Software Engineering Courses (SECourses)•3y ago

@Furkan Gözükara SECourses I am Following your video on Crating my own model https://www.youtube.c

@Furkan Gözükara SECourses I am Following your video on Crating my own model https://www.youtube.com/watch?v=TpuDOsuKIBo

For the pictures where i am to train my images

What is the min resolution, and corresponding File size should i target to train the model with to get the best image possible?
Do all my images need to be in the same resolution to be able to train?

YouTubeSECourses

Generate Studio Quality Realistic Photos By Kohya LoRA Stable Diffu...

#Kohya SS web GUI DreamBooth #LoRA training full tutorial. You don't need technical knowledge to follow this tutorial. In this tutorial I have explained how to generate professional photo studio quality portrait / self images for free with Stable Diffusion training.

Our Discord server

https://bit.ly/SECoursesDiscord

If I have been of assis...

Ppaleolithic @Furkan Gözükara SECourses I am Following your video on Crating my own model h...

Furkan Gözükara SECourses•5/24/23, 11:21 PM

1 : 512x512 preferred

Furkan Gözükara SECourses•5/24/23, 11:21 PM

2 : no

Furkan Gözükara SECourses•5/24/23, 11:21 PM

but they will get downscaled according to your max resolution you set

paleolithicOP•5/24/23, 11:22 PM

Thank you!

Final one, For installing Kohya, i found a kohya Plugin in Automatic1111 called Kohya-ss Additional Networks. Is that the same kohya as your tutorial or it that a different concept all together?

Ppaleolithic Thank you! Final one, For installing Kohya, i found a kohya Plugin in Automat...

Furkan Gözükara SECourses•5/24/23, 11:24 PM

it is for only using kohya generated lora files i think

Ppaleolithic @Furkan Gözükara SECourses I am Following your video on Crating my own model h...

felixsanz•5/24/23, 11:29 PM

is your face flexible here? can you do "smiling" prompt for example?

felixsanz•5/24/23, 11:30 PM

or your face is very rigid?

paleolithicOP•5/24/23, 11:30 PM

Same question, also for my training i am using a combo of full body and faces.

paleolithicOP•5/24/23, 11:31 PM

Let's see

paleolithicOP•5/24/23, 11:33 PM

Also idk is 20 HQ images are sufficient?

Furkan Gözükara SECourses•5/24/23, 11:33 PM

full body usually wont give you good result

Furkan Gözükara SECourses•5/24/23, 11:33 PM

you need inpainting

Furkan Gözükara SECourses•5/24/23, 11:34 PM

so add few full body just for overall shape

paleolithicOP•5/24/23, 11:43 PM

Gotcha

felixsanz•5/24/23, 11:52 PM

after months i'm still not able to use this, any idea someone?

>> patchmatch.patch_match: ERROR - patchmatch failed to load or compile (libnppc.so.12: cannot open shared object file: No such file or directory).

felixsanz•5/24/23, 11:53 PM

i think it's related to cuda 12

felixsanz•5/24/23, 11:53 PM

but i'm using 11.7

felixsanz•5/24/23, 11:53 PM

maybe my linux drivers are problem here

Ffelixsanz after months i'm still not able to use this, any idea someone? >> patchmatch.p...

Furkan Gözükara SECourses•5/24/23, 11:53 PM

where do you get this error

Furkan Gözükara SECourses•5/24/23, 11:55 PM

i am going to sleep hopefully see you tomorrow. if i missed any questions please mention me again

felixsanz•5/24/23, 11:58 PM

on invokeai

Dawood•5/24/23, 11:59 PM

@Furkan Gözükara SECourses I basically binge watched all of your dreambooth training videos, very helpful. I wanted to ask you tho, if I want to be able to generate a face in a specific style like let's say there's a civit ai model of that style, if i train my face on that model, the training is very bad, do u have any recommended approaches for this

felixsanz•5/24/23, 11:59 PM

patchmatch is the infill method for inpainting

FFurkan Gözükara SECourses i am going to sleep hopefully see you tomorrow. if i missed any questions please...

felixsanz•5/24/23, 11:59 PM

good night

Null•5/25/23, 2:18 AM

Hi All, I just joined here from the Lora stable diffusion video

Null•5/25/23, 2:18 AM

does anyone know what is Stable Diffusion by Automatic1111, why do we need it if I already have stable diffusion in kohya_ss

pat._.fenis•5/25/23, 3:08 AM

Having essentially the same issue with LDSR as I was having with controlnet, I did not see any outgoing request through my firewall that was being blocked so I am not sure how to fix the issue. This is a fresh Windows 10 install with fresh Python 3.10.6 and freshAutomatic1111 dev build install on an Auros Master z590 with a 4090, 11700@4.9ghz, 128gb 3200 ram and a 2tb gen 4.0 NVME.

