Onetrainer a kohya ss alternative SDXL Lora Training on RTX 6GIG and UP

Onetrainer a kohya ss alternative SDXL Lora Training on RTX 6GIG and UP

please not this is a long video, speed it up, Enhancer for youtube is great at that.

this is a over view and how to install and me talking about it, In hopes to encourage more people to do videos on it and get the word out about it.
CivitAI has people using it to make there loras most on RTX3060 8gig cards.

Onetrainer

git

Python

Nvidia Toolkit - CUDA

[streamtabulous]

Good news I'm working out the training I have a very ugly me so it's working.
Update, lora looks great so have the configuration and settings needed.
Unfortunately it's not using cudnn due to a issues with my backend not onetrainer so it's taking much longer than it should.
I'll work that out next but this is fantastic news.

[joneschunghk]

I have trained with this setting on my rtx-3060 8g vram. Its training speed is 1xx s/it (batch 4). Only takes 2 s/it (batch 1) on Kohya_ss. If I need to train LoRA to 5000 steps, it will take over 50 hours to train. I don’t think this speed can “alternate” Kohya_ss

[streamtabulous]

git

Python

Nvidia Toolkit - CUDA

Onetrainer

[AceOnlineMath]

you should try stability matrix to install it, and part of your problem is over tagging your data, try just putting a random key word and man,

[marcusmeins]

Why is CUDA important? one trainer didn't have it before. now it is very slow when i train, slower than before without CUDA .
The old version didn't have any of these new features. this is something new.

[PaulRoneClarke]

I'm showing my ignorance here. But after weeks of using Instant ID with absolutely superb results. Add a face, type in a prompt. 15 seconds later an image that is almost perfect of that face that works at almost work all head angles in different lighting etc.
Then looking at what these model trainers require to achieve the same results. A degree in rocket science, a £1200 graphics card, hours of training on a large image set - and... after doing it, results that as SO much worse than Instant ID
I'm wondering why the best results I get are from the simplest, cheapest and quickest method. (by a country mile)
What is it that Instant ID does that all this faffing about with Loras fails to even get close to?

[beragis]

A number like 3e-06 is not a code, but a representation of a number in scientific notation. For example 3e-4 is 0.0003, 3e-6 is