Software Engineering Courses (SECourses)•15mo ago

I trained flux with some big datasets off 3500 images for 40 epochs and I hade great results but is

I trained flux with some big datasets off 3500 images for 40 epochs and I hade great results but is for a style and some new concepts, is unable to train many specific individuals consistently

Ddsienra I trained flux with some big datasets off 3500 images for 40 epochs and I hade g...

crystalwizard•10/5/24, 5:25 AM

you'll get 'something' - but you won't get something that actually updates flux's weights the way a training is supposed to. all you're going to get is something that overwrites what the AI knows. the results you'd get would be different if it was actually training the model

crystalwizard•10/5/24, 5:26 AM

that's what a LoRA is for - to allow you to add information and update the weights for specific things without retraining the entire model. but what you're getting is about the same as if someone took a piece of paper, drew on it, and pasted it over a photo. you're not changing the photo, you're just putting somethign over it.

crystalwizard•10/5/24, 5:26 AM

and because flux IS NOT trainable, regardless of what you keep seeing people say, when you try to train it for things that do require those weights to be updated, it can't happen

crystalwizard•10/5/24, 5:28 AM

you can make something that'll put your face on an image - but you could do that with face swap, too

dsienraOP•10/5/24, 5:29 AM

no ,but face swap not compares at all one you can get training a good lora

dsienraOP•10/5/24, 5:30 AM

you can get a good style

dsienraOP•10/5/24, 5:30 AM

and then a lora for one subject at a time

crystalwizard•10/5/24, 5:31 AM

and that is exactly what you will not get out of flux. use SDXL

crystalwizard•10/5/24, 5:31 AM

also, i'll be very surprised if black forest releases any updates to dev or schnell anytime soon. the money is in pro, and the people that are paying 5 cents a generation for it's API

dsienraOP•10/5/24, 5:32 AM

I'm not interested in paying for it

crystalwizard•10/5/24, 5:33 AM

that's the only way you're going to get your hands on pro. it's only available via an expensive API

dsienraOP•10/5/24, 5:33 AM

I use everything local in my computer

crystalwizard•10/5/24, 5:33 AM

as do i

crystalwizard•10/5/24, 5:33 AM

and pro is the only version that wasn't run through the distill process

dsienraOP•10/5/24, 5:33 AM

yes I know

crystalwizard•10/5/24, 5:34 AM

give flux some tokens with unclear subjects and see what it creates for you

crystalwizard•10/5/24, 5:35 AM

actually, pull up flux dev and give it the word Pail as a prompt. just one word. run that 10 times, and see what it does

crystalwizard•10/5/24, 5:36 AM

use the actual flux dev that bfl released, not something that's been messed with by the community

dsienraOP•10/5/24, 5:37 AM

let's see, for know it works for my purpose, I can train a style and some concepts and on top a character at a time, that works perfect for me, is tedious because I need a lora for each subject but is a workaround

dsienraOP•10/5/24, 5:38 AM

two people in the same lora is imposible

Ddsienra two people in the same lora is imposible

crystalwizard•10/5/24, 5:39 AM

no it's not. well, for flux it is, but no it's not

dsienraOP•10/5/24, 5:43 AM

with sdxl I can train more than 20 people on the same lora no bleeding and the style at the same time, works perfect

dsienraOP•10/5/24, 5:44 AM

but the quality is so much worse than blux

dsienraOP•10/5/24, 5:44 AM

but the quality is so much worse than Flux

Ddsienra with sdxl I can train more than 20 people on the same lora no bleeding and the s...

crystalwizard•10/5/24, 5:45 AM

because flux is not trainable. you are getting 'something' - but you are not getting an actual object trained on flux.

