Software Engineering Courses (SECourses)•3y ago

ive been doing stuff where i start with my photography as img2img and just get lost in layers of con

ive been doing stuff where i start with my photography as img2img and just get lost in layers of control nets using variations of photos and img2img and just lose track of what even goes in to an image so many different steps were taken

dave5555OP•3/7/23, 11:28 PM

style transfer looks like a cool way to make use of everything youve done in past to influence stuff in future

Thermidor•3/7/23, 11:31 PM

Is anyone having CUDA problems on runpod? I noticed Dr. Gozukara's pod template version in the tutorial videos is web-automatic-1.5.15 but now pods only display the new version web-automatic-2.1.18

Thermidor•3/7/23, 11:32 PM

The latest tutorial isn't working on these, I think

Thermidor•3/7/23, 11:38 PM

Freshly updated actually, just a heads up

Thermidor•3/7/23, 11:51 PM

OK, got it working now with the latest of Dr. Gozukara's tutorials. It's pretty straightforward actually, just create a new runpod template as follows:

TThermidor OK, got it working now with the latest of Dr. Gozukara's tutorials. It's pretty ...

Furkan Gözükara SECourses•3/7/23, 11:51 PM

awesome

Furkan Gözükara SECourses•3/7/23, 11:51 PM

i also updated the gist file accordingly to new template

Furkan Gözükara SECourses•3/7/23, 11:51 PM

https://gist.github.com/FurkanGozukara/ad1aa55e64576d49f829450278a15885

Thermidor•3/7/23, 11:52 PM

In case anyone's interested, simply create a template with the following text:

Thermidor•3/7/23, 11:52 PM

FFurkan Gözükara SECourses i also updated the gist file accordingly to new template

Thermidor•3/7/23, 11:53 PM

Also, great! Thank you so much for all the help

TThermidor Click to see attachment

Furkan Gözükara SECourses•3/7/23, 11:54 PM

wow very good tips

Ddave5555 ive been doing stuff where i start with my photography as img2img and just get l...

Haashim•3/8/23, 12:11 AM

Wow, that’s exactly what I’m doing now.
I use 2.1 so I just got controlnet working yesterday.
I use it to change fashions in photos and now I am changing the backgrounds.

dave5555OP•3/8/23, 12:12 AM

controlnet works on 2.1 now?

Haashim•3/8/23, 12:12 AM

I must say I preferred the img2img outputs without controlnet more. But maybe I need to learn more controlnet settings

Ddave5555 controlnet works on 2.1 now?

Haashim•3/8/23, 12:13 AM

A community member made a version and released yesterday.

dave5555OP•3/8/23, 12:13 AM

img2img is so good as it is

HHaashim A community member made a version and released yesterday.

dave5555OP•3/8/23, 12:14 AM

a controlnet extension or is it just a model

dave5555OP•3/8/23, 12:16 AM

after running img2img and getting an img u like , try rerolling it same settings but with depth model controlnet but empty image so it just uses img2img init

dave5555OP•3/8/23, 12:17 AM

u can get more detail but keep the composition

Ddave5555 a controlnet extension or is it just a model

Haashim•3/8/23, 12:18 AM

Sent to you on DM. There’s two versions.

Ones a canny model and the other has a few models but I haven’t tried.

Definitely will try that trick thanks

Haashim•3/8/23, 12:19 AM

Hopefully they continue to develop. I find 2.1 very good for photo realism.

We lucky someone took the time to make that

TThermidor Click to see attachment

Haashim•3/8/23, 12:24 AM

Thank you, I havent tried the new pod yet

HHaashim Thank you, I havent tried the new pod yet

Furkan Gözükara SECourses•3/8/23, 12:28 AM

it is same actually

Furkan Gözükara SECourses•3/8/23, 12:28 AM

very minor changes

Ddave5555 after running img2img and getting an img u like , try rerolling it same settings...

Haashim•3/8/23, 12:41 AM

This is a great tip.. changes details dramatically

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

running 3 pods for experiments

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

ye they consume a lot

Furkan Gözükara SECourses•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

dave5555OP•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

dave5555OP•3/8/23, 1:32 AM

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

dave5555OP•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...

dave5555OP•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.

ive been doing stuff where i start with my photography as img2img and just get lost in layers of con

Similar Threads