Software Engineering Courses (SECourses)•3y ago

Hey @Dr. Furkan Gözükara is it possible to generate the same model (same face/ hair/ body proportion

Hey @Dr. Furkan Gözükara is it possible to generate the same model (same face/ hair/ body proportions) but in different poses or backgrounds in stable diffusion? I been trying to generate a consistent character but am having a difficult time

teachtaha•6/5/23, 5:50 AM

File "D:\voice cloning\tortoise-tts-fast\scripts\tortoise_tts.py", line 15, in <module>
from tortoise.api import MODELS_DIR, TextToSpeech
ModuleNotFoundError: No module named 'tortoise.api'
Please help! I really need to get this tts model working.

FFurkan Gözükara SECourses currently kohya latest version broken. updated readme file : https://github.com/...

ashley•6/5/23, 6:40 AM

Thanks, thought I was doing something wrong.

Akash trickster•6/5/23, 8:34 AM

Hey guys , i want to use lora models in stable diffusion, but i don't know how to update or use lora inside stable diffusion, i tried to update my repository but can't, any help for this , thanks in advance

Akash trickster•6/5/23, 8:35 AM

ashley•6/5/23, 8:35 AM

Automatic1111 v1.3.2 was released today:

https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.3.2

GitHub

Release 1.3.2 · AUTOMATIC1111/stable-diffusion-webui

1.3.2
Bug Fixes:

fix files served out of tmp directory even if they are saved to disk
fix postprocessing overwriting parameters

AAkash trickster Click to see attachment

Akash trickster•6/5/23, 8:38 AM

I used git pull command but can't update to lastest stable diffusion version

AAkash trickster I used git pull command but can't update to lastest stable diffusion version

ashley•6/5/23, 8:55 AM

Not sure what the issue is, it says its installing requirements, I don't see any errors

Aashley Not sure what the issue is, it says its installing requirements, I don't see any...

Akash trickster•6/5/23, 9:00 AM

I cannot see something like this after the installation, and i don't know how to use lora models, i cannot find lora checkpoint in my models tab in stabel diffusion

Screenshot_2023-06-05-13-59-19-71_f9ee0578fe1cc94de7482bd41accb329.jpg

Cchyler Hey @Dr. Furkan Gözükara is it possible to generate the same model (same face/ h...

Furkan Gözükara SECourses•6/5/23, 9:16 AM

yes possible but try use as many as possible distances and poses in your training set for best quality

Aashley Thanks, thought I was doing something wrong.

Furkan Gözükara SECourses•6/5/23, 9:18 AM

nah current version shows no errors but dont learn

Tteachtaha File "D:\voice cloning\tortoise-tts-fast\scripts\tortoise_tts.py", line 15, in <...

teachtaha•6/5/23, 9:29 AM

Sir @Dr. Furkan Gözükara please guide!

Steckdose007•6/5/23, 9:33 AM

Hi, i want to fine tune a conditioned img2img stable diffusion model on the FFHQ aging dataset. The aim to create a model where you can age a picture of yourself. But i have trouble creating the training process in torch and i can't find any related work. Does sombody know anything related or can help me?

Tteachtaha Sir @Dr. Furkan Gözükara please guide!

Furkan Gözükara SECourses•6/5/23, 9:35 AM

probably install error

Furkan Gözükara SECourses•6/5/23, 9:35 AM

i would do reinstall

Furkan Gözükara SECourses•6/5/23, 9:35 AM

also use python 3.10.x

FFurkan Gözükara SECourses i would do reinstall

teachtaha•6/5/23, 10:00 AM

Though I am using 3.10.9. btw u mean python reinstall or everything from scratch?

teachtaha•6/5/23, 10:01 AM

@Dr. Furkan Gözükara

Tteachtaha Though I am using 3.10.9. btw u mean python reinstall or everything from scratch...

Furkan Gözükara SECourses•6/5/23, 10:12 AM

Install tortoise from scratch

Furkan Gözükara SECourses•6/5/23, 10:12 AM

Without skipping step

FFurkan Gözükara SECourses yes possible but try use as many as possible distances and poses in your trainin...

chylerOP•6/5/23, 10:30 AM

As in I make my own checkpoint model? I was trying to do that but was having issues with generating the same face, as well as getting full body portraits, stable diffusion to prefer generating upper body shots or head shots

Cchyler As in I make my own checkpoint model? I was trying to do that but was having iss...

Furkan Gözükara SECourses•6/5/23, 10:31 AM

my new workflow may help you

Furkan Gözükara SECourses•6/5/23, 10:31 AM

working on it

FFurkan Gözükara SECourses working on it

chylerOP•6/5/23, 10:32 AM

Thank you, looking forward to it

Furkan Gözükara SECourses•6/5/23, 10:35 AM

delete venv worked

Zono50•6/5/23, 11:03 AM

@Dr. Furkan Gözükara hey doc, can you send me the link to the updated dreambooth/lora video you did? Can't find it for some reason

djent0101•6/5/23, 11:04 AM

@Dr. Furkan Gözükara Hello! It seems you are someone who wants to use runpod.io with JupyterLab for Stable Diffusion training, and you watched the YouTube video at https://youtu.be/QN1vdGhjcRc. However, when you double-click on "webui-user.sh" as shown at 15:20 in the video, you encounter a "File Load Error" with the message "Unexpected token '<', "<html><hea"... is not valid JSON". You are wondering why this is happening and how to resolve it.

