Software Engineering Courses (SECourses)•3y ago

running 3 pods for experiments

Furkan Gözükara SECoursesOP•3/8/23, 12:43 AM

this is sponsored by one of our viewers

FFurkan Gözükara SECourses running 3 pods for experiments

Haashim•3/8/23, 12:53 AM

nice.. I just put $15 yesterday and already need more lol

Haashim•3/8/23, 12:54 AM

I should use a smaller GPU

HHaashim nice.. I just put $15 yesterday and already need more lol

Furkan Gözükara SECoursesOP•3/8/23, 12:55 AM

ye they consume a lot

Furkan Gözükara SECoursesOP•3/8/23, 1:06 AM

I going to sleep hopefully see you tomorrow

Ttouchdown After updating the DreamBooth, I found a problem where I cannot create a checkpo...

Trimac•3/8/23, 1:26 AM

This is what i thought sd is so unstable for now, the scary part i have one gpu rtx 3060 12gb not able to power on anymore after 2 months of consistent training on dreambooth

dave5555•3/8/23, 1:31 AM

so yeah stable tuner runpod script is broken currently

Trimac•3/8/23, 1:32 AM

Run pod is utilizing a sort of gpu farm like mining setups, How about in SD local can we do atleast 2 gpu running in one board? to improve our work flow since i was cyypto miner b4 i have extra cards here that might help some of us eith extras

dave5555•3/8/23, 1:32 AM

ModuleNotFoundError: No module named 'dataloaders_util' is error the stable tuner throws

dave5555•3/8/23, 1:33 AM

I'll need to fix it in regards to the runpod integration is what dev says

Trimac•3/8/23, 1:52 AM

Ey guys! In dreambooth do you have to select specific 1.5 model on top?

Trimac•3/8/23, 1:52 AM

Trimac•3/8/23, 1:53 AM

I want to use deliberate model for face training and im unsure if i have to base something above

TTrimac I want to use deliberate model for face training and im unsure if i have to base...

dave5555•3/8/23, 2:01 AM

should be just in the create area you select base model, the main model shouldnt matter

P1pSl1p•3/8/23, 2:03 AM

in here select the model you want to train on

P1pSl1p•3/8/23, 2:03 AM

Source checkpoint

Trimac•3/8/23, 2:21 AM

I have 15 images 512 what learning rate should we start? is 0.000002? with warmup or soemthing else worth to try. Thank you for your time guys

Trimac•3/8/23, 2:21 AM

im gonaa try 200 steps "epoch" but im unsure of the learning rates

P1pSl1p•3/8/23, 2:23 AM

https://www.youtube.com/watch?v=sRdtVanSRl4&t=662s

YouTubeSECourses - Software Engineering Courses

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...

P1pSl1p•3/8/23, 2:23 AM

start with the settings he uses in this video

P1pSl1p•3/8/23, 2:23 AM

gets good results

Trimac•3/8/23, 2:28 AM

okay then i have to watch 30mins video lol. thank you

P1pSl1p•3/8/23, 2:29 AM

Trained with 20 images and no filewords on Liberty model. very good results but not very flexible. going to work with filewords moving forward.

TTrimac okay then i have to watch 30mins video lol. thank you

P1pSl1p•3/8/23, 2:31 AM

use the settings from the first part of the video where he sets up test_0. it doesn't take much time..

PP1pSl1p Trained with 20 images and no filewords on Liberty model. very good results but ...

Trimac•3/8/23, 2:36 AM

looks consistent results, have tried some stylish prompts? maybe futuristic and let see how effective it is

Trimac•3/8/23, 2:37 AM

The question is what based ckpt will be use if we want stylish result

Trimac•3/8/23, 2:39 AM

Seacourses only used the 1.5 original and that model is old for me and not so impressive in creativity

TTrimac looks consistent results, have tried some stylish prompts? maybe futuristic and ...

P1pSl1p•3/8/23, 2:44 AM

The model isn't flexible at all. Most likely due to the lack of filewords

TTrimac Seacourses only used the 1.5 original and that model is old for me and not so im...

P1pSl1p•3/8/23, 2:46 AM

yeah, I originaly trained on 1.5 model. it was okay but flexible. but then I started experimenting with other models and got better results but they weren't as flexible.

P1pSl1p•3/8/23, 2:48 AM

2k photos should give solid results I imaging. lol

P1pSl1p•3/8/23, 2:48 AM

did you use filewords?

Steel•3/8/23, 2:48 AM

well if you watch videos they all talk about using few photos like 20 good once

Steel•3/8/23, 2:48 AM

yes. I fileword the clothing

Steel•3/8/23, 2:48 AM

and haircolor

Steel•3/8/23, 2:49 AM

this is also ai

P1pSl1p•3/8/23, 2:49 AM

that's my next step. up the dataset count and filewords meticulously

Steel•3/8/23, 2:50 AM

and this is a real photo of her

P1pSl1p•3/8/23, 2:50 AM

nice results

Steel•3/8/23, 2:51 AM

very.. I tell you if you use dreambooth and make normal models you are wasting time

Steel•3/8/23, 2:51 AM

kohya lora, only way to go

P1pSl1p•3/8/23, 2:51 AM

guess I have a mission for today

P1pSl1p•3/8/23, 2:51 AM

got any good resources to get started?

Steel•3/8/23, 2:51 AM

what do you mean by resources?

P1pSl1p•3/8/23, 2:52 AM

links to tutorials... etc.

Steel•3/8/23, 2:52 AM

oh and train with realistic vision

Steel•3/8/23, 2:52 AM

no, cause all tutorials do it wrong

P1pSl1p•3/8/23, 2:52 AM

lol

Steel•3/8/23, 2:52 AM

I tried folloing tutorials which gave me crap

Steel•3/8/23, 2:53 AM

dont listen, they only focus on either stylized photos of their own faces

Steel•3/8/23, 2:54 AM

512,512 is NOT a a good idea

running 3 pods for experiments

Similar Threads

Similar Threads

Similar Threads