Software Engineering Courses (SECourses)•3y ago

Hello Furkan, I keep getting broken images with artifacts. Pls refer me to a tutorial where you expl

Hello Furkan, I keep getting broken images with artifacts. Pls refer me to a tutorial where you explain how to solve such mismatch of VAE or resolution. Thank you.

nissanleOP•12/12/23, 4:22 PM

I reinstalled everything from scratch, python, git and stable diffusion 1111, but still getting the same corrupted images.

FFurkan Gözükara SECourses looks like VAE or resolution mismatch

nissanleOP•12/12/23, 4:43 PM

here is an example

PPelolisu open your path C:\Users\datin\Desktop\New Folder\stable-diffusion-webui\venv\bin

Lorelai AI•12/12/23, 5:04 PM

I think I have it working but what’s the hack to get 768x1344 and 1344x768

PPelolisu @Dr. Furkan Gözükara can you help with one tip

Furkan Gözükara SECourses•12/12/23, 6:33 PM

my new strategy is

Furkan Gözükara SECourses•12/12/23, 6:33 PM

200 repeat

Furkan Gözükara SECourses•12/12/23, 6:33 PM

1 epoch

Furkan Gözükara SECourses•12/12/23, 6:34 PM

getting checkpoints based on n steps

LLorelai AI I did a new install to setup tensorrt of automatic1111 using your installer and ...

Furkan Gözükara SECourses•12/12/23, 6:34 PM

yes you will get them

Furkan Gözükara SECourses•12/12/23, 6:34 PM

those are not problem

Sstrakovic Hi guys, I'm creating a character of a hero for series and want to train sdxl fo...

Furkan Gözükara SECourses•12/12/23, 6:34 PM

probably several different trainings and find best workingone

Nnissanle Hello Furkan, What is the best python version today for Stable Diffusion AUTOMAT...

Furkan Gözükara SECourses•12/12/23, 6:35 PM

3.10.11 is best i think

Furkan Gözükara SECourses•12/12/23, 6:35 PM

most widely supported

HHustle with AI I keep getting this error whenever I restart runpod & start Stable Diffusion: E...

Furkan Gözükara SECourses•12/12/23, 6:35 PM

try delete venv and start again

NNeuromasters Thank you all for your help! Especially @Dr. Furkan Gözükara Now we're gonna do...

Furkan Gözükara SECourses•12/12/23, 6:35 PM

amazing

Nnissanle Hello Furkan, I keep getting broken images with artifacts. Pls refer me to a tut...

Furkan Gözükara SECourses•12/12/23, 6:35 PM

https://youtu.be/sBFGitIvD2A

YouTubeSECourses

Become A Master Of SDXL Training With Kohya SS LoRAs - Combine Powe...

In this tutorial, you will learn how to install Automatic1111 Web UI for SDXL. How to use LoRAs with Automatic1111 SD Web UI. How to install Kohya SS GUI scripts to do Stable Diffusion training. How to train LoRAs on SDXL model with least amount of VRAM using settings. All of the details, tips and tricks of Kohya trainings. How to do x/y/z plot ...

Furkan Gözükara SECourses•12/12/23, 6:35 PM

watch begining 20 min or so

FFurkan Gözükara SECourses yes you will get them

Lorelai AI•12/12/23, 6:43 PM

yeah but how do you configure a tensor engine for 768x1344 and 1344x768?

Lorelai AI•12/12/23, 6:44 PM

I may have found it actually

LLorelai AI yeah but how do you configure a tensor engine for 768x1344 and 1344x768?

Furkan Gözükara SECourses•12/12/23, 6:44 PM

you can so easy

Furkan Gözükara SECourses•12/12/23, 6:45 PM

i have sohwn in video

FFurkan Gözükara SECourses you can so easy

Lorelai AI•12/12/23, 6:45 PM

I may have it

FFurkan Gözükara SECourses you can so easy

Lorelai AI•12/12/23, 6:54 PM

I can generate standard sizes but when I change the sliders based in your video to non-standard I get this

LLorelai AI I can generate standard sizes but when I change the sliders based in your video ...