YouTubeSECourses

Ultimate RunPod Tutorial For Stable Diffusion - Automatic1111 - Dat...

Sign up RunPod: https://bit.ly/RunPodIO. Our Discord : https://discord.gg/HbqgGaZVmr. This is the Grand Master tutorial for running Stable Diffusion via Web UI on RunPod cloud services. 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...

ZZono50 @Dr. Furkan Gözükara hey doc, can you send me the link to the updated dreambooth...

Furkan Gözükara SECourses•6/5/23, 11:09 AM

no video. same video but github file updated

Ddjent0101 @Dr. Furkan Gözükara Hello! It seems you are someone who wants to use runpod.io ...

Furkan Gözükara SECourses•6/5/23, 11:09 AM

could be related browser

Furkan Gözükara SECourses•6/5/23, 11:09 AM

currently i am opening it with double click

Aashley Not sure what the issue is, it says its installing requirements, I don't see any...

Furkan Gözükara SECourses•6/5/23, 11:10 AM

any idea for this : i need help with unzipping password protected zip file on runpod jupyter lab

FFurkan Gözükara SECourses could be related browser

djent0101•6/5/23, 11:17 AM

I am running runpod through Google Chrome and in the video, they also demonstrate opening "webui-user.sh" by double-clicking. I am not sure what problem I have encountered.

FFurkan Gözükara SECourses any idea for this : i need help with unzipping password protected zip file on ru...

ashley•6/5/23, 11:21 AM

Just unzip it with terminal, it will prompt for the password. Usually unzip is not installed on runpod images though so just install it first:

apt update
apt install unzip

apt update
apt install unzip

Zono50•6/5/23, 11:22 AM

@Dr. Furkan Gözükara on the updated dreambooth, what's good learning rates or tenc learning rates?

Zono50•6/5/23, 11:22 AM

Training a lora

FFurkan Gözükara SECourses Install tortoise from scratch

teachtaha•6/5/23, 11:57 AM

@Dr. Furkan Gözükara Thanks a ton

It worked. I was missing the full stop at the end of requirements command line.

Aashley Just unzip it with terminal, it will prompt for the password. Usually unzip is ...

Furkan Gözükara SECourses•6/5/23, 12:11 PM

it turns out for my zipping 7zip was necessary

Furkan Gözükara SECourses•6/5/23, 12:11 PM

i updated patreon post

ZZono50 @Dr. Furkan Gözükara on the updated dreambooth, what's good learning rates or te...

Furkan Gözükara SECourses•6/5/23, 12:11 PM

not sure. i still use lion and 1e-7

Ddjent0101 I am running runpod through Google Chrome and in the video, they also demonstrat...

Furkan Gözükara SECourses•6/5/23, 12:11 PM

ye weird

Zono50•6/5/23, 12:12 PM

@Dr. Furkan Gözükara What are you using for Lora rates?

ZZono50 @Dr. Furkan Gözükara What are you using for Lora rates?

Furkan Gözükara SECourses•6/5/23, 12:22 PM

i used default

Zono50•6/5/23, 12:45 PM

can i use 512x512 images that have been upscaled using 4x ultrasharp to 1024x1024 for training in dreambooth?

ZZono50 can i use 512x512 images that have been upscaled using 4x ultrasharp to 1024x102...

Furkan Gözükara SECourses•6/5/23, 12:48 PM

why not i think you can

Zono50•6/5/23, 12:55 PM

I'll give it a shot and we shall see

Furkan Gözükara SECourses•6/5/23, 2:00 PM

i have updated both kohya and roop readme files

Furkan Gözükara SECourses•6/5/23, 2:00 PM

both working

Furkan Gözükara SECourses•6/5/23, 2:00 PM

https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/1-Click-DeepFake-Tutorial.md

GitHub

Stable-Diffusion/1-Click-DeepFake-Tutorial.md at main · FurkanGozuk...

Best Stable Diffusion and AI Tutorials, Guides, News, Tips and Tricks - Stable-Diffusion/1-Click-DeepFake-Tutorial.md at main · FurkanGozukara/Stable-Diffusion

Furkan Gözükara SECourses•6/5/23, 2:00 PM

https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/Generate-Studio-Quality-Realistic-Photos-By-Kohya-LoRA-Stable-Diffusion-Training-Full-Tutorial.md

GitHub

Stable-Diffusion/Generate-Studio-Quality-Realistic-Photos-By-Kohya-...

Best Stable Diffusion and AI Tutorials, Guides, News, Tips and Tricks - Stable-Diffusion/Generate-Studio-Quality-Realistic-Photos-By-Kohya-LoRA-Stable-Diffusion-Training-Full-Tutorial.md at main · ...

Nom•6/5/23, 2:30 PM

has anyone tried training multiple concept? I noticed that it basically doubled the steps, so it seems like it's simply just training one concept and than continuing to the second concept. Is it the same as just doing two training?

Zono50•6/5/23, 3:19 PM

where does dreambooth generate the sample images?

Hey @Dr. Furkan Gözükara is it possible to generate the same model (same face/ hair/ body proportion

Similar Threads