Is there a size recommendation like 512x512 or distance from camera that is better? I used 5 pics a

M

mtnmeccaOP•5/9/23, 2:13 AM

I’ll comment on your latest high quality image video tomorrow but I wanted to tell you that I updated to newer versions of xformers, torch and others and my image generation quality (especially skin texture) went way up. I have both old and new versions installed so the comparison is really good. I didn’t know the quality could improve this much through updating SD component code. I have spent so much time trying to improve training but good of improvement was also achieved by newer code updates..

W

weilu•5/9/23, 5:19 AM

@Furkan Gözükara SECourses Do we need to use blip or tagger to label abstract styles when training with Dreambooth?

N

Neo•5/9/23, 6:57 AM

Hocam kolay gelsin

Müsait olduğunuz müddetçe burada kafanızı şişirmemiz mümkün mü?

T

TheWhykiki•5/9/23, 7:27 AM

My next test will be training on Icons, like Font Awesome and co.
Any suggestions how big the dataset should be and which model to use as a base?
My idea is to use the Colorbook Model from civitai - or some of the Logo Models.
The goal should be:
Use img2img and control net to generate new icons and then vectorize them with the vector extension....

M

MartaCalabuig•5/9/23, 7:28 AM

Hi everybody! Do you have any recommendation on which server i should choose if I'm not currently going to train the ai? I want to generate images and add extensions such as ControlNet. Will a 3080 work or is it too limited?

Mmtnmecca Is there a size recommendation like 512x512 or distance from camera that is bett...

F

Furkan Gözükara SECourses•5/9/23, 7:32 AM

512 is really small resolution if distant shot

T

TheWhykiki•5/9/23, 7:32 AM

For generating images it will work I think.

F

Furkan Gözükara SECourses•5/9/23, 7:32 AM

that is also why stable diffusion struggles

M

MartaCalabuig•5/9/23, 7:32 AM

Thanks!

TTheWhykiki My next test will be training on Icons, like Font Awesome and co. Any suggestion...

F

Furkan Gözükara SECourses•5/9/23, 7:32 AM

nice idea

T

TheWhykiki•5/9/23, 7:33 AM

@MartaCalabuig I use the Colabds and RunPods only for training. Generating images I'm doing on a 2080Ti on my Desktop

MMartaCalabuig Hi everybody! Do you have any recommendation on which server i should choose if ...

F

Furkan Gözükara SECourses•5/9/23, 7:33 AM

how much vram you have?

F

Furkan Gözükara SECourses•5/9/23, 7:33 AM

for image generation yes it will work great

FFurkan Gözükara SECourses how much vram you have?

M

MartaCalabuig•5/9/23, 7:41 AM

Only 4Gb

MMartaCalabuig Only 4Gb 🥲

F

Furkan Gözükara SECourses•5/9/23, 7:42 AM

with 4 gb you cant to any training but you can generate images

M

MartaCalabuig•5/9/23, 7:43 AM

I tried when 1.5 fist came out but it didn't work, maybe it will now. I'll try! Thanks!

MMartaCalabuig I tried when 1.5 fist came out but it didn't work, maybe it will now. I'll try! ...

F

Furkan Gözükara SECourses•5/9/23, 7:45 AM

it works i tested

F

Furkan Gözükara SECourses•5/9/23, 7:45 AM

use --medvram command line argument

F

Furkan Gözükara SECourses•5/9/23, 7:45 AM

if fails --lowvram

M

MartaCalabuig•5/9/23, 7:45 AM

Great! Thanks

Y

yellowgator_•5/9/23, 8:29 AM

@Furkan Gözükara SECourses Hey Prof ! I am building a side project(a web app), which essentially tries to replicate your work in the "Video to Anime" video.

As such, I would like to know if there's a way to use checkpoints and LoRA without the Automatic1111 UI i.e. I would like to essentially use a Python script that could load up a checkpoint/LoRA(downloaded from CIVIT AI and stored in Google Drive). Your help would be greatly appreciated!

Y

yellowgator_•5/9/23, 8:29 AM

Essentially, a way to modify this script to allow me to use LoRAs and Checkpoints downloaded from CiVIT AI.

Yyellowgator_@Furkan Gözükara SECourses Hey Prof ! I am building a side project(a web app), w...

F

Furkan Gözükara SECourses•5/9/23, 8:35 AM

you can use api of automatic1111 too

Yyellowgator_Essentially, a way to modify this script to allow me to use LoRAs and Checkpoint...

F

Furkan Gözükara SECourses•5/9/23, 8:35 AM

unfortunately i dont have much knowledge about this and this requires a lot of research to make it work

FFurkan Gözükara SECourses you can use api of automatic1111 too

Y

yellowgator_•5/9/23, 8:39 AM

I see, thank you Prof !

