Software Engineering Courses (SECourses)•3y ago

Is the workflow for training an object or a concept basically the same? Captioning? A bunch of image

Is the workflow for training an object or a concept basically the same? Captioning? A bunch of images? How many?
Also, what kind of thing are you training for a client - any interesting thoughts about how to get that kind of work - good potential industries for clients?

FFurkan Gözükara SECourses https://youtu.be/3E5fhFQUVLo

Digital [Starburst]•11/26/23, 1:14 AM

I think this is the second class in your Udemy course on SD

Vveldonlives Is the workflow for training an object or a concept basically the same? Captioni...

Furkan Gözükara SECourses•11/26/23, 1:14 AM

i am trying to train a comic style certain

DDigital [Starburst]I think this is the second class in your Udemy course on SD

Furkan Gözükara SECourses•11/26/23, 1:14 AM

yes accurate

Vveldonlives Is the workflow for training an object or a concept basically the same? Captioni...

Furkan Gözükara SECourses•11/26/23, 1:14 AM

captioning effect is experimental

Furkan Gözükara SECourses•11/26/23, 1:15 AM

before going to sleep started this

Furkan Gözükara SECourses•11/26/23, 1:15 AM

with llava captions

Furkan Gözükara SECourses•11/26/23, 1:15 AM

DR.Siva•11/26/23, 1:17 AM

Please help with kaggle error. Dreambooth training ends with error

DDR.Siva Please help with kaggle error. Dreambooth training ends with error

Furkan Gözükara SECourses•11/26/23, 1:19 AM

show the error here. i got to go though. private message me

Furkan Gözükara SECourses•11/26/23, 1:19 AM

also use latest notebook

Furkan Gözükara SECourses•11/26/23, 1:19 AM

and follow this video

Furkan Gözükara SECourses•11/26/23, 1:19 AM

https://youtu.be/16-b1AjvyBE

YouTubeSECourses

How To Do Stable Diffusion XL (SDXL) DreamBooth Training For Free -...

Master Stable Diffusion XL Training on Kaggle for Free!

Welcome to this comprehensive tutorial where I'll be guiding you through the exciting world of setting up and training Stable Diffusion XL (SDXL) with Kohya on a free Kaggle account. This video is your one-stop resource for learning everything from initiating a Kaggle session with dual ...

How To Do Stable Diffusion XL (SDXL) DreamBooth Training For Free -...

DDR.Siva kaggle error : File "/opt/conda/lib/python3.10/site-packages/accelerate/comma...

DR.Siva•11/26/23, 1:19 AM

This

DDR.Siva This

Furkan Gözükara SECourses•11/26/23, 1:20 AM

it doesnt tell teh reason

Furkan Gözükara SECourses•11/26/23, 1:20 AM

start from beginning

Furkan Gözükara SECourses•11/26/23, 1:20 AM

watch tutorial

DR.Siva•11/26/23, 1:21 AM

Give me a sec

DR.Siva•11/26/23, 1:26 AM

https://pastebin.com/6apERzrG

Pastebin

To create a public link, set `share=True` in `launch()`.16:41:02-51...

Pastebin.com is the number one paste tool since 2002. Pastebin is a website where you can store text online for a set period of time.

DR.Siva•11/26/23, 1:41 AM

using latest only : kohya-sdxl-lora-training-on-a-free-kaggle-notebook_v12.ipynb

DR.Siva•11/26/23, 2:22 AM

started fresh.. caching going on.

DR.Siva•11/26/23, 2:36 AM

https://pastebin.com/uqHeWkqu

Pastebin

[Dataset 0]caching latents.checking cache validity...100%|█████████...

Pastebin.com is the number one paste tool since 2002. Pastebin is a website where you can store text online for a set period of time.

DR.Siva•11/26/23, 2:54 AM

ok there was slight variation of size of my training images , some were 1024 and few were 512.. will rectify and try it again..

GeekDadKevin•11/26/23, 4:02 AM

Has anyone played with stable-fast yet? I'm getting decent results in SDXL (crap with 1.5) and it's 2x as fast as a1111/sd.next (sd.next claims it is in their latest build but I only get results when I gen using python scripts)

Ned Shoaei•11/26/23, 4:03 AM

hi everyone, I have a question about my xl controlnet models. for some reason even when I updated them from the patreon file in my runpod, it's still not working.

Ned Shoaei•11/26/23, 4:03 AM

screencapture-2c799b4184f6fb1bde-gradio-live-2023-11-25-23_02_00.png

Ned Shoaei•11/26/23, 4:04 AM

it shows it in the preview, but it's not showing in my generated image

GeekDadKevin•11/26/23, 4:06 AM

that is an SD1.5 model .. it will break control net

GeekDadKevin•11/26/23, 4:06 AM

need the XL models

GeekDadKevin•11/26/23, 4:07 AM

https://huggingface.co/lllyasviel/sd_control_collection/tree/main

lllyasviel/sd_control_collection at main

GeekDadKevin•11/26/23, 4:08 AM

or if you have them already hit the down arrow on models and choose an XL compatible one

Ned Shoaei•11/26/23, 4:14 AM

screencapture-d316c8191a7ad70277-gradio-live-2023-11-25-23_14_09.png

GGeekDadKevin or if you have them already hit the down arrow on models and choose an XL compat...

