Software Engineering Courses (SECourses)•3y ago

yes runpod works

Furkan Gözükara SECoursesOP•5/26/23, 1:41 AM

i have necessary tutorials

Furkan Gözükara SECoursesOP•5/26/23, 1:42 AM

you can see tutorials list here : https://github.com/FurkanGozukara/Stable-Diffusion

GitHub

GitHub - FurkanGozukara/Stable-Diffusion: Best Stable Diffusion and...

Best Stable Diffusion and AI Tutorials, Guides, News, Tips and Tricks - GitHub - FurkanGozukara/Stable-Diffusion: Best Stable Diffusion and AI Tutorials, Guides, News, Tips and Tricks

Furkan Gözükara SECoursesOP•5/26/23, 1:42 AM

search runpod word

Furkan Gözükara SECoursesOP•5/26/23, 1:42 AM

i am going to sleep hopefully see you tomorrow

FFurkan Gözükara SECourses yes runpod works

kevh•5/26/23, 1:43 AM

thank you! is there a way to use google colab to do it? just because i already have some compute on google colab and don't want to waste them

thebean•5/26/23, 3:52 AM

me: i don't really understand truncation error with regards to image diffusion samplers. can you lay it out in eli5 terms for me?

ChatGPT said:
Sure! Let's say you're baking cookies and the recipe calls for 1/3 cup of sugar. But your measuring cups only have 1/4 cup and 1/2 cup.

If you use the 1/4 cup, you won't be adding enough sugar. If you use the 1/2 cup, it will be too much. So, you decide to fill the 1/4 cup and add a little bit more, hoping it's about 1/3 cup.

The difference between the amount of sugar you actually added and the exact 1/3 cup the recipe called for is like the truncation error. It's a small error that comes from having to stop (or "truncate") your measuring because you don't have the exact tool (in this case, the right measuring cup) to get the precise amount.

In the case of the image diffusion, the "sampling steps" are like the measuring cups. If you could do an infinite number of steps, you could get the exact, perfect result. But in reality, you have to stop at some point (just like you can't keep adding sugar forever), and this results in a small error. Increasing the number of steps is like adding a bit more sugar to the 1/4 cup to try and get closer to the exact 1/3 cup you need.

thebean•5/26/23, 3:52 AM

how correct did chatGPT get this i wonder?

生

生死•5/26/23, 4:03 AM

hey guys i try this vedio but the cmd show this is means i dont process in GPU? my gpu is RX6600

生

生死•5/26/23, 4:03 AM

https://www.youtube.com/watch?v=ku6UvK1bsp4

YouTubeSECourses

Dolly 2.0 : Free ChatGPT-like Model for Commercial Use - How To Ins...

Databricks’ #Dolly v2 is a free, open source, commercially useable ChatGPT-style #AI model. Dolly 2.0 could spark a new wave of fully open source LLMs similar to #ChatGPT . Open source community working hardest to bring up a model that can compete with GPT4. Our discord: https://bit.ly/SECoursesDiscord

If I have been of assistance to you and yo...

生

生死•5/26/23, 4:07 AM

生生死 hey guys i try this vedio but the cmd show this is means i dont process in GPU? ...

thebean•5/26/23, 4:08 AM

i'm a nooby, but from what others have told me, AMD doesn't work well with machine learning stuff like stable diffusion (yet)

生

生死•5/26/23, 4:09 AM

oh that too bad QQ

thebean•5/26/23, 4:09 AM

i'm not familiar with the specific error message your seeing, so maybe someone can give better help. i'm not saying AMD can't run stable diffusion

thebean•5/26/23, 4:10 AM

just that it isn't as stable as an nvidia card or as easy

生

生死•5/26/23, 4:11 AM

alright i will try this again with my own computer

生

生死•5/26/23, 4:11 AM

thx

thebean•5/26/23, 4:11 AM

good luck

AlmoIppy•5/26/23, 5:06 AM

Was wondering if there is any way to instruct SD (A1111) within prompt to only apply lora to specific subjects? Say I have a lora that generates specific person, if I put few subjects it will usually apply lora to them to all, is there a way to limit lora's influence to only one specific subject without having to use regional prompt or other similar extensions?