F

Furkan Gözükara SECourses•5/9/23, 8:50 AM

lol my cpu and gpu is being 100% used

F

Furkan Gözükara SECourses•5/9/23, 9:58 AM

guys what you think about this intro speech

Hello and welcome, one and all! Today, we are embarking on an exciting journey through the most intuitive and comprehensive deep voice cloning tutorial you will find anywhere. Our mission? To show you how to train your voice and generate hours of speech in just a single click.

This tutorial is built on open source projects, meaning it is entirely free and runs directly on your own computer. You may have heard of pricey services like Eleven Labs that offer voice training and speech synthesis. But why break the bank when you can achieve stunning results without any prior technical knowledge? That is right, all you need to do is follow along with me.

Interestingly, the voice you are hearing now is a deep clone! Drop a comment to let me know what you think, and who it reminds you of. We will switch to my natural voice after this introduction, so stay tuned!

Every step of this tutorial is meticulously detailed, both in this video and in the accompanying GitHub introduction file. This file is your one stop shop, packed with all the information you will need. You will find the link in the description and the pinned comment, so don't forget to check it out.

Are you wondering why this tutorial stands out from the rest? It is because, with a simple drag and drop, your speech file can be transformed into your complete training data. Thanks to our chosen user friendly graphical user interface, you can set up all training parameters and launch your training with just a single click. Once the training is complete, my specially developed scripts will enable you to convert an entire text file into speech, again, just by dragging and dropping. What is more, each step is clearly documented and demonstrated in this tutorial video, making it incredibly easy for you to follow along. This tutorial offers a seamless and convenient process unlike any other.

So, are you ready to jump into the world of voice cloning? Let's get started!

Hello and welcome, one and all! Today, we are embarking on an exciting journey through the most intuitive and comprehensive deep voice cloning tutorial you will find anywhere. Our mission? To show you how to train your voice and generate hours of speech in just a single click.

This tutorial is built on open source projects, meaning it is entirely free and runs directly on your own computer. You may have heard of pricey services like Eleven Labs that offer voice training and speech synthesis. But why break the bank when you can achieve stunning results without any prior technical knowledge? That is right, all you need to do is follow along with me.

Interestingly, the voice you are hearing now is a deep clone! Drop a comment to let me know what you think, and who it reminds you of. We will switch to my natural voice after this introduction, so stay tuned!

Every step of this tutorial is meticulously detailed, both in this video and in the accompanying GitHub introduction file. This file is your one stop shop, packed with all the information you will need. You will find the link in the description and the pinned comment, so don't forget to check it out.

Are you wondering why this tutorial stands out from the rest? It is because, with a simple drag and drop, your speech file can be transformed into your complete training data. Thanks to our chosen user friendly graphical user interface, you can set up all training parameters and launch your training with just a single click. Once the training is complete, my specially developed scripts will enable you to convert an entire text file into speech, again, just by dragging and dropping. What is more, each step is clearly documented and demonstrated in this tutorial video, making it incredibly easy for you to follow along. This tutorial offers a seamless and convenient process unlike any other.

So, are you ready to jump into the world of voice cloning? Let's get started!

Hello and welcome, one and all! Today, we are embarking on an exciting journey through the most intuitive and comprehensive deep voice cloning tutorial you will find anywhere. Our mission? To show you how to train your voice and generate hours of speech in just a single click.

This tutorial is built on open source projects, meaning it is entirely free and runs directly on your own computer. You may have heard of pricey services like Eleven Labs that offer voice training and speech synthesis. But why break the bank when you can achieve stunning results without any prior technical knowledge? That is right, all you need to do is follow along with me.

Interestingly, the voice you are hearing now is a deep clone! Drop a comment to let me know what you think, and who it reminds you of. We will switch to my natural voice after this introduction, so stay tuned!

Every step of this tutorial is meticulously detailed, both in this video and in the accompanying GitHub introduction file. This file is your one stop shop, packed with all the information you will need. You will find the link in the description and the pinned comment, so don't forget to check it out.

Are you wondering why this tutorial stands out from the rest? It is because, with a simple drag and drop, your speech file can be transformed into your complete training data. Thanks to our chosen user friendly graphical user interface, you can set up all training parameters and launch your training with just a single click. Once the training is complete, my specially developed scripts will enable you to convert an entire text file into speech, again, just by dragging and dropping. What is more, each step is clearly documented and demonstrated in this tutorial video, making it incredibly easy for you to follow along. This tutorial offers a seamless and convenient process unlike any other.

So, are you ready to jump into the world of voice cloning? Let's get started!

