Software Engineering Courses (SECourses)•3y ago

also this video : https://youtu.be/kvxX6NrPtEk

Double Your Stable Diffusion Inference Speed with RTX Acceleration ...

Stable Diffusion Gets A Major Boost With RTX Acceleration. One of the most common ways to use Stable Diffusion, the popular Generative AI tool that allows users to produce images from simple text descriptions, is through the Stable Diffusion Web UI by Automatic1111. In today’s Game Ready Driver, NVIDIA added TensorRT acceleration for Stable Diff...

Furkan Gözükara SECoursesOP•12/11/23, 12:54 AM

you have 3 space letters having folders

Furkan Gözükara SECoursesOP•12/11/23, 12:54 AM

big no no

Furkan Gözükara SECoursesOP•12/11/23, 12:59 AM

also your cmd doesn't give any info about the error

soymarcelojs•12/11/23, 12:59 AM

thanks!

soymarcelojs•12/11/23, 12:59 AM

ill see that now!

Digital [Starburst]•12/11/23, 1:02 AM

The RunPod setup tutorial is a bit outdated because they have updated the platform. You no longer have a choice between Stable-Diffusion-1.5 and Stable-Diffusion-2.1. You now must choose between Fast-Stable-Diffusion, ComfyUI-Stable-Diffusion, Stable-Diffusion-webui, and I think there's one other option. Under the Community options the A5000 is still an option. There is one other option for the same price that has more CPU RAM, but I don't know if you want that one.

soymarcelojs•12/11/23, 1:16 AM

I thank you, but I'm not there yet. I'm trying to get stability to run SDWebUI. Do you suggest I watch that class? because I was stuck in the second one even for this issue

FFurkan Gözükara SECourses also this video : https://youtu.be/kvxX6NrPtEk

Lorelai AI•12/11/23, 1:21 AM

Can the TensorRT do images above 1024X1024? I need images by 768x1344 and I don't think I could get it to work when I used to use it because sizes are capped?

Pelolisu•12/11/23, 1:30 AM

@Dr. Furkan Gözükara have you managed to get Drembooth to work locally with DeepSpeed? If so, have you had good results with that?

Jehex•12/11/23, 2:10 AM

Hi, again an error of path right ?

Hustle with AI•12/11/23, 4:22 AM

Hello, very new to SD. I have installed Dreambooth extension in web UI using auto installer scripts on Runpod. I am trying to create what's shown in Corridor Digital crew video.

Any help to use Dreambooth like they did in using 4 datasets to train a model?

Dataset1: Niko - The main subject (a real man's images for training data set)
Dataset2: Ghibli Animation characters - images to train the main subject on
Dataset3: General images of man (reg images)
Dataset4: General images of art style (reg images)

Benjamin•12/11/23, 10:26 AM

@FiveSAI sorry if I missed it, but did you already share your training parameters for sdxl dreambooth?

interested in trying them out

Ssoymarcelojs I thank you, but I'm not there yet. I'm trying to get stability to run SDWebUI. ...

Furkan Gözükara SECoursesOP•12/11/23, 3:01 PM

i got up to date tutorials and install scripts

Furkan Gözükara SECoursesOP•12/11/23, 3:01 PM

what you need

LLorelai AI Can the TensorRT do images above 1024X1024? I need images by 768x1344 and I don'...

Furkan Gözükara SECoursesOP•12/11/23, 3:01 PM

yes it can do

Furkan Gözükara SECoursesOP•12/11/23, 3:01 PM

you need to modify 1 file though

Furkan Gözükara SECoursesOP•12/11/23, 3:02 PM

https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT/issues/199

GitHub

Maximum resolution is limited to 1024 but sliders goes up to 2048 h...

I had to modify this code to generate TensorRT that will support highres fix for SDXL self.max_image_shape = 768 if version in ("1.4", "1.5") else 2048 It is by default 1024 So ...

Furkan Gözükara SECoursesOP•12/11/23, 3:02 PM

self.max_image_shape = 768 if version in ("1.4", "1.5") else 2048

PPelolisu @Dr. Furkan Gözükara have you managed to get Drembooth to work locally with Deep...

