we already have tutorial for that
we already have tutorial for that
FYouTubeSECourses
In this tutorial, I am going to show you how to install OneTrainer from scratch on your computer and do a Stable Diffusion SDXL (Full Fine-Tuning 10.3 GB VRAM) and SD 1.5 (Full Fine-Tuning 7GB VRAM) based models training on your computer and also do the same training on a very cheap cloud machine from MassedCompute if you don't have such compute...
Fthis one best
FYouTubeSECourses
In this tutorial, I am going to show you how to install OneTrainer from scratch on your computer and do a Stable Diffusion SDXL (Full Fine-Tuning 10.3 GB VRAM) and SD 1.5 (Full Fine-Tuning 7GB VRAM) based models training on your computer and also do the same training on a very cheap cloud machine from MassedCompute if you don't have such compute...
Fi am also reconfiguring the kohya training preset right now
DI'll look at it today ty!
POkay, thank you. I already started with the other tutorial and thought it was working as it's on the 6th epoch, but nothing is saved in the models folder. Do you know why this may be?
Fshow me config
Fmust have made error at config,, you can show interface
Fyolu are missing this
F"save_every_n_epochs": 1,
Fthis is how mine looks
POh
okay, thank you, I'll start again
okay, thank you, I'll start againF
Fwhen doing kohya
Fi suggest
Fmore repeat
Fand save every n steps
FYouTubeSECourses
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 ...
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 ...POkay, great. Kohya wouldn't let me load in your configuration earlier for some reason
F13:33 How to calculate the N number of save every N steps parameter to save checkpoints
13:45 How to calculate total number of steps that your Kohya Stable Diffusion going to take
14:10 If I want to take 5 checkpoints what number of steps I need calculation
13:45 How to calculate total number of steps that your Kohya Stable Diffusion going to take
14:10 If I want to take 5 checkpoints what number of steps I need calculation
Fi am gonna update today hopefully
Fdoing some serious testing
PThis is helpful, thank you, will watch today
F
PAh so it's normal that it wouldn't let me load in your json config? It worked on the pc, but not via runpod for some reason
Fno not normal
Fyou must have given path inaccurately
PI'll try again
Nguys I think there is an error with a detailer
NI am try to open new instances on RunPod and everytime I remove the --skip-install for a detailer to run
Nthen the HTTP server is not running.. I can open auto1111 I mean
Fi can test now
Fstarting a new machine
Fdid you update auto1111 too?
Fusing this?
FNno
Nbecause lately this isn't working anymore
Finstall_latest_auto_1111.sh
Fi am testing now
Nwas saying that to the Runpod team the other days
Nand I gotta be openning HTTP only
Frunpod recently having huge issues
Ftesting installers now
Nfor real
F
Fdmn this speed
F@RMK ask that question to @NicB
R@NicB Could you guys create a way to access JupyterLab inside MasseCompute from an external machine?
For example, JupyterLab is currently on a localhost URL.
Can you make a public URL so that I can access it from an outside network computer like an outside Windows or Mac?
For example, JupyterLab is currently on a localhost URL.
Can you make a public URL so that I can access it from an outside network computer like an outside Windows or Mac?