undelirium•5/26/23, 5:41 AM

yes there is, you need to learn to use latent couple and masking

undelirium•5/26/23, 5:42 AM

also if people werent aware https://discord.com/invite/stablediffusion

undelirium•5/26/23, 5:42 AM

theyre letting you test and vote on SDXL (reportedly 50% done)

undelirium•5/26/23, 5:42 AM

ive 3 prompts currently in the current round of voting which is neat

AAlmoIppy Was wondering if there is any way to instruct SD (A1111) within prompt to only a...

undelirium•5/26/23, 5:44 AM

I see now you are asking without using those extensions. your best bet becomes inpainting i guess.

undelirium•5/26/23, 5:54 AM

i really recommend latent couple tho since it lets you create masks and define each one in a single prompt, ill give example:

05429-1536x768-__favorites_V08_V08-DPM202M20Karras-35-7-highly20detailed20horror20film.png

undelirium•5/26/23, 5:55 AM

using control net plus latent couple i could define all 6 characters. i can bring them out a lot more with more control nets and defined details

undelirium•5/26/23, 5:55 AM

thetres a lot of room for flexibility with the modified softedge_hedsafe control net im using

undelirium•5/26/23, 5:58 AM

the bottom right image is the latent couple mask, the colors are arranged in order that they'll fill out in the form underneath, white being the general prompt for scene with left to right in color being each character. you can do it with loras. there was a bug for a bit using loras in prompts, but i think tehy fixed it? so if you were to make an openpose control net and latent couple each pose similar to how my masking was done, your prompt would read:
generral scene of scene-like things and such BREAK
AND <lora A:0.6> BREAK
AND <lora B:0.6> BREAK
AND <lora C:0.6> BREAK
AND <lora D:0.6>

undelirium•5/26/23, 5:59 AM

you have to use those steps tho if you want to do what you're talkingabout in one generation

undelirium•5/26/23, 6:00 AM

I am not using loras for my image, but this is the only way i know how. i know you wanted a different answer but hope this might help

undelirium•5/26/23, 6:35 AM

better render and more info

Kkevh thank you! is there a way to use google colab to do it? just because i already h...

Furkan Gözükara SECoursesOP•5/26/23, 9:04 AM

for google colab it is not working as good as on your pc

Tthebean me: i don't really understand truncation error with regards to image diffusion s...

Furkan Gözükara SECoursesOP•5/26/23, 9:04 AM

ChatGPT has no idead about stable diffusion yet. but i am planning an in depth tutorial for this

生生死 hey guys i try this vedio but the cmd show this is means i dont process in GPU? ...

Furkan Gözükara SECoursesOP•5/26/23, 9:06 AM

hi. probably they dont support amd right away. there could be way to make it work but i havent tested

Uundelirium i really recommend latent couple tho since it lets you create masks and define e...

Furkan Gözükara SECoursesOP•5/26/23, 9:08 AM

you are using latent couple extension? this is something i plan to cover

undelirium•5/26/23, 9:21 AM

Yes. I love the feature of defining a mask as it allows. I've not tried regional prompter or whatever it's called, I looked at it and it seemed to be a step backwards in function

undelirium•5/26/23, 9:23 AM

Total power over generations between latent couple and control net, tho to fully utilize latent couple, requires some skill with Photoshop or similar for precision. The control net segment preprocessor might have some potential too. I've not tried it just considered it.

ashley•5/26/23, 9:41 AM

I aim finding that I get better training results using linearlinear as the learning rate scheduler than using constant_with_warmupconstant_with_warmup

undelirium•5/26/23, 9:46 AM

Personally cosine and polynomial have given me good results. Seems to be a matter of just finding settings. There's a write up in discussions for dreambooth on GitHub that has a very thorough fleshing out of how to do your settings according to a formula.
https://github.com/d8ahazard/sd_dreambooth_extension/discussions/547

GitHub

[Pre-Final] A large research of the main training parameters *Updat...

