Software Engineering Courses (SECourses)•2y ago

@Dr. Furkan Gözükara think I’m having the same issue as the person above? I’ve been trying to train

@Dr. Furkan Gözükara think I’m having the same issue as the person above? I’ve been trying to train today on runpod and physical rtx4090 and keep getting errors

PoppyOP•5/22/24, 2:00 PM

Runpod errors

PoppyOP•5/22/24, 2:01 PM

I’ve just got the pc to work on the 2nd epoch but it’s very glitchy. I have to restart gui.bat around 10 times before it provided the gradio link

FFurkan Gözükara SECourses yes you can use after generated

kareem9000•5/22/24, 2:06 PM

would it work as good as inpainting tho? how does it have context of the picture

AArtChicken thanx... I stopper running windows of tensorrt, but Forge and A111 still crashin...

Furkan Gözükara SECourses•5/22/24, 2:06 PM

restart

Furkan Gözükara SECourses•5/22/24, 2:06 PM

or hard

Furkan Gözükara SECourses•5/22/24, 2:07 PM

you need to delete venv

Furkan Gözükara SECourses•5/22/24, 2:07 PM

and start webui.sh file

PPoppy @Dr. Furkan Gözükara think I’m having the same issue as the person above? I’ve b...

Furkan Gözükara SECourses•5/22/24, 2:07 PM

i think corrupted model

Kkareem9000 would it work as good as inpainting tho? how does it have context of the picture

Furkan Gözükara SECourses•5/22/24, 2:07 PM

i dont know try it

PPoppy @Dr. Furkan Gözükara think I’m having the same issue as the person above? I’ve b...

Furkan Gözükara SECourses•5/22/24, 2:08 PM

i donwload model

Furkan Gözükara SECourses•5/22/24, 2:08 PM

generate image with web ui

Furkan Gözükara SECourses•5/22/24, 2:08 PM

then do training to verify

FFurkan Gözükara SECourses i think corrupted model

PoppyOP•5/22/24, 2:08 PM

How can it be corrupted? I just did your simple tutorial installation for kohya on runpod

PPoppy How can it be corrupted? I just did your simple tutorial installation for kohya ...

Furkan Gözükara SECourses•5/22/24, 2:09 PM

pod

Furkan Gözükara SECourses•5/22/24, 2:09 PM

which model you downloaded?

PoppyOP•5/22/24, 2:09 PM

Oh I see okay

Furkan Gözükara SECourses•5/22/24, 2:09 PM

to ensure load model in web ui and generate image

Furkan Gözükara SECourses•5/22/24, 2:09 PM

that is what i do

Furkan Gözükara SECourses•5/22/24, 2:09 PM

to not waste time

PoppyOP•5/22/24, 2:09 PM

Okay will try that

PoppyOP•5/22/24, 2:59 PM

@Dr. Furkan Gözükara do you know why it won’t provide the link when I run gui.bat?

PoppyOP•5/22/24, 3:05 PM

I managed to get the link after several tries but then the same thing happens when I click “start training”. Here are the types of errors I receive

PoppyOP•5/22/24, 3:05 PM

16:02:36-949749 INFO Epoch: 8
16:02:36-949749 INFO Max train steps: 1600
16:02:36-949749 INFO stop_text_encoder_training = 0
16:02:36-949749 INFO lr_warmup_steps = 0
16:02:36-949749 INFO Saving training config to
C:/Users/RENDA/Pictures/loraface2output\model\loraface2_20240522-160236.json...
16:02:36-949749 INFO Executing command: C:\kohya_ss\venv\Scripts\accelerate.EXE launch --dynamo_backend no
--dynamo_mode default --mixed_precision bf16 --num_processes 1 --num_machines 1
--num_cpu_threads_per_process 2 C:/kohya_ss/sd-scripts/sdxl_train_network.py --config_file
C:/Users/RENDA/Pictures/loraface2output\model/config_lora-20240522-160236.toml
16:02:36-966750 INFO Command executed.
16:02:41-172981 INFO Training has ended.

PoppyOP•5/22/24, 3:06 PM

File "C:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 637, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['C:\kohya_ss\venv\Scripts\python.exe', 'C:/kohya_ss/sd-scripts/sdxl_train_network.py', '--config_file', 'C:/Users/RENDA/Pictures/loraface2output\model/config_lora-20240522-160332.toml']' returned non-zero exit status 3221225477.
16:03:42-841621 INFO Training has ended.

PPoppy @Dr. Furkan Gözükara do you know why it won’t provide the link when I run gui.ba...

Furkan Gözükara SECourses•5/22/24, 3:18 PM

you dont have git?

PPoppy @Dr. Furkan Gözükara do you know why it won’t provide the link when I run gui.ba...