Furkan Gözükara SECourses•12/12/23, 7:06 PM

yes you need multipler of 64

Furkan Gözükara SECourses•12/12/23, 7:06 PM

that is limitation

Furkan Gözükara SECourses•12/12/23, 7:06 PM

also you need to increase max allowed size

Furkan Gözükara SECourses•12/12/23, 7:07 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 ...

FFurkan Gözükara SECourses yes you need multipler of 64

Lorelai AI•12/12/23, 7:08 PM

I tried both but my regular sizes engines are getting errors as well so it's something else. My venv is Python 3.10.6 do I need to update?

FFurkan Gözükara SECourses that is limitation

Pelolisu•12/12/23, 7:10 PM

I'm horrified seeing the quality of A1111's python code and its extensions, even more so because I come from the .NET world haha

LLorelai AI I tried both but my regular sizes engines are getting errors as well so it's som...

Furkan Gözükara SECourses•12/12/23, 7:10 PM

no i just gave you answer

Pelolisu•12/12/23, 7:11 PM

This seems like a lawless land

PPelolisu This seems like a lawless land

Lorelai AI•12/12/23, 7:14 PM

I don't care how broken it is if it does what I need. I give up on TensorRT I'll come back when the option is less broken

Lorelai AI•12/12/23, 7:16 PM

I spend more time fixing and trying to install broken TensorRT than the time I'd save generating images

Lorelai AI•12/12/23, 7:17 PM

I should just pay someone with a working venv and TensorRT to send it

LLorelai AI I should just pay someone with a working venv and TensorRT to send it 😵‍💫

Furkan Gözükara SECourses•12/12/23, 7:18 PM

i can instlal for you

Furkan Gözükara SECourses•12/12/23, 7:18 PM

what is your current level?

Furkan Gözükara SECourses•12/12/23, 7:18 PM

patreon level

Lorelai AI•12/12/23, 7:20 PM

It's entry but I will upgrade if you can get me a manageble and Stable Tensor RT build that can generate 768x1344 and 1344x768. The sizes are critical.

LLorelai AI It's entry but I will upgrade if you can get me a manageble and Stable Tensor RT...

Furkan Gözükara SECourses•12/12/23, 7:23 PM

please upgrade gold i will connect your pc

Furkan Gözükara SECourses•12/12/23, 7:23 PM

do it and explain you logic

LLorelai AI It's entry but I will upgrade if you can get me a manageble and Stable Tensor RT...

Furkan Gözükara SECourses•12/12/23, 7:26 PM

please open anydesk

Furkan Gözükara SECourses•12/12/23, 7:26 PM

message me

Furkan Gözükara SECourses•12/12/23, 7:26 PM

shortdwarf•12/12/23, 8:30 PM

Does anyone have thoughts on how I can train my personal LoRA to not include the background? I know part of this is using an earlier epoch, however before/during the training process is there anything I can do to really ensure it only trains the person?

Sshortdwarf Does anyone have thoughts on how I can train my personal LoRA to not include the...

strakovic•12/12/23, 8:34 PM

Remove background

shortdwarf•12/12/23, 8:35 PM

I considered swapping with plain color backgrounds (ex. one red, one blue, etc) or would white be best?

Sshortdwarf I considered swapping with plain color backgrounds (ex. one red, one blue, etc) ...

strakovic•12/12/23, 8:36 PM

Personally don’t see a benefit using other than white

shortdwarf•12/12/23, 8:37 PM

great, i only hestitated doing this because I thought it might lead to a strong constrast between subject and background but ill give it a shot. is there a program youd recommend using to swap in the white background or just photoshop?

Sshortdwarf Does anyone have thoughts on how I can train my personal LoRA to not include the...

Furkan Gözükara SECourses•12/12/23, 8:37 PM

using different backgrounds

Sshortdwarf I considered swapping with plain color backgrounds (ex. one red, one blue, etc) ...

Furkan Gözükara SECourses•12/12/23, 8:37 PM

it learns this

Hello Furkan, I keep getting broken images with artifacts. Pls refer me to a tutorial where you expl

Similar Threads

Similar Threads

Similar Threads