NEW UPDATE Updated formulas for calculating frame resolutions. Also updates with permissions were carried out in the table with mathematics. The custom lr_scheduler has been moved to a separate doc...

Uundelirium Personally cosine and polynomial have given me good results. Seems to be a matte...

ashley•5/26/23, 9:50 AM

Thanks, any chance you could share your settings with me?

Furkan Gözükara SECoursesOP•5/26/23, 10:32 AM

newest xformers is compatiable with torch 2.0.1

Uundelirium Personally cosine and polynomial have given me good results. Seems to be a matte...

Furkan Gözükara SECoursesOP•5/26/23, 10:33 AM

i tested a lot in this video : https://youtu.be/sRdtVanSRl4

YouTubeSECourses

Epic Web UI DreamBooth Update - New Best Settings - 10 Stable Diffu...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Web UI DreamBooth got epic update and we tested all new features to find the best settings (10). 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...

FFurkan Gözükara SECourses i tested a lot in this video : https://youtu.be/sRdtVanSRl4

ashley•5/26/23, 10:35 AM

Buy these are all constant_with_warmup aren't they? and polynomial and linear both work better.

undelirium•5/26/23, 10:41 AM

@ashleyk I would not presume to know better than the good doctor.

I am mobile at this time and cannot access my dreambooth settings. The advantage I like of any scheduler on a curve is that it greatly helps with avoiding over fitting. Lots of ways to preserve the model you train on.

undelirium•5/26/23, 10:41 AM

But I cannot argue with the doctor's results.

FFurkan Gözükara SECourses i tested a lot in this video : https://youtu.be/sRdtVanSRl4

undelirium•5/26/23, 10:42 AM

It's 6am here and bed time, but as I need to get back into training this weekend, ty for the link. I will definitely watch. I've been bookmarking several of your courses for references.

Uundelirium It's 6am here and bed time, but as I need to get back into training this weekend...

ashley•5/26/23, 10:45 AM

This video is awesome, you definitely need to watch it if you have not already done so

undelirium•5/26/23, 10:46 AM

I plan to. His courses are fantastic. This weekend I have a lot of work I need to get done, so I'll be training to his spec and looking forward to the results

undelirium•5/26/23, 10:47 AM

I am really putting my 3090 TI through the ringer! Wish I had a 4090 but I can't be unhappy with what I do have.

ashley•5/26/23, 10:55 AM

Yeah you are fortunate to have your own GPU, I don't have a GPU so use the cloud for training

Diego•5/26/23, 11:13 AM

@Furkan Gözükara SECourses I'm trying to do dreambooth training using the Inkpunk model to get the same style but I'm having a few errors. Using 1 x A100 80GB
24 vCPU 125 GB RAM on Runpod.

I installed dreambooth manually, changed the requirements, but when training I get this error:
AssertionError:
from user code:
File "/workspace/venv/lib/python3.10/site-packages/torch/random.py", line 23, in get_rng_state
return default_generator.get_state()
Set torch._dynamo.config.verbose=True for more information

So I tried installing torch torch 1.13 following the steps in https://www.youtube.com/watch?v=zA4LksIVas8&ab_channel=SECourses

pip3 install torch==1.13.1 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117

pip uninstall xformers

pip install https://huggingface.co/MonsterMMORPG/SECourses/resolve/main/xformers-0.0.19-cp310-cp310-manylinux2014_x86_64.whl

In dreambooth extension folder: pip install -r requirements.txt

Installed VAE file

Restart pod

fuser -k 3000/tcp

But now when I type Python relauncher.py it won't start:( I get this error: TypeError: expected string or bytes-like object

I've stayed awake many hours trying to solve this but can't. Please help

YouTubeSECourses

RunPod Fix For DreamBooth & xFormers - How To Use Automatic1111 Web...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. How to install latest version of Automatic1111 Web UI and #DreamBooth on #RunPod. 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 #StableDiffusi...

yes runpod works

Similar Threads

Similar Threads

Similar Threads