Furkan Gözükara SECourses•5/22/24, 3:19 PM

i bet related to your folders

Furkan Gözükara SECourses•5/22/24, 3:19 PM

C:/Users/RENDA/Pictures/

Furkan Gözükara SECourses•5/22/24, 3:19 PM

dont use users renda pictures

Furkan Gözükara SECourses•5/22/24, 3:19 PM

use like c:/ai_testing

FFurkan Gözükara SECourses C:/Users/RENDA/Pictures/

PoppyOP•5/22/24, 3:30 PM

Hmm but the issues occur even before I reach the stage of putting in the path to images. I’ll check the git.
What’s wrong with the current path? I have just stored the data preparation folder in the pictures

Sandeep•5/22/24, 3:42 PM

does dreambooth lora is capable of style finetuning ?

PPoppy Hmm but the issues occur even before I reach the stage of putting in the path to...

Furkan Gözükara SECourses•5/22/24, 4:01 PM

i dont know try it

Furkan Gözükara SECourses•5/22/24, 4:01 PM

it doesnt show any specific error

SSandeep does dreambooth lora is capable of style finetuning ?

Furkan Gözükara SECourses•5/22/24, 4:01 PM

yes of course

FFurkan Gözükara SECourses TensorRT not working

NicB•5/22/24, 5:04 PM

Do you happen to know what version you are experimenting with? I haven't used tensorrt before but can play around with it a bit too

NNicB Do you happen to know what version you are experimenting with? I haven't used te...

Furkan Gözükara SECourses•5/22/24, 5:05 PM

i tried since first day. never worked. i tried forked repo as well

AArtChicken @Dr. Furkan Gözükara and other fellows that can help: on Massed Compute somethin...

NicB•5/22/24, 5:05 PM

im taking a look at this

Furkan Gözükara SECourses•5/22/24, 5:05 PM

whichj works on runpod windows

NNicB im taking a look at this

Furkan Gözükara SECourses•5/22/24, 5:05 PM

official repo here : https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT

GitHub

GitHub - NVIDIA/Stable-Diffusion-WebUI-TensorRT: TensorRT Extension...

TensorRT Extension for Stable Diffusion Web UI. Contribute to NVIDIA/Stable-Diffusion-WebUI-TensorRT development by creating an account on GitHub.

NicB•5/22/24, 5:05 PM

thanks!

Furkan Gözükara SECourses•5/22/24, 5:05 PM

forked repo : https://github.com/andrewtvuong/Stable-Diffusion-WebUI-TensorRT

GitHub

GitHub - andrewtvuong/Stable-Diffusion-WebUI-TensorRT: TensorRT Ext...

TensorRT Extension for Stable Diffusion Web UI. Contribute to andrewtvuong/Stable-Diffusion-WebUI-TensorRT development by creating an account on GitHub.

Furkan Gözükara SECourses•5/22/24, 5:06 PM

i just used official repo on windows today - latest auto1111

EyeSpyBekoAI•5/22/24, 5:06 PM

Hey community, question for you prompt specialists. Do any of you know what a "prompt modifier" is? I see it get used as a node in ComfyUI, and I see it get loaded in as a positive prompt. It has a "pre-prompt" and a "post-prompt" option. It's a nice addition. Is there a A1111 equivalent of it?
Thanks much!

dxqb•5/22/24, 7:51 PM

what does it do? change the prompt during generation? A1111 syntax is [elephant:mous:0.5]

Ddxqb what does it do? change the prompt during generation? A1111 syntax is [elephant:...

EyeSpyBekoAI•5/22/24, 7:55 PM

From what I can tell, yes, it prioritizes and changes the prompt during generation. When I did a metadata check, it looks like it's doing "pre-prompt - Text Input - Post prompt". But I'm not sure what logic it uses to prioritize.

dxqb•5/22/24, 7:57 PM

well the A1111 prompt can make elephats with mouse ears, if that's what you are looking for

Ddxqb well the A1111 prompt can make elephats with mouse ears, if that's what you are ...

EyeSpyBekoAI•5/22/24, 7:59 PM

Let me see if I understand right. The "mous:0.5" is the weight of the prompt. what does the "elephant:mous" portion of the prompt do?

EEyeSpyBekoAI Hey community, question for you prompt specialists. Do any of you know what a "p...

TheToday•5/22/24, 10:17 PM

What is that version/program of Comfy?

TTheToday What is that version/program of Comfy?

EyeSpyBekoAI•5/22/24, 10:25 PM

Good question. Not sure. It's a workflow I saw online. I found the pre/post prompt concept inriguing.

EyeSpyBekoAI•5/22/24, 10:37 PM

Alright, I did what I should have done 5 hours ago and asked Claude. There's a very clear explanation of what this is and it gave a great answer. I'll screenshot it here.