Software Engineering Courses (SECourses)•14mo ago

Hi Doc... can you explain this to the 5yrs child I am?... I edited the josn and pointed to the Kaggl

Hi Doc... can you explain this to the 5yrs child I am?... I edited the josn and pointed to the Kaggle notebook; unfortunately after the deployment, the kohya instance did'nt show the base model I put in the json file (hosted on my HF account)...

RRebelPuppy should my datasets be on ssd as well. There isn't alot of room on it.

Furkan Gözükara SECourses•11/25/24, 9:34 PM

nope it can be anywhere

Furkan Gözükara SECourses•11/25/24, 9:34 PM

or models

AArtChicken Hi Doc... can you explain this to the 5yrs child I am?... I edited the josn and ...

Furkan Gözükara SECourses•11/25/24, 9:35 PM

using kaggle hard because it is free

Furkan Gözükara SECourses•11/25/24, 9:35 PM

watch this : https://youtu.be/X5WVZ0NMaTg

YouTubeSECourses

How to Download (wget) Models from CivitAI & Hugging Face (HF) & up...

Notebook updated to V5 with huge improvements. If you are having trouble to download models onto your cloud platforms such as RunPod, Google Colab, Kaggle, Massed Compute or anywhere, this tutorial is made for you. Moreover, you can upload your files / models into your private Hugging Face repository and save them permanently privately and downl...

Furkan Gözükara SECourses•11/25/24, 9:35 PM

you need to download into kaggle

Furkan Gözükara SECourses•11/25/24, 9:35 PM

then you need to give its path

RebelPuppy•11/25/24, 9:36 PM

so far your the only one who seems to making good resources for this @Furkan Gözükara SECourses

RRebelPuppy so far your the only one who seems to making good resources for this <@205854764...

Furkan Gözükara SECourses•11/25/24, 9:39 PM

thanks

Xcorpion•11/26/24, 3:44 AM

does Gradient accumulate steps make lora quality bad?

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•11/26/24, 10:48 AM

if all training pics are 2048x2048, should I keep them that way, or reduce to 1024x1024?

RebelPuppy•11/26/24, 2:46 PM

How do I install xformers

XXcorpion does Gradient accumulate steps make lora quality bad?

Furkan Gözükara SECourses•11/26/24, 2:48 PM

it is increasing batch size

Furkan Gözükara SECourses•11/26/24, 2:48 PM

dont do it unless you know what you are doing

RebelPuppy•11/26/24, 2:48 PM

RRebelPuppy How do I install xformers

Furkan Gözükara SECourses•11/26/24, 2:48 PM

venv logic : https://youtu.be/-NjNy7afOQ0

YouTubeSECourses

Essential AI Tools and Libraries: A Guide to Python, Git, C++ Compi...

Welcome to the Pillars of AI Application Libraries: How to Install Tutorial!

Are you ready to embark on a journey of installing AI libraries and applications with ease?

In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine.

We'll also show you ho...

Essential AI Tools and Libraries: A Guide to Python, Git, C++ Compi...

RebelPuppy•11/26/24, 2:49 PM

okay i look at that video

FFurkan Gözükara SECourses it is increasing batch size

Xcorpion•11/26/24, 3:02 PM

yeah that's what I want to do, since 12GB vram cant handle 2batch size with prodigy I was gonna add some accu steps, but saw some people say that it does lower the quality

XXcorpion yeah that's what I want to do, since 12GB vram cant handle 2batch size with prod...

Furkan Gözükara SECourses•11/26/24, 3:04 PM

bigger batch size = lowers quality

Furkan Gözükara SECourses•11/26/24, 3:04 PM

true

RebelPuppy•11/26/24, 3:19 PM

do i need s pefic version of torch or would the most recent work

FFurkan Gözükara SECourses venv logic : https://youtu.be/-NjNy7afOQ0

RebelPuppy•11/26/24, 3:33 PM

Okay xformers is installing now, thanks

RebelPuppy•11/26/24, 3:39 PM

do i use cuda 11.8 or 12.4

RebelPuppy•11/26/24, 3:40 PM

your video used 11.8

Konstantinas•11/26/24, 4:33 PM

I have a general question for anyone who might know: When working with existing Flux checkpoints, should I:

Take an existing checkpoint and train my concepts on top of it, or
Merge my checkpoint (containing my concepts) with another existing checkpoint?

Will both approaches yield the same results? I'm wondering if training on top of an existing checkpoint is better, or if it's just a waste of time when I could simply merge checkpoints instead

RRebelPuppy do i use cuda 11.8 or 12.4

Furkan Gözükara SECourses•11/26/24, 6:25 PM

cuda 12.4

Furkan Gözükara SECourses•11/26/24, 6:25 PM

now we recommend that