmaltais/kohya_ss/master/setup.sh
chmod +x setup.sh
./setup.sh -d /workspace/kohya_ss
cd /workspace/kohya_ss
./gui.sh --listen 0.0.0.0 --server_port 3000

apt update && apt install apt-utils
wget https://raw.githubusercontent.com/bmaltais/kohya_ss/master/setup.sh
chmod +x setup.sh
./setup.sh -d /workspace/kohya_ss
cd /workspace/kohya_ss
./gui.sh --listen 0.0.0.0 --server_port 3000

It takes care of Python Tk and everything for you.

Aashley Just be weary of the Facebook Dadaptation optimizers. They have very specific l...

flowwolf•6/1/23, 4:34 PM

by very specific, you mean "1" set all learn rates to 1 and it takes care of it all automagically on the fly

flowwolf•6/1/23, 4:35 PM

i've been using dadaptlion this week and it's very succesful

flowwolf•6/1/23, 4:37 PM

here's a terran style i trained with it last night. not the best work. but it sure was easy work. i think improvements could be made on the dataset side but the training went so well. 20images with short minimalist captions. The train image is a good candidate for inpainting, like they're coming up to parallel rails together ready for a hijacking or something. could fixe the long train's cars too

flowwolf•6/1/23, 4:48 PM

Nom•6/1/23, 4:49 PM

@ashleyk I just spent 8 hours trying to fix dreambooth errors in runpod, and then I found this discord, I'm going to try your template to see if I can finally do some training

NNom @ashleyk I just spent 8 hours trying to fix dreambooth errors in runpod, and the...

flowwolf•6/1/23, 4:50 PM

not a waste of time if you consider it learning experience of what to avoid in the future

Fflowwolf not a waste of time if you consider it learning experience of what to avoid in t...

Nom•6/1/23, 4:50 PM

lol true. how did you do your training? also on runpod?

NNom lol true. how did you do your training? also on runpod?

flowwolf•6/1/23, 4:51 PM

i had a good pc already so i upgraded the gpu. big pricetag tho. used kohya's scripts, with the gui

NNom @ashleyk I just spent 8 hours trying to fix dreambooth errors in runpod, and the...

ashleyOP•6/1/23, 4:51 PM

Feel free to DM me if you have any questions or need help with anything.

Nom•6/1/23, 4:54 PM

@ashleyk how do I open the jypter page in your template, it asks for a token/password

NNom @ashleyk how do I open the jypter page in your template, it asks for a token/pas...

ashleyOP•6/1/23, 4:57 PM

You need to specify

JUPYTER_PASSWORD

JUPYTER_PASSWORD

in the environment variables, read the README

Aashley You need to specify `JUPYTER_PASSWORD` in the environment variables, read the RE...

Nom•6/1/23, 5:00 PM

sorry didnt know theres a readme! I got my first error

  Traceback (most recent call last):
2023-06-01T16:59:14.685731564Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/utils.py", line 200, in f
2023-06-01T16:59:14.685746164Z     res = func(*args, **kwargs)
2023-06-01T16:59:14.685748394Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 683, in start_training
2023-06-01T16:59:14.685750304Z     if config.pretrained_vae_name_or_path == "":
2023-06-01T16:59:14.685752134Z AttributeError: 'NoneType' object has no attribute 'pretrained_vae_name_or_path'
2023-06-01T16:59:14.685753844Z

  Traceback (most recent call last):
2023-06-01T16:59:14.685731564Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/utils.py", line 200, in f
2023-06-01T16:59:14.685746164Z     res = func(*args, **kwargs)
2023-06-01T16:59:14.685748394Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 683, in start_training
2023-06-01T16:59:14.685750304Z     if config.pretrained_vae_name_or_path == "":
2023-06-01T16:59:14.685752134Z AttributeError: 'NoneType' object has no attribute 'pretrained_vae_name_or_path'
2023-06-01T16:59:14.685753844Z

NNom sorry didnt know theres a readme! I got my first error 😦 ``` Traceback (most...

ashleyOP•6/1/23, 5:02 PM

Which model are you using as the base?