Ned Shoaei•11/26/23, 4:16 AM

I send the wrong photo sry, it's not working with xl controlnet models

FFurkan Gözükara SECourses currently if you have GPU

Ereshkigal•11/26/23, 4:17 AM

Yes, I'm running a 4090 at the moment. I'm just wondering which version of Dreambooth I should use in terms of the ones listed here https://github.com/d8ahazard/sd_dreambooth_extension/tags , because it seems like the version I got from the "extensions" tab is just not working properly, or I have something set very wrong & nothing is fixing it for some reason.
I mentioned before, when I first watched your original Tutorial on training LoRA through Dreambooth, my Dreambooth looked the same as yours & everything was decent enough, but then my SD broke when I was trying to get TensorRT working the first time, so I had to reinstall it from scratch, and since then, my Dreambooth looks very different from the one in the tutorial, so I'm not sure if I'm missing a setting, have something wrong, or what the issue is.
I've tried training the same face off as many as 60 & as few as 25 images, with quite a few different settings ranges (I've literally tried to train this face 10 times now lol), and it keeps coming up as barely any different than if I put the person's name in with no LoRA loaded, in terms of how they look, on a given Checkpoint.

GitHub

Tags · d8ahazard/sd_dreambooth_extension

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

DDigital [Starburst]I'm getting an error with TensorRT when trying to install Dreambooth

Ereshkigal•11/26/23, 4:21 AM

depending on how hot you're getting, and what GPU we're talking about, it should be fine. I cranked my 4090 at one point when rendering batches of 4x4, and it was actually getting warm enough to thermally throttle the clocks slightly, but that was with a +150 core or so offset, with the voltage maxed & the power slider maxed, and that's on an air cooled card in a well ventilated case, the GPU Hotspot in HWInfo was showing 87.6C

it was kinda warm in here since it's winter, but yeah. If you're not overclocking and you have a well ventilated case, I would say don't worry about it.
You can also try Undervolting, because rendering in SD uses VRAM more than the Core, so undervolting/downclocking your core a bit will actually save a lot of heat by lowering your power draw. I've been running my 4090 @ 2600MHz core with 900mV & the difference in render time between that & stock is less than 3 seconds on a 16-image batch - but that runs literally 10C cooler on the core & draws ~120W less power while rendering.
Quoted the wrong post but that was in reference to you asking about liquid cooling your GPU.

NNed Shoaei I send the wrong photo sry, it's not working with xl controlnet models

Ned Shoaei•11/26/23, 4:52 AM

I have used the CN py from patreon to update:
python CND_runpod.py

still having issues

Ned Shoaei•11/26/23, 4:52 AM

this is my extension tab:

DR.Siva•11/26/23, 4:52 AM

It failed again : https://pastebin.com/0h7sSbKa

Pastebin

--2023-11-26 03:58:27-- https://huggingface.co/MonsterMMORPG/SECou...

Pastebin.com is the number one paste tool since 2002. Pastebin is a website where you can store text online for a set period of time.

DR.Siva•11/26/23, 4:53 AM

for time being will train new image batch with lora. Last time there were too many repeating images which made lora inherit certain aspect of dress/color into it and was making output with repative features of the images

DDR.Siva It failed again : https://pastebin.com/0h7sSbKa

Furkan Gözükara SECourses•11/26/23, 9:07 AM

just run cell again

Furkan Gözükara SECourses•11/26/23, 9:07 AM

load and hit again

Furkan Gözükara SECourses•11/26/23, 9:07 AM

it will cache the remaining images

Furkan Gözükara SECourses•11/26/23, 9:07 AM

what(): [Rank 1] Watchdog caught collective operation timeout: WorkNCCL(SeqNum=3, OpType=ALLREDUCE, Timeout(ms)=1800000) ran for 1802130 milliseconds before timing out.

Furkan Gözükara SECourses•11/26/23, 9:07 AM

caching taking too long thus failing

Furkan Gözükara SECourses•11/26/23, 9:08 AM

or reduce repeating count

Furkan Gözükara SECourses•11/26/23, 9:08 AM

like half it and double the epoch

NNed Shoaei I have used the CN py from patreon to update: python CND_runpod.py still having...

Furkan Gözükara SECourses•11/26/23, 9:09 AM

hi you need to show cmd output

Furkan Gözükara SECourses•11/26/23, 9:09 AM

did you kill previous instance and started yourself?