Hello and welcome, one and all! Today, we are embarking on an exciting journey through the most intuitive and comprehensive deep voice cloning tutorial you will find anywhere. Our mission? To show you how to train your voice and generate hours of speech in just a single click.

This tutorial is built on open source projects, meaning it is entirely free and runs directly on your own computer. You may have heard of pricey services like Eleven Labs that offer voice training and speech synthesis. But why break the bank when you can achieve stunning results without any prior technical knowledge? That is right, all you need to do is follow along with me.

Interestingly, the voice you are hearing now is a deep clone! Drop a comment to let me know what you think, and who it reminds you of. We will switch to my natural voice after this introduction, so stay tuned!

Every step of this tutorial is meticulously detailed, both in this video and in the accompanying GitHub introduction file. This file is your one stop shop, packed with all the information you will need. You will find the link in the description and the pinned comment, so don't forget to check it out.

Are you wondering why this tutorial stands out from the rest? It is because, with a simple drag and drop, your speech file can be transformed into your complete training data. Thanks to our chosen user friendly graphical user interface, you can set up all training parameters and launch your training with just a single click. Once the training is complete, my specially developed scripts will enable you to convert an entire text file into speech, again, just by dragging and dropping. What is more, each step is clearly documented and demonstrated in this tutorial video, making it incredibly easy for you to follow along. This tutorial offers a seamless and convenient process unlike any other.

So, are you ready to jump into the world of voice cloning? Let's get started!

FFurkan Gözükara SECourses guys what you think about this intro speech ```Hello and welcome, one and all! T...

D

Dagbarox•5/9/23, 11:16 AM

I think it sounds great. I cant wait for the video ^^

DDagbarox I think it sounds great. I cant wait for the video ^^

F

Furkan Gözükara SECourses•5/9/23, 11:24 AM

thank you. post processing

F

Furkan Gözükara SECourses•5/9/23, 11:25 AM

computer working 100% https://twitter.com/GozukaraFurkan/status/1655889216872513538

Furkan Gözükara (@GozukaraFurkan)

case is drawing 690 watt per hour :)

Twitter

•

5/9/23, 10:55 AM

F

Furkan Gözükara SECourses•5/9/23, 11:25 AM

you can follow my twitter too

A

Andrei•5/9/23, 11:43 AM

hi everyone, is it possible to use sd 1.5 and 2.1 if i install them in separated directories on my pc?

AAndrei hi everyone, is it possible to use sd 1.5 and 2.1 if i install them in separated...

F

Furkan Gözükara SECourses•5/9/23, 11:53 AM

100%

F

Furkan Gözükara SECourses•5/9/23, 11:53 AM

but why do you want seperate folders?

F

Furkan Gözükara SECourses•5/9/23, 11:54 AM

the loss graph of voice training. this is not very useful in stable diffusion since we dont have validation dataset in that one

W

Wolvenkoning•5/9/23, 11:55 AM

Hi there! I have a quick question. I'm tinkering with stable diffusion and dreambooth a lot lately. and was wondering if you can train a SD model with style and subjects in the google colab (or on Runpod)? so far I havent been able to get it to work... I tried training the subject and style simultaneously with 2 trigger words. but when I call them both out at the same time. I just get the person but not the style... is there any way to fix this? or do I need to run it on runpod or even localy?

WWolvenkoning Hi there! I have a quick question. I'm tinkering with stable diffusion and dream...

F

Furkan Gözükara SECourses•5/9/23, 11:57 AM

you dont need runpod

FFurkan Gözükara SECourses but why do you want seperate folders?

A

Andrei•5/9/23, 11:57 AM

how do i use 1.5 and 2.1 at same directory without causing any problems then?

F

Furkan Gözükara SECourses•5/9/23, 11:57 AM

by following these 2 tutorial you can do with automatic1111

AAndrei how do i use 1.5 and 2.1 at same directory without causing any problems then?

F

Furkan Gözükara SECourses•5/9/23, 11:57 AM

watch this video : https://youtu.be/aAyvsX-EpG4

YouTubeSECourses

How to use Stable Diffusion V2.1 and Different Models in the Web UI...

Our Discord : https://discord.gg/HbqgGaZVmr. How to use custom, different, .safetensors and SD 2.1 on Automatic1111 Web UI. 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 Go...

How to use Stable Diffusion V2.1 and Different Models in the Web UI...

F

Furkan Gözükara SECourses•5/9/23, 11:57 AM

and for style and person training this video

F

Furkan Gözükara SECourses•5/9/23, 11:58 AM

https://youtu.be/m-UVVY_syP0

YouTubeSECourses

Training Midjourney Level Style And Yourself Into The SD 1.5 Model ...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. 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 #StableDiffusion Tutorials, Au...