Software Engineering Courses (SECourses)•3y ago

Is there some bug in A1111 dreambooth training where the checkpoints it generates just ignore all th

Is there some bug in A1111 dreambooth training where the checkpoints it generates just ignore all the training? it generates samples fine but then try to use the checkpoint to generate images and the model you generate works but just ignores all the training instance tokens completely

FabricatedgirlsOP•3/22/23, 5:44 AM

or resuming training is broken or something, not sure wth is going on

FFORTUNE VARO It´s so frustrating! Spent days trying for a model to work and to understand the...

FORTUNE VARO•3/22/23, 5:45 AM

yes

FORTUNE VARO•3/22/23, 5:51 AM

I read somewhere that the latest Dreambooth is just broken, no matter what you do, what parameters you adjust the results would be nightmarish
It´s so frustrating! Spent days trying for a model to work and to understand the app but the results are always garbage after hours of waiting

FFORTUNE VARO I read somewhere that the latest Dreambooth is just broken, no matter what you d...

FabricatedgirlsOP•3/22/23, 5:51 AM

how do you mean garbage?

FORTUNE VARO•3/22/23, 5:52 AM

distorted nightmarish

FabricatedgirlsOP•3/22/23, 5:53 AM

thats not exactly the issue i'm facing, it is training, its generating good samples, but when i try to use the checkpoints in SD to generate images, it ignores the training and just treats it like its the underlying model with no training at all.

FabricatedgirlsOP•3/22/23, 5:53 AM

its not doing a crappy warped version of what i ask it to do, its just ignoring the training altogether

EssaBalls•3/22/23, 7:41 AM

I got error like this while training hypernetwork:
"A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check."
I tried to add --no-half or set the "Upcast cross attention layer to float32" but it wont help. Wheni used --disable-nan-check then error disappeard BUT my samples are all black.

FFORTUNE VARO Hi! I´m learning how to train models following this tutorials. I´m training my f...

Furkan Gözükara SECourses•3/22/23, 7:48 AM

hi welcome

FFabricatedgirls Is there some bug in A1111 dreambooth training where the checkpoints it generate...

Furkan Gözükara SECourses•3/22/23, 7:49 AM

i did a new train yesterday it worked for me. i didnt generate any previews later did x/y/z

Furkan Gözükara SECourses•3/22/23, 7:49 AM

latest dreambooth working. i just did train yesterday

EEssaBalls I got error like this while training hypernetwork: "A tensor with all NaNs was p...

Furkan Gözükara SECourses•3/22/23, 7:49 AM

what model you are training sd 2.1?

EssaBalls•3/22/23, 7:49 AM

yes

EEssaBalls yes

Furkan Gözükara SECourses•3/22/23, 7:51 AM

you need to add --no-half

Furkan Gözükara SECourses•3/22/23, 7:51 AM

that requires more vram

EssaBalls•3/22/23, 7:52 AM

Yes i know

I then I have error that I dont have vram

I thought maybe I can resolve this in another way

EssaBalls•3/22/23, 7:53 AM

1.5 requires less vram?

EEssaBalls 1.5 requires less vram?

Furkan Gözükara SECourses•3/22/23, 7:53 AM

yes 1.5 much lesser vram

Furkan Gözükara SECourses•3/22/23, 7:53 AM

for example i cant do dreambooth on sd 2.1

Furkan Gözükara SECourses•3/22/23, 7:53 AM

even on 512 px

EssaBalls•3/22/23, 7:59 AM

I thought maybe it is because I resized the images from 768 to 512 using tool in automatic1111 and it somehow broke the images but i doubt that is the issue. Ok, I will try 1.5 then, thanks

Trimac•3/22/23, 8:04 AM

Hello Sd trainiacs. Can somebody share the command line to reset sd repo?

EEssaBalls I thought maybe it is because I resized the images from 768 to 512 using tool in...

Furkan Gözükara SECourses•3/22/23, 8:14 AM

which version of sd 2.1 you are using 512 or 768

TTrimac Hello Sd trainiacs. Can somebody share the command line to reset sd repo?

Furkan Gözükara SECourses•3/22/23, 8:14 AM

what you mean by reset?

Furkan Gözükara SECourses•3/22/23, 8:14 AM

you can do git pull

FFurkan Gözükara SECourses which version of sd 2.1 you are using 512 or 768

EssaBalls•3/22/23, 8:15 AM

768

FFurkan Gözükara SECourses what you mean by reset?

Trimac•3/22/23, 8:16 AM

i got this error Dr. No python found at my directory after i made a dualbooth Os

Trimac•3/22/23, 8:16 AM

No matter how path the python it wont start

Trimac•3/22/23, 8:17 AM

So maybe hard reset on repositories will help me

Trimac•3/22/23, 8:17 AM

To Default sertings

EEssaBalls 768

Furkan Gözükara SECourses•3/22/23, 8:30 AM

You have to use 768 training images

TTrimac i got this error Dr. No python found at my directory after i made a dualbooth Os

Furkan Gözükara SECourses•3/22/23, 8:30 AM

You need to set environment variable

Furkan Gözükara SECourses•3/22/23, 8:31 AM

I explained in this video you watched it?

Furkan Gözükara SECourses•3/22/23, 8:31 AM

https://youtu.be/AZg6vzWHOTA

YouTubeSECourses - Software Engineering Courses

Easiest Way to Install & Run Stable Diffusion Web UI on PC by Using...

Our Discord : https://discord.gg/HbqgGaZVmr. How to download and install Stable Diffusion Automatic1111 Web UI interface. 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 Stable Diffusion Tutorials, Automatic1111 and Goog...

n8hawk_•3/22/23, 8:32 AM

@Furkan Gözükara SECourses as I know you have the same grafikcard- a 3060 12gb. I updaed xformers and facing now the problem that everything seems to work until the generation prozess of images just freezes with no error. any ide what the reason is and/or what to do?

Nn8hawk_@Furkan Gözükara SECourses as I know you have the same grafikcard- a 3060 12gb. ...

Furkan Gözükara SECourses•3/22/23, 8:34 AM

What version you are using

n8hawk_•3/22/23, 8:34 AM

python: 3.10.6 • torch: 2.0.0+cu118 • xformers: 0.0.17+b6be33a.d20230315

Nn8hawk_python: 3.10.6 • torch: 2.0.0+cu118 • xformers: 0.0.17+b6be33a.d20230315

Furkan Gözükara SECourses•3/22/23, 8:35 AM

Does it work when use older version?

Furkan Gözükara SECourses•3/22/23, 8:35 AM

Or did you try without sample image generation during training

n8hawk_•3/22/23, 8:36 AM

let me say it like this: it worked perfect unteil I started updating xformers