Software Engineering Courses (SECourses)•3y ago

and i'm assuming the more epochs I do, the more versatile my model will be?

ZZono50 and i'm assuming the more epochs I do, the more versatile my model will be?

Furkan Gözükara SECourses•3/25/23, 3:16 PM

it will be lesser flexiable

Zono50OP•3/25/23, 3:16 PM

so i want to do as few epochs as possible while still getting my character?

Zono50OP•3/25/23, 3:17 PM

i'll run some test, and i'll do that tomer hanuka image

ZhuoFan•3/25/23, 3:18 PM

you can check this video, could be usefull https://www.youtube.com/watch?v=7m522D01mh0

Zono50OP•3/25/23, 3:19 PM

i'll train for a while, and the images will look perfect, then like 10 or 20 epochs later, their faces just get all blurry, is it overtrained at that point?

AlaBeat•3/25/23, 3:22 PM

yes, the more you train, the higher the chances to overcook your model

Zono50OP•3/25/23, 3:27 PM

i'm assuming that's based on the scheduler as well

genialgenteel•3/25/23, 3:41 PM

@Furkan Gözükara SECourses Hello, I am new here, and I am trying out training a model for the first time on Google Colab. I have been following this video:
https://www.youtube.com/watch?v=mnCY8uM7E50
To preface, I am not a programmer, just a hobbyist interested in generating AI art of my original character (fictional). So sorry if I ask any dumb questions!

I am trying to start the training. I click the arrow to run the cell starting with

!accelerate launch train_dreambooth.py \

and a message appeared saying:

[15:34:11] WARNING The following values were not passed to

Is that normal? Did I do something wrong? Can anyone help? I'd appreciate it. Thank you!

YouTubeSECourses - Software Engineering Courses

Transform Your Selfie into a Stunning AI Avatar with Stable Diffusi...

Our Discord : https://discord.gg/HbqgGaZVmr. How to do free Stable Diffusion DreamBooth training on Google Colab 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 Stable Diffusion Tutorials, Automatic1111 and Goo...

FFurkan Gözükara SECourses Click to see attachment

Cypo•3/25/23, 3:46 PM

do you have the little video ?

Original message was deleted

Cypo•3/25/23, 5:08 PM

@Furkan Gözükara SECourses

felixsanz•3/25/23, 5:28 PM

i'm trying loras but i'm gettiing this kind of look

felixsanz•3/25/23, 5:28 PM

felixsanz•3/25/23, 5:28 PM

is that overtraining?

felixsanz•3/25/23, 5:34 PM

or still need more training? face doesn't even look much like subject

Nesith•3/25/23, 6:24 PM

why cant i get a perfect spider man kit on my self

felixsanz•3/25/23, 6:28 PM

does your model knows about spiderman?

felixsanz•3/25/23, 6:28 PM

try spider-man

Nesith•3/25/23, 6:29 PM

yes i think so

Nesith•3/25/23, 6:30 PM

wait i will send a screenshot

Nesith•3/25/23, 6:32 PM

this is the only good one i got

Nesith•3/25/23, 6:33 PM

brenkhof•3/25/23, 6:45 PM

@Furkan Gözükara SECourses Hey I followed your dreambooth extension install tutorial for runpod today on youtube, but I'm stuck at the last 2 steps. Could you help me please?

brenkhof•3/25/23, 6:46 PM

Longshao•3/25/23, 7:41 PM

Hey guys, just downloaded realistic vision to my laptop. How do I get it to work in runpod?

LLongshao Hey guys, just downloaded realistic vision to my laptop. How do I get it to work...

idmon•3/25/23, 7:43 PM

Connect to Jupyter (backend of your server) and there go to /workspace and navigate within the web-ui folder towards the /models folder as you already know

idmon•3/25/23, 7:43 PM

Drop your model there and let it upload.. might take a while since Jupyter is slow

Iidmon Drop your model there and let it upload.. might take a while since Jupyter is sl...

Longshao•3/25/23, 7:45 PM

Thanks, I'm new to this, but I'll follow your instructions, do you know of any video tutorials etc?

idmon•3/25/23, 7:46 PM

I think Furkan made some excellent tutorials explaining Runpod and Jupyter

idmon•3/25/23, 7:46 PM

problem is this space moves so fast. A tutorial from last month might be outdated today

Longshao•3/25/23, 7:46 PM

Facts, lol

Rewire•3/25/23, 7:48 PM

I cant get a good model out of dreambooth, and training takes hours on my 3090. Also, it keeps trying to make thousands of class samples.

What gives?

idmon•3/25/23, 7:49 PM

I'm training dreambooth as well on my 3090... it shouldn't take hours

idmon•3/25/23, 7:51 PM

Did you provide a folder with pre-generated class images?

idmon•3/25/23, 7:51 PM

Because if you don't provide it... it will generate it based on this value

brenkhof•3/25/23, 7:59 PM

Does anybody have a good fresh tutorial on how to install dreambooth on runpod? I used Furkans last one, but that didn't work

TMorgan•3/25/23, 8:51 PM

@Furkan Gözükara SECourses Hello! I finished downloading all the ControlNet files and am continuing to get the FileNotFound message. I could not find the cldm_v15.yaml file, either.

Iidmon Did you provide a folder with pre-generated class images?

Rewire•3/25/23, 9:19 PM

Every tutorial I've watched says nothing about providing class images. They always just seem to generate them?

Rewire•3/25/23, 9:20 PM

Picture of a man

Rewire•3/25/23, 9:20 PM

For example

idmon•3/25/23, 9:20 PM

You can generate them yourself and save them for future trainings

idmon•3/25/23, 9:21 PM

Store them in a folder "man", "woman", "..." all the classes you frequently train

idmon•3/25/23, 9:21 PM

and link back to that

idmon•3/25/23, 9:21 PM

saves time

Rewire•3/25/23, 9:21 PM

Interesting

Rewire•3/25/23, 9:21 PM

I mean after the training I can generate pictures of my face just fine but attaching them to something else like a superhero costume doesn't do anything anytime I insert my instance prompt it just generates a picture of my face it won't ever do anything extra beyond that.

Rewire•3/25/23, 9:23 PM

Can I use my own preprocessed images with clip descriptions to act as a class?

Rewire•3/25/23, 9:23 PM

Or will that skew the training data.

idmon•3/25/23, 9:23 PM

Yes I do that myself actually

idmon•3/25/23, 9:24 PM

I generate them on the same model I train on (important detail) on sampler: DDIM (default diffusion method for training) on 30 - 50 steps

Rewire•3/25/23, 9:24 PM

Interesting. Any luck with adding additional prompts though like making yourself into a superhero or making yourself into like iron Man or something.

and i'm assuming the more epochs I do, the more versatile my model will be?

Similar Threads

Similar Threads

Similar Threads