Software Engineering Courses (SECourses)•16mo ago

Now I`m using SwarmUI, but I have no clue on hoe to achieve the faces I have already with future gen

Now I`m using SwarmUI, but I have no clue on hoe to achieve the faces I have already with future generations. Does anyone have a suggestion of how can I go about this?

VVinmi Now I`m using SwarmUI, but I have no clue on hoe to achieve the faces I have alr...

Furkan Gözükara SECourses•9/12/24, 12:24 AM

what you want to do?

Furkan Gözükara SECourses•9/12/24, 12:24 AM

once you do training you dont need swapface

FFurkan Gözükara SECourses once you do training you dont need swapface

VinmiOP•9/12/24, 12:26 AM

You mean make a LORA?

VVinmi You mean make a LORA?

Furkan Gözükara SECourses•9/12/24, 12:26 AM

yep

VinmiOP•9/12/24, 12:27 AM

I assume I don't have enough computer power to do that

VinmiOP•9/12/24, 12:27 AM

How many images do I need of my subject?

VVinmi How many images do I need of my subject?

Furkan Gözükara SECourses•9/12/24, 12:28 AM

15 good

Furkan Gözükara SECourses•9/12/24, 12:28 AM

you can use cloud

Furkan Gözükara SECourses•9/12/24, 12:28 AM

first tutorial : https://youtu.be/nySGu12Y05k

YouTubeSECourses

FLUX LoRA Training Simplified: From Zero to Hero with Kohya SS GUI ...

Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please wat...

Furkan Gözükara SECourses•9/12/24, 12:28 AM

second for cloud : https://youtu.be/-uhL2nW7Ddw

YouTubeSECourses

Blazing Fast & Ultra Cheap FLUX LoRA Training on Massed Compute & R...

Unlock the power of FLUX LoRA training, even if you're short on GPUs or looking to boost speed and scale! This comprehensive guide takes you from novice to expert, showing you how to use Kohya GUI for creating top-notch FLUX LoRAs in the cloud. We'll cover everything: maximizing quality, optimizing speed, and finding the best deals. With our exc...

Furkan Gözükara SECourses•9/12/24, 12:30 AM

lower LR 256 images failed , it is undertrained at 40 epochs

FFurkan Gözükara SECourses lower LR 256 images failed , it is undertrained at 40 epochs 😄

VinmiOP•9/12/24, 12:30 AM

what those terms mean?

VinmiOP•9/12/24, 12:30 AM

Seem them before

Furkan Gözükara SECourses•9/12/24, 12:30 AM

LR means learning rate

Furkan Gözükara SECourses•9/12/24, 12:30 AM

you should watch above videos fully

Furkan Gözükara SECourses•9/12/24, 12:31 AM

Furkan Gözükara SECourses•9/12/24, 12:31 AM

the resemblance not there yet

Furkan Gözükara SECourses•9/12/24, 12:32 AM

also lacking that lora brought realism

Furkan Gözükara SECourses•9/12/24, 12:33 AM

i will post 256 images result on patreon now

Furkan Gözükara SECourses•9/12/24, 12:33 AM

will do another training

AIGambino•9/12/24, 1:03 AM

AIGambino•9/12/24, 1:03 AM

hands still major issue in fully body poses

Furkan Gözükara SECourses•9/12/24, 1:29 AM

started new training :d

FFurkan Gözükara SECourses started new training :d

VinmiOP•9/12/24, 1:31 AM

VinmiOP•9/12/24, 1:32 AM

also training here

VinmiOP•9/12/24, 1:32 AM

but on the cloud, my 3070TI has a shitty amount of VRAM for that task

VVinmi Click to see attachment

Furkan Gözükara SECourses•9/12/24, 1:34 AM

use massed compute

Furkan Gözükara SECourses•9/12/24, 1:34 AM

way cheaper

Furkan Gözükara SECourses•9/12/24, 1:34 AM

way better quality with our config

VinmiOP•9/12/24, 1:34 AM

I had some credits there

Furkan Gözükara SECourses•9/12/24, 1:34 AM

h100 total waste of money :d

Furkan Gözükara SECourses•9/12/24, 1:35 AM

for example lora rank 16 = much lower quality compared to 128

Furkan Gözükara SECourses•9/12/24, 1:35 AM

i compared

FFurkan Gözükara SECourses for example lora rank 16 = much lower quality compared to 128

VinmiOP•9/12/24, 1:53 AM

I'm training again on 128

AIGambino•9/12/24, 3:00 AM

what quality specifically dr?

VinmiOP•9/12/24, 3:37 AM

did it and now all I get are big headed photos

Dragoy•9/12/24, 3:57 AM

@Lecturer - Main Admin I wonder if you've ever used modal.com? How difficult is it to run kohya_ss there?

xlads•9/12/24, 5:16 AM

xlads•9/12/24, 5:19 AM

Something that I see has helped in prompts that include multiple people is changing what the people are wearing their age and hair color

mikemenders•9/12/24, 5:25 AM

I'm still waiting with Flux for several reasons. For one thing, what I see from current loras is that low weight/alpha is enough for posing, so some people use 8s. On the other hand, human anatomy is horrible, so not trained on nsfw images, so it will be a lot more work to train all body parts, and I'd rather wait for that until more sophisticated flux models are available. As I see it, it will be at least 2-3 months. The Pony is also being made for Auraflow first (which is also because of the license), so the transition to flux is a long way off for me.

wardensc2•9/12/24, 6:37 AM

Does fp8 vs fp16 lora quality diffrerent much ?

DDragoy @Lecturer - Main Admin I wonder if you've ever used modal.com? How difficult is ...

Furkan Gözükara SECourses•9/12/24, 9:36 AM

no idea

AAIGambino what quality specifically dr?

Furkan Gözükara SECourses•9/12/24, 9:36 AM

quality of training

Wwardensc2 Does fp8 vs fp16 lora quality diffrerent much ?

Furkan Gözükara SECourses•9/12/24, 9:37 AM

a little bit

magical•9/12/24, 10:09 AM

For sdxl training on runpod, restarting the pod or pkill -f "relauncher.py" isn't ending the gpu memory usage for me

magical•9/12/24, 10:09 AM

Does anyone else have this problem?

magical•9/12/24, 10:20 AM

but if I only want to train and not use A1111 in kohya I don't have to choose Stable Diffusion template and upload the relauncher.py, right?

TOPUI•9/12/24, 10:54 AM

If my current image size is 16:9 and the resolution is 1024X576, is this how the size should be filled in on OneTrainer? @Dr. Furkan Gözükara

hellolaco•9/12/24, 10:56 AM

if I want to run Flux dev on a cloud with Forge webui, which site do you recommend? I've tried runpod but their Forge is not updated.

liorftw•9/12/24, 11:45 AM

https://github.com/rickrender/FluxLatentUpscaler
hey i saw this, and i trained a lora model with my dataset, can i use this upscaler in the swarmui? because the results looks very good, or it's something not relatable and its his own model

GitHub

GitHub - rickrender/FluxLatentUpscaler: This Flux latent upscaler w...

This Flux latent upscaler workflow creates a lower-resolution initial pass, then advances to a second pass that upscales in latent space to twice the original size. Latent space manipulations in th...

Now I`m using SwarmUI, but I have no clue on hoe to achieve the faces I have already with future gen

Similar Threads