Furkan Gözükara SECoursesOP•12/11/23, 3:02 PM

,i am using Kohya. waiting Triton package to be available on Windows

Furkan Gözükara SECoursesOP•12/11/23, 3:02 PM

almost there

JJehex Hi, again an error of path right ?

Furkan Gözükara SECoursesOP•12/11/23, 3:03 PM

doesnt show error

Furkan Gözükara SECoursesOP•12/11/23, 3:03 PM

show full error

HHustle with AI Hello, very new to SD. I have installed Dreambooth extension in web UI using aut...

Furkan Gözükara SECoursesOP•12/11/23, 3:03 PM

hello welcome

Furkan Gözükara SECoursesOP•12/11/23, 3:03 PM

i have 2 tutorials that shows their approach

Furkan Gözükara SECoursesOP•12/11/23, 3:03 PM

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...

Furkan Gözükara SECoursesOP•12/11/23, 3:03 PM

https://youtu.be/kmT-z2lqEPQ

YouTubeSECourses

Video To Anime - Generate An EPIC Animation From Your Phone Recordi...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Turn your real video into an animation with just 1 click by using Stable Diffusion for free. 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 Sta...

FFurkan Gözükara SECourses ,i am using Kohya. waiting Triton package to be available on Windows

Pelolisu•12/11/23, 3:04 PM

humm have you ever run Koyah in WSL2?

PPelolisu humm have you ever run Koyah in WSL2?

Furkan Gözükara SECoursesOP•12/11/23, 3:05 PM

nope

Pelolisu•12/11/23, 3:05 PM

Today I'm going to try to install it according to your video, I'm going to try in wsl2.

Pelolisu•12/11/23, 3:06 PM

I managed to make the latest version of the A1111 dreambooth work in wsl2 but it seems that this koyah must be better.

Pelolisu•12/11/23, 3:06 PM

*Kohya

FFurkan Gözükara SECourses https://youtu.be/kmT-z2lqEPQ

Hustle with AI•12/11/23, 3:12 PM

wow thanks for sharing!

FFurkan Gözükara SECourses i got up to date tutorials and install scripts

soymarcelojs•12/11/23, 3:14 PM

thanks i solve it i think XD i can run A1111 whit normaly! thanks you very much!

Pelolisu•12/11/23, 4:50 PM

@Dr. Furkan Gözükara Do you know if there is any known issue with Torch 2.1.0? I always see the dependencies pointing to 2.0.1. I did a test with 2.1.0 on my dreambooth 2.1.0 and noticed that it performed faster.

PPelolisu @Dr. Furkan Gözükara Do you know if there is any known issue with Torch 2.1.0? ...

mtnmecca•12/11/23, 5:43 PM

also interested in this topic since I tried an update from torch 2.0.1 to 2.1.1 with xformers 0.23 and couldn't get it to work. Always trying to figure out which dependencies are needed.

Mmtnmecca also interested in this topic since I tried an update from torch 2.0.1 to 2.1.1 ...

Pelolisu•12/11/23, 5:54 PM

in A1111 i have this setup

Pelolisu•12/11/23, 5:55 PM

what changes in xformers 0.23?

mtnmecca•12/11/23, 5:57 PM

didn't research changes - just that it was a newly released version and @Dr. Furkan Gözükara recently tested it in latest patreon

Pelolisu•12/11/23, 5:59 PM

Well, I'm going to test Kohya with its default configuration, after I get good results I'll do the experiment and try to update the dependencies to the most recent ones.

Elisoli•12/11/23, 6:08 PM

Dr, you think we can train this new realistic SDXL model (https://civitai.com/models/152525) with your config files as base? the model contains VAE baked inside already

Realism Engine SDXL - v2.0 VAE | Stable Diffusion Checkpoint | Civitai

Introducing Version 2.0 of the Realism Engine We are excited to announce that Version 2.0 of the Realism Engine is now available, featuring signifi...

Pelolisu•12/11/23, 6:23 PM

@Dr. Furkan Gözükara when you say that not using xformers with 24gb is better than using xformers with 16gb, does it mean that it only changes the quality of image rendering or affects the quality of training the face correctly?

PPelolisu in A1111 i have this setup