The 11GB size of LoRA… that’s why it’s better in quality. There’s no magic here. If LoRA weighed 1GB while maintaining quality, that would be a real breakthrough. But models with a size of 23GB, where LoRA doesn’t work properly, and extracted LoRAs at 11GB, are a significant negative effect that needs to be known in advance.

ZZhigarev There is no option to select FP8... only FP16, BF16, Float, and None.

Furkan Gözükara SECourses•12/14/24, 11:32 AM

ok then you need 2 steps

FFurkan Gözükara SECourses ok then you need 2 steps

ZhigarevOP•12/14/24, 11:34 AM

Which steps?

ZZhigarev Which steps?

Furkan Gözükara SECourses•12/14/24, 11:34 AM

convert to fp8

Furkan Gözükara SECourses•12/14/24, 11:34 AM

https://www.patreon.com/posts/how-to-convert-3-115376830

Patreon

How to Convert Your Trained FLUX, Stable Diffusion 3.5, SDXL and Ot...

Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon

ZhigarevOP•12/14/24, 12:21 PM

It reduced the size, but the image is completely black.

ZhigarevOP•12/14/24, 12:22 PM

ZhigarevOP•12/14/24, 1:19 PM

@Furkan Gözükara SECourses This doesn’t work. I performed LoRA extraction from the model with conversion parameters set to FP16 quality, then converted this LoRA to FP8, and again got a black screen.

ZhigarevOP•12/14/24, 1:20 PM

Are you sure your method works?

ZZhigarev <@205854764540362752> This doesn’t work. I performed LoRA extraction from the m...

Furkan Gözükara SECourses•12/14/24, 1:57 PM

yep working

Furkan Gözükara SECourses•12/14/24, 1:58 PM

looks like you did accurate maybe something went wrong or swarmui broken etc

NAMU•12/15/24, 3:25 AM

I know there are much better ways to train a face, but I've got some credits I need to burn through on dreamlook.ai - can anyone suggest best settings to use with their expert mode?

QM•12/15/24, 2:57 PM

for a multi-gpu system Kohya cannot train. It gives me an error for gpu id not set. I tried to specify the GPU id in the Windows_start_Kohya_SS.bat file by somthing like this
set CUDA_VISIBLE_DEVICES=5
changing the device IDs but it didnt start -

running from the Install.bat menu worked for me but it is using the first GPU - it would be great to run paralell if they cannot run across the GPUs

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•12/15/24, 7:41 PM

@Furkan Gözükara SECourses can a rank 256 fp16 lora work well if I'm using the fp8 version of my flux dev fine tune? or does the lora have to be fp8 as well?

QQM for a multi-gpu system Kohya cannot train. It gives me an error for gpu id not s...

Furkan Gözükara SECourses•12/15/24, 9:22 PM

as far as i know multi gpu jnot working on windows

Furkan Gözükara SECourses•12/15/24, 9:22 PM

but if youy want to train on different gpuıs

Furkan Gözükara SECourses•12/15/24, 9:23 PM

use accelerate gpu id setting

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭<@205854764540362752> can a rank 256 fp16 lora work well if I'm using the fp8 ve...

Furkan Gözükara SECourses•12/15/24, 9:23 PM

it should work

ZZhigarev <@205854764540362752> This doesn’t work. I performed LoRA extraction from the m...

Testitou•12/15/24, 9:45 PM

Black screen for me also after conversion to lora fp8

QQM for a multi-gpu system Kohya cannot train. It gives me an error for gpu id not s...

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•12/15/24, 9:52 PM

in Acceleration you can set GPU, and multi GPU, but for fine tune using multi GPU you need 80 GB GPUs, if I remember correctly. No need to edit the bat file

FFurkan Gözükara SECourses it should work

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•12/15/24, 9:52 PM

but it's better to convert it to fp8?

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭in Acceleration you can set GPU, and multi GPU, but for fine tune using multi GP...

Furkan Gözükara SECourses•12/15/24, 10:34 PM

true

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭but it's better to convert it to fp8? 🙂

Furkan Gözükara SECourses•12/15/24, 10:34 PM

not sure. i keep loras as fp32 and base models fp16

Furkan Gözükara SECourses•12/15/24, 10:35 PM

swarmui is able to auto cast into used precision

You do understand that people mostly use models with Loras, right?

Similar Threads

Similar Threads

Similar Threads