crystalwizard•10/5/24, 5:45 AM

you're just getting something that'll draw over it and run with it without errors

crystalwizard•10/5/24, 5:45 AM

there's a reason that BFL never released the training parmeters - it's not trainable

crystalwizard•10/5/24, 5:46 AM

and they know it isn't

crystalwizard•10/5/24, 5:46 AM

they couldn't fix the issues it has, so they did stuff to mask them, and that makes it almost unusuable for anything other than exactly what they released, with a very narrow range of what it can successfully do

crystalwizard•10/5/24, 5:48 AM

you could take sd3-2b-medium, train loras for it, get better trained loras and have stuff that would work just as well.

dsienraOP•10/5/24, 5:50 AM

I understand what you say, may be you right and is imposible to reverse engineering it

Ddsienra I understand what you say, may be you right and is imposible to reverse enginee...

crystalwizard•10/5/24, 5:50 AM

i know what they did - along with filling up their data set with midjourney images.

Maxivi•10/5/24, 5:51 AM

https://x.com/ostrisai/status/1842388844970135932

hes still working on it

Ostris (@ostrisai) on X

I haven't spoken much about my ongoing project to de-distill schnell to make a permissive licensed version of flux, but I have been updating it periodically as it trains. I just noticed it is the #2 trending text-to-image model on Hugging Face. Working on aesthetic tuning now.

Twitter

•

10/5/24, 2:18 AM

crystalwizard•10/5/24, 5:51 AM

it's not a matter of reverse engineering it, it's a matter of it's being impossible to undo

MMaxivi https://x.com/ostrisai/status/1842388844970135932 hes still working on it

crystalwizard•10/5/24, 5:51 AM

yeah, i know. he can't do what he think he can.

crystalwizard•10/5/24, 5:52 AM

it's sort of like this - if you mix up flour, water, eggs, chocolate chips, sugar, baking soda, salt - you have a batter that can be turned into a lot of things. YOu could make a chocolate chip cake or cookies at this point. if you then bake cookies, you have cookies. and no one can come along and turn those cookies back into batter.

crystalwizard•10/5/24, 5:53 AM

they can soak them in water, and get mush

crystalwizard•10/5/24, 5:53 AM

but it's still nto batter

crystalwizard•10/5/24, 5:54 AM

you can then shape the mush into some other shape, and say you turned it back into batter and now you've baked a cake or something - but you didn't actually do that. you just made mush and reshaped cookies into cake shaped cookies that now don't taste all that good

dsienraOP•10/5/24, 5:55 AM

if you right will see all this projects fail

Maxivi•10/5/24, 5:56 AM

i mean i think he's right, i tried 100+ trainings on these distill models, it just gives it texture and artifacts

Ddsienra if you right will see all this projects fail

crystalwizard•10/5/24, 5:56 AM

eh, he'll keep working on it till he gets something that he'll then prance around and boast about. you'd think HE would know better - but he's backed himself into a corner

crystalwizard•10/5/24, 5:56 AM

he's desperate to be able to create controlnet for flux - and you can't do that, either.

Maxivi•10/5/24, 5:57 AM

these dont work??
https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro

Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro · Hugging Face

MMaxivi these dont work?? https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Unio...

crystalwizard•10/5/24, 5:58 AM

that depends on what you mean by work, and whether what ostris wants is what they actualy do or not

dsienraOP•10/5/24, 5:58 AM

let's see as I said I'm not an expert, I can't gave a informed opinion

dsienraOP•10/5/24, 6:00 AM

you have good points

Ddsienra you have good points

crystalwizard•10/5/24, 6:01 AM

i've got close to 3500 hours in on studying stable diffusion in the last 2.5 years. and close to 300 hours in on studying flux since it released. if not more

crystalwizard•10/5/24, 6:01 AM

i literally spend an entire month sitting here, feeding it one single prompt at a time to see what it would return by default - walking through it's latent space

crystalwizard•10/5/24, 6:02 AM

give it an unclear concept - you're going to get women, dogs, fantasy, or anime cat girls - and frequently a mixture of those

I trained flux with some big datasets off 3500 images for 40 epochs and I hade great results but is

Similar Threads

Similar Threads

Similar Threads