Null•5/25/23, 4:01 AM

Null•5/25/23, 4:01 AM

I'm getting this even for 1 batch size

Null•5/25/23, 4:02 AM

kevh•5/25/23, 4:04 AM

Is Multi-frame Video rendering not working for other people? It seems like I'm just not able to upload guide frames. I'm able to select, but get no confirmation message about this. Trying to follow this tutorial: https://www.youtube.com/watch?v=kmT-z2lqEPQ&ab_channel=SECourses. Reverting to a previous commit also doesn't work because I'm using the Google Colab from fastBen Automatic1111 and reverting breaks other components of the code

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...

kevh•5/25/23, 4:12 AM

Nevermind, I'm able to upload, I just run into this error: PIL.UnidentifiedImageError: cannot identify image file '/tmp/1000bz1rz3p6.png'. Does this error just render this tutorial not really followable? Because it seems like a crucial step in creating the video that's missing from the entire pipeline with this bug

DeadMan1999•5/25/23, 6:13 AM

@Furkan Gözükara SECourses what is the best approach for Dreambooth training in terms of time and resource (RAM/VRAM) consumption for a single GPU (3060 12GB). Are the Kohya_ss and A1111 the most efficient for model training or does these libraries ColossalAI (https://github.com/hpcaitech/ColossalAI#AIGC) and VoltaML (https://github.com/VoltaML/voltaML-fast-stable-diffusion) offer better training speed and efficient memory utilization? I don't mind the OS, be it windows or Linux.

saudhach•5/25/23, 8:14 AM

Hii all of you

Ssaudhach Hii all of you

ashley•5/25/23, 8:20 AM

Hello

ashley•5/25/23, 8:20 AM

How does one go about cloning the configuration/persistent volumes for a RunPod pod? Is that done using Cloud Sync or something else?

AvidyaCM•5/25/23, 8:21 AM

@Furkan Gözükara SECourses https://geohot.github.io/blog/jekyll/update/2023/05/24/the-tiny-corp-raised-5M.html
very interesting article from popular startup ceo making chip company. curious ur thoughts as he says NVIDIA is like apple and they will make android (working with AMD)

the singularity is nearer

the tiny corp raised $5.1M

Here we go again. I started another company. The money is in the bank.

AvidyaCM•5/25/23, 8:22 AM

code here: https://github.com/geohot/tinygrad

GitHub

GitHub - geohot/tinygrad: You like pytorch? You like micrograd? You...

You like pytorch? You like micrograd? You love tinygrad!

GitHub - geohot/tinygrad: You like pytorch? You like micrograd? You love tinygrad!

Aashley Hello

saudhach•5/25/23, 8:27 AM

hopeyan•5/25/23, 9:35 AM

@Furkan Gözükara SECourses when choose lion optimizer , what is the best setting for batch size ,gradient accumulation steps ,learning rate

majidzendaniyan•5/25/23, 9:46 AM

Is it possible to create such an image with stable diffusion? What tips are needed to make it?

ManicWulf•5/25/23, 9:54 AM

I've just seen the Video to Anime tutorial and now I wonder, would it be possible/feasible to apply this to something other than a person? Specifically I'm thinking about taking footage of me cooking (no person in frame, only hands/food/tools) and style change it to anime style.
If it's doable, would I have to do the training for each new recipe/video or could I just do the training with a few videos and then use the same training data for more?

Furkan Gözükara SECourses•5/25/23, 10:36 AM

wow i am having so many meetings with companies recently

DDawood @Furkan Gözükara SECourses I basically binge watched all of your dreambooth trai...

Furkan Gözükara SECourses•5/25/23, 10:36 AM

did you try to train with dreambooth?

Furkan Gözükara SECourses•5/25/23, 10:36 AM

i think it works better

NNull does anyone know what is Stable Diffusion by Automatic1111, why do we need it if...

Furkan Gözükara SECourses•5/25/23, 10:37 AM

we use automatic1111 for inference. kohya for training

NNull Click to see attachment

Furkan Gözükara SECourses•5/25/23, 10:37 AM

you need to add more memory optimization

Furkan Gözükara SECourses•5/25/23, 10:37 AM

there are advanced settings

Furkan Gözükara SECourses•5/25/23, 10:38 AM

gradient checkpoint memory attention xformers

Kkevh Nevermind, I'm able to upload, I just run into this error: PIL.UnidentifiedImage...

Furkan Gözükara SECourses•5/25/23, 10:38 AM

it still works. are you using dev version of the atuomatic1111? try with dev branch. i tested the video workflow on runpod few days ago for a patreon subscriber. it worked very well

@Furkan Gözükara SECourses I am Following your video on Crating my own model https://www.youtube.c

Similar Threads