Nom•6/1/23, 5:03 PM

just the default from the template, 1.5-pruned

Nom•6/1/23, 5:09 PM

I thought maybe pruned is the problem, I downloaded deliberate and got another error from just creating the model

   FileNotFoundError: [Errno 2] No such file or directory: '/workspace/stable-diffusion-webui/models/dreambooth/test/db_config.json'
2023-06-01T17:06:53.652922673Z Exception loading config: [Errno 2] No such file or directory: '/workspace/stable-diffusion-webui/models/dreambooth/test/db_config.json'
2023-06-01T17:06:53.652946353Z Can't load config!

   FileNotFoundError: [Errno 2] No such file or directory: '/workspace/stable-diffusion-webui/models/dreambooth/test/db_config.json'
2023-06-01T17:06:53.652922673Z Exception loading config: [Errno 2] No such file or directory: '/workspace/stable-diffusion-webui/models/dreambooth/test/db_config.json'
2023-06-01T17:06:53.652946353Z Can't load config!

NNom I thought maybe pruned is the problem, I downloaded deliberate and got another e...

ashleyOP•6/1/23, 5:13 PM

DM me and will look into it

felixsanz•6/1/23, 5:20 PM

@Dr. Furkan Gözükara it means that he will re-publish the model as a docker container, isolated inside

felixsanz•6/1/23, 5:20 PM

but i doubt it

Ffelixsanz @Dr. Furkan Gözükara it means that he will re-publish the model as a docker cont...

Furkan Gözükara SECourses•6/1/23, 5:23 PM

ah i see no reason

Furkan Gözükara SECourses•6/1/23, 5:23 PM

people verified hash

felixsanz•6/1/23, 5:23 PM

who?

felixsanz•6/1/23, 5:24 PM

no one verified it actually

Furkan Gözükara SECourses•6/1/23, 5:24 PM

you see in first posts said that hash matches

Furkan Gözükara SECourses•6/1/23, 5:24 PM

the ones before deleted

felixsanz•6/1/23, 5:25 PM

how do you know that account is not involved with a malware version of the model?

felixsanz•6/1/23, 5:25 PM

thay guy is a random one

felixsanz•6/1/23, 5:25 PM

in fact, a collaborator of the repo said that he doesn't have that hash

felixsanz•6/1/23, 5:25 PM

but he's messing md5 with sha256, so who knows. this people is really dumb

Furkan Gözükara SECourses•6/1/23, 5:26 PM

i am pretty sure an average cyber security expert could look into onnx file

Furkan Gözükara SECourses•6/1/23, 5:29 PM

Have too many messages. Will reply all slowly

ashleyOP•6/1/23, 5:30 PM

I honestly don't know where you find all the time in the day to get all the things done that you get done, you have my utmost respect.

Rclemente27•6/1/23, 7:13 PM

Hello! I've been trying to follow this tutorial (https://www.youtube.com/watch?v=TpuDOsuKIBo) but I get this errors when trying to run ".\setup.bat" any idea on how to solve it?:

ERROR: Could not find a version that satisfies the requirement tensorflow==2.10.1 (from versions: 2.12.0rc0, 2.12.0rc1, 2.12.0, 2.13.0rc0, 2.13.0rc1)
ERROR: No matching distribution found for tensorflow==2.10.1

[notice] A new release of pip available: 22.3.1 -> 23.1.2
[notice] To update, run: python.exe -m pip install --upgrade pip
ERROR: Could not find a version that satisfies the requirement xformers==0.0.19 (from versions: 0.0.1, 0.0.2, 0.0.3, 0.0.4, 0.0.5, 0.0.6, 0.0.7, 0.0.8, 0.0.9, 0.0.10, 0.0.11, 0.0.12, 0.0.13, 0.0.16rc424, 0.0.16rc425, 0.0.16, 0.0.20.dev539, 0.0.20.dev540, 0.0.20, 0.0.21.dev541, 0.0.21.dev542)
ERROR: No matching distribution found for xformers==0.0.19

[notice] A new release of pip available: 22.3.1 -> 23.1.2
[notice] To update, run: python.exe -m pip install --upgrade pip
ERROR: triton-2.0.0-cp310-cp310-win_amd64.whl is not a supported wheel on this platform.

