Software Engineering Courses (SECourses)•3y ago

Hey! So I got stable-Diffusion auto1111 running and the dreambooth extention installed both on my lo

Hey! So I got stable-Diffusion auto1111 running and the dreambooth extention installed both on my local and on runpod. However on the local machine I get the following message when trying to create a model

https://gdl.space/lajekudili.coffeescript

https://gdl.space/lajekudili.coffeescript

Any help would be amazing. I am also following the zero the hero tutorial

GGarreth210 Hey! So I got stable-Diffusion auto1111 running and the dreambooth extention ins...

Furkan Gözükara SECourses•3/20/23, 12:20 PM

what is the message?

Furkan Gözükara SECourses•3/20/23, 12:20 PM

if you dont have at least 12 gb vram add this to command line arguments

Furkan Gözükara SECourses•3/20/23, 12:20 PM

--ckptfix

Garreth210OP•3/20/23, 12:22 PM

let me give that a try

FFurkan Gözükara SECourses what is the message?

Garreth210OP•3/20/23, 12:28 PM

Success

Loading model from checkpoint.
Loading ckpt...
Pred and size are epsilon and 512, using config: C:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\..\configs\v1-training-default.yaml
v1 model loaded.
Trying to load: C:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\..\configs\v1-training-default.yaml
Converting unet...
Converting vae...
Converting text encoder...
Saving text_encoder
Saving tokenizer
Checkpoint successfully extracted to C:\stable-diffusion-webui\models\dreambooth\GarrethD_VamphuntD-model\working
Restored system models.
Duration: 00:00:23
Model dir set to: C:\stable-diffusion-webui\models\dreambooth\GarrethD_VamphuntD-model
Using CPU for extraction.
Loading model from checkpoint.
Loading ckpt...

Loading model from checkpoint.
Loading ckpt...
Pred and size are epsilon and 512, using config: C:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\..\configs\v1-training-default.yaml
v1 model loaded.
Trying to load: C:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\..\configs\v1-training-default.yaml
Converting unet...
Converting vae...
Converting text encoder...
Saving text_encoder
Saving tokenizer
Checkpoint successfully extracted to C:\stable-diffusion-webui\models\dreambooth\GarrethD_VamphuntD-model\working
Restored system models.
Duration: 00:00:23
Model dir set to: C:\stable-diffusion-webui\models\dreambooth\GarrethD_VamphuntD-model
Using CPU for extraction.
Loading model from checkpoint.
Loading ckpt...

Zono50•3/20/23, 12:30 PM

i'm a generate 2400 images of woman, then set my num class instances of image to 50 and see how that does me

Garreth210OP•3/20/23, 12:39 PM

I just want to understand that, I am running a 3070Ti and I have dreambooth running now after adding the --ckptfix arag. Do I continue as normal or Do I need to enable Lora?

Zono50•3/20/23, 12:44 PM

What is the relationship between classification dataset directory and Class images per instance image

Furkan Gözükara SECourses•3/20/23, 12:45 PM

which one is best to use in thumbnail

GGarreth210 I just want to understand that, I am running a 3070Ti and I have dreambooth runn...

Furkan Gözükara SECourses•3/20/23, 12:46 PM

continue as normal after that. that is for generate training model

FFurkan Gözükara SECourses continue as normal after that. that is for generate training model

Garreth210OP•3/20/23, 12:46 PM

perfect.

FFurkan Gözükara SECourses which one is best to use in thumbnail

Garreth210OP•3/20/23, 12:47 PM

Second row third column

Garreth210OP•3/20/23, 12:48 PM

I can use the regularization images you have supplied here right ?

GGarreth210 I can use the regularization images you have supplied here right ?

Furkan Gözükara SECourses•3/20/23, 12:48 PM

yes

Furkan Gözükara SECourses•3/20/23, 12:48 PM

use same class prompt

Garreth210OP•3/20/23, 12:49 PM

I don't quite understand the filewords like instance token or class token or instance prompt or class prompts. I will continue watching but evaerything up until this point has been fairly straight forward

Jan•3/20/23, 12:51 PM

This is a wiki guid but I do not understand it either hope it helps you: https://github.com/d8ahazard/sd_dreambooth_extension/wiki/Class-Explained

GitHub

Class Explained

Contribute to d8ahazard/sd_dreambooth_extension development by creating an account on GitHub.

GGarreth210 I don't quite understand the filewords like instance token or class token or ins...

Furkan Gözükara SECourses•3/20/23, 12:51 PM

explained in this video

Furkan Gözükara SECourses•3/20/23, 12:51 PM

wait it

Garreth210OP•3/20/23, 12:53 PM

Ya, I get the idea around concepts but what throws me off is that I have no idea what fileworlds, traning prompts and sample prompts do . I will continue with the video but it's not the 1st time watching. I feel it's a difficult concept to grasp

Jan•3/20/23, 12:55 PM

which video exactly, then I would also look at it maybe we can understand it together

Garreth210OP•3/20/23, 12:56 PM

https://www.youtube.com/watch?v=Bdl-jWR3Ukc

YouTubeSECourses - Software Engineering Courses

Zero To Hero Stable Diffusion DreamBooth Tutorial By Using Automati...