YouTubeSECourses

Generate Studio Quality Realistic Photos By Kohya LoRA Stable Diffu...

#Kohya SS web GUI DreamBooth #LoRA training full tutorial. You don't need technical knowledge to follow this tutorial. In this tutorial I have explained how to generate professional photo studio quality portrait / self images for free with Stable Diffusion training.

Our Discord server

https://bit.ly/SECoursesDiscord

If I have been of assis...

felixsanz•6/1/23, 7:20 PM

the error is pretty clear

felixsanz•6/1/23, 7:20 PM

ERROR: Could not find a version that satisfies the requirement tensorflow==2.10.1 (from versions: 2.12.0rc0, 2.12.0rc1, 2.12.0, 2.13.0rc0, 2.13.0rc1)

felixsanz•6/1/23, 7:20 PM

there is no 2.10.1

felixsanz•6/1/23, 7:20 PM

try 2.12.0

▲

▲•6/1/23, 7:40 PM

hello!

its been days i can't use my kohya anymore.
once i start training it freeze and dont proceed.
this is the only error i got in the list

▲

▲•6/1/23, 7:42 PM

▲▲hello! 🙂 its been days i can't use my kohya anymore. once i start training it f...

Furkan Gözükara SECourses•6/1/23, 7:58 PM

hello. did you make a new installation ?

FFurkan Gözükara SECourses hello. did you make a new installation ?

▲

▲•6/1/23, 8:01 PM

3 times

no luck

▲

▲•6/1/23, 8:01 PM

i always chose torch 2 cause i use it for auto1111 (not sure if is shared or whatever)
should i redo install choosing torch 1?

▲▲i always chose torch 2 cause i use it for auto1111 (not sure if is shared or wha...

Furkan Gözükara SECourses•6/1/23, 8:03 PM

dont do that

▲

▲•6/1/23, 8:03 PM

Furkan Gözükara SECourses•6/1/23, 8:03 PM

kohya makes its own venv

Furkan Gözükara SECourses•6/1/23, 8:03 PM

follow as i did

Furkan Gözükara SECourses•6/1/23, 8:03 PM

it wont affect your main install

▲

▲•6/1/23, 8:03 PM

ok so i reinstall and choose torch 1

apt update && apt install apt-utils wget https://raw.githubusercontent.com/bmaltais/kohya_ss/master/setup.sh chmod +x setup.sh ./setup.sh -d /workspace/kohya_ss cd /workspace/kohya_ss ./gui.sh --listen 0.0.0.0 --server_port 3000

Traceback (most recent call last): 2023-06-01T16:59:14.685731564Z File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/utils.py", line 200, in f 2023-06-01T16:59:14.685746164Z res = func(*args, **kwargs) 2023-06-01T16:59:14.685748394Z File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 683, in start_training 2023-06-01T16:59:14.685750304Z if config.pretrained_vae_name_or_path == "": 2023-06-01T16:59:14.685752134Z AttributeError: 'NoneType' object has no attribute 'pretrained_vae_name_or_path' 2023-06-01T16:59:14.685753844Z

FileNotFoundError: [Errno 2] No such file or directory: '/workspace/stable-diffusion-webui/models/dreambooth/test/db_config.json' 2023-06-01T17:06:53.652922673Z Exception loading config: [Errno 2] No such file or directory: '/workspace/stable-diffusion-webui/models/dreambooth/test/db_config.json' 2023-06-01T17:06:53.652946353Z Can't load config!

New RunPod template available for Stable Diffusion Web UI: https://runpod.io/gsc?template=ya6013lj5

Similar Threads

Similar Threads

Similar Threads