Our Discord : https://discord.gg/HbqgGaZVmr. The most advanced tutorial of Stable Diffusion Dreambooth Training. 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 Google Colab ...

Garreth210OP•3/20/23, 12:56 PM

So I am currently adding the filewords

Furkan Gözükara SECourses•3/20/23, 12:57 PM

Yes that one is really comprehensive

Garreth210OP•3/20/23, 12:57 PM

Furkan Gözükara SECourses•3/20/23, 12:57 PM

I don't put them in filewords tab

Furkan Gözükara SECourses•3/20/23, 12:57 PM

Using in training prompts better

Furkan Gözükara SECourses•3/20/23, 12:57 PM

Easier to understand also

Furkan Gözükara SECourses•3/20/23, 12:57 PM

Explained in New video hopefully will be published in 1 hour

FFurkan Gözükara SECourses I don't put them in filewords tab

Garreth210OP•3/20/23, 12:58 PM

I look forward to it

Arshy•3/20/23, 12:59 PM

Hello everyone! glad to find this treasure trove. Was wondering if there are any resources to learn dreambooth for objects such as a lamp? Thanks in advance.

FFurkan Gözükara SECourses Yes that one is really comprehensive

Jan•3/20/23, 12:59 PM

I must confess it was a bit too fast for me.
I will have to make a kind of pre flight checklist so that I can use at first because it is so much at once.

AArshy Hello everyone! glad to find this treasure trove. Was wondering if there are any...

Jan•3/20/23, 1:05 PM

I don't know anything about this, but I have seen that in dreambooth there is "Traing Wizard (Object/Style)" under Concepts:

JJan I don't know anything about this, but I have seen that in dreambooth there is "T...

Arshy•3/20/23, 1:06 PM

appreciate thanks a lot. will try it out n report

AArshy appreciate thanks a lot. will try it out n report

Jan•3/20/23, 1:07 PM

If you understand Classen and Filwords you are welcome to return the favor.

JJan If you understand Classen and Filwords you are welcome to return the favor. 😄

Garreth210OP•3/20/23, 1:10 PM

stuck on this as well XD

JJan If you understand Classen and Filwords you are welcome to return the favor. 😄

Arshy•3/20/23, 1:11 PM

Sure thing

Trimac•3/20/23, 1:14 PM

Hey guys. I just ran a two gpu in one system unit for Sd rendering or training. I was wondering how did Colab ran multiple gpus? I cant still figure it out on local sd. Anyone doing like what im doing here?

TTrimac Hey guys. I just ran a two gpu in one system unit for Sd rendering or training. ...

Jan•3/20/23, 1:19 PM

Out of interest, are these two systems or one PC with two graphics? Vertical / Horizontal upgrade?

AArshy Sure thing 😂

Jan•3/20/23, 1:25 PM

@Arshy
@Garreth210
Would you have time and interest that we sit together tonight, research and exchange information. (Voice)
Maybe we can help each other.

Garreth210OP•3/20/23, 1:25 PM

Sure, I don't mind

Garreth210OP•3/20/23, 1:25 PM

This is my current setup

Garreth210OP•3/20/23, 1:26 PM

Garreth210OP•3/20/23, 1:26 PM

I am just trying things at this point

JJan @Arshy @Garreth210 Would you have time and interest that we sit together tonig...

Arshy•3/20/23, 1:27 PM

I’m GMT+5.5. Not sure if that works for u guys. Also later in the week would be better for me. But I had be interested

Garreth210OP•3/20/23, 1:29 PM

@Furkan Gözükara SECourses Question:
If I use the reference images you have supplied on gDrive, Do I still need to set the class image generation ?

Garreth210OP•3/20/23, 1:29 PM

GGarreth210 @Furkan Gözükara SECourses Question: If I use the reference images you have sup...

Jan•3/20/23, 1:32 PM

As far as I understand, no, if you start from the standard model and have a similar training targets. Otherwise it is recommended. (I think the reference images should correspond to the trainigs gole.

Garreth210OP•3/20/23, 1:32 PM

okay

Loading model from checkpoint. Loading ckpt... Pred and size are epsilon and 512, using config: C:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\..\configs\v1-training-default.yaml v1 model loaded. Trying to load: C:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\..\configs\v1-training-default.yaml Converting unet... Converting vae... Converting text encoder... Saving text_encoder Saving tokenizer Checkpoint successfully extracted to C:\stable-diffusion-webui\models\dreambooth\GarrethD_VamphuntD-model\working Restored system models. Duration: 00:00:23 Model dir set to: C:\stable-diffusion-webui\models\dreambooth\GarrethD_VamphuntD-model Using CPU for extraction. Loading model from checkpoint. Loading ckpt...

Hey! So I got stable-Diffusion auto1111 running and the dreambooth extention installed both on my lo

Similar Threads

Similar Threads

Similar Threads