Software Engineering Courses (SECourses)•16mo ago

or maybe it is because of my pics are being oversized for training? Or is it rather the mixed aspect

or maybe it is because of my pics are being oversized for training? Or is it rather the mixed aspect ratio?

LLuciani or maybe it is because of my pics are being oversized for training? Or is it rat...

Furkan Gözükara SECourses•9/7/24, 10:09 PM

mixed aspect ratio

Furkan Gözükara SECourses•9/7/24, 10:09 PM

you have too many

Furkan Gözükara SECourses•9/7/24, 10:09 PM

and too little number of images

LucianiOP•9/7/24, 10:10 PM

I have 132 images for lora training -- I thought that even would be too much -- as other people I heard of only train with like 20 images? So 132 is commonly ok?

FFurkan Gözükara SECourses rank 1 best

Phuong Bui•9/7/24, 10:13 PM

I used rank 2 and it worked. But the problem is that I used 25 images but I don't know why the num train images * repeats is up to 1025. Am I setting it wrong somewhere? And if so, where should I go to fix it?

LLuciani I have 132 images for lora training -- I thought that even would be too much -- ...

Furkan Gözükara SECourses•9/7/24, 10:15 PM

for flux

Furkan Gözükara SECourses•9/7/24, 10:15 PM

more better

PPhuong Bui I used rank 2 and it worked. But the problem is that I used 25 images but I don'...

Furkan Gözükara SECourses•9/7/24, 10:15 PM

make repeat 1

Furkan Gözükara SECourses•9/7/24, 10:15 PM

if you have another folder in training folder

Furkan Gözükara SECourses•9/7/24, 10:15 PM

it uses all

FFurkan Gözükara SECourses make repeat 1

Phuong Bui•9/7/24, 10:16 PM

thanks you

DEXperience Solutions•9/7/24, 10:17 PM

I just made the payment, and I hope you can help me achieve the goal of generating comic images of my NFTs. I’m starting to watch your video. Best regards.

DDEXperience Solutions I just made the payment, and I hope you can help me achieve the goal of generati...

Furkan Gözükara SECourses•9/7/24, 10:21 PM

welcome

Furkan Gözükara SECourses•9/7/24, 10:21 PM

read here very carefully : https://huggingface.co/MonsterMMORPG/3D-Cartoon-Style-FLUX

MonsterMMORPG/3D-Cartoon-Style-FLUX · Hugging Face

Furkan Gözükara SECourses•9/7/24, 10:21 PM

style training concluded i written everything there

LucianiOP•9/7/24, 10:26 PM

So to ensure -- it would be ok to have mixed resolution for training images but they should have the same aspect ratio

For example havin mixed 1000x1000, 1200x1200, 1400x1400 and so on but all have the aspect ratio of 1:1
Can I have the some with aspect ratio 2:1 like havin 70 images with 2000x1000 and 70 with 1000x1000?

LucianiOP•9/7/24, 10:27 PM

Background: I do not want always only to crop the face -- because the lora should also "learn" the body proportions

LLuciani So to ensure -- it would be ok to have mixed resolution for training images but ...

Furkan Gözükara SECourses•9/7/24, 10:32 PM

this sounds better than your older case

LucianiOP•9/7/24, 10:33 PM

i´ll try, thank you -- by the way - I also subscribed to your patreon cause I think you do a great work, thank you!

Furkan Gözükara SECourses•9/7/24, 10:56 PM

our style model published with full details : https://civitai.com/models/731347

SECourses 3D Render for FLUX - Full Dataset and Workflow Shared - v...

Full Training Tutorial and Guide and Research For a FLUX Style Hugging Face repo with all checkpoints, prompts and more details > https://huggin...

DEXperience Solutions•9/7/24, 11:00 PM

@Dr. Furkan Gözükara I’ve read in detail what you did with MonsterMMORPG/3D-Cartoon-Style-FLUX, and now I’ll try to train following that guide. I have 800 images of 2608 x 2608; they are all spheres that vary in accessories and country color. My goal, after achieving a decent result that reuses the character in different scenarios, is to deploy it on an API that I will later query through a Telegram bot. One question I have is whether to use Massed Compute or RunPod?

DDEXperience Solutions @Dr. Furkan Gözükara I’ve read in detail what you did with MonsterMMORPG/3D-Cart...

Furkan Gözükara SECourses•9/7/24, 11:04 PM

go massed compute

Furkan Gözükara SECourses•9/7/24, 11:04 PM

way more dependable

Furkan Gözükara SECourses•9/7/24, 11:04 PM

rent 4x A6000 - 1.25 usd per hour

Furkan Gözükara SECourses•9/7/24, 11:04 PM

probably you can get good results with early epochs if they are consistent

Furkan Gözükara SECourses•9/7/24, 11:05 PM

66 images required only 75 epochs

DEXperience Solutions•9/7/24, 11:07 PM

I have 800 different characters, between accessories and country, do you think that training with the 800 images is not the way to go?
I should choose 100 and work with them?
Because per country I have 4-6 versions which share the same flag color, but different accessories.

DEXperience Solutions•9/7/24, 11:09 PM

The least I hope in this experiment is to get to occupy a prompt, that I can pass it for example “Ball on the beach” I hope one of those balls with a background on the beach.

DDEXperience Solutions I have 800 different characters, between accessories and country, do you think t...

Furkan Gözükara SECourses•9/7/24, 11:09 PM

as long as they consistent and not repeating i would say use all

Furkan Gözükara SECourses•9/7/24, 11:09 PM

also in your case captions may work better not sure though

DDEXperience Solutions I have 800 different characters, between accessories and country, do you think t...

xlads•9/7/24, 11:10 PM

This is interesting is it an nft project?

Xxlads This is interesting is it an nft project?

DEXperience Solutions•9/7/24, 11:10 PM

yes.

FFurkan Gözükara SECourses as long as they consistent and not repeating i would say use all

DEXperience Solutions•9/7/24, 11:12 PM

Do you recommend using them without background?

DDEXperience Solutions Do you recommend using them without background?

Furkan Gözükara SECourses•9/7/24, 11:14 PM

i say keep dont remove

Furkan Gözükara SECourses•9/7/24, 11:14 PM

it is how you want to generate right?

Furkan Gözükara SECourses•9/7/24, 11:15 PM

wow : https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/1733

GitHub

Why is the flux realism sampler code hidden in a zipped blockly imp...

I was having a hell of a time trying to figure out what the new "flux realism" sampler was (I'm guessing it's similar to comfyui's dpmpp_2s_ancestral that was semi-recently ad...

FFurkan Gözükara SECourses it is how you want to generate right?

DEXperience Solutions•9/7/24, 11:17 PM

I mean, I want the background to be on the FLUX side, if I ask for 'Ball in paris' I would want one of the cartoon with a realistic or non-realistic background of the paris background.

DDEXperience Solutions I mean, I want the background to be on the FLUX side, if I ask for 'Ball in pari...

Furkan Gözükara SECourses•9/7/24, 11:22 PM

not sure try it

xlads•9/7/24, 11:37 PM

After done training I need to download swarmui to generate images right? also what exactly are regularization images for?

Xxlads After done training I need to download swarmui to generate images right? also wh...

Furkan Gözükara SECourses•9/7/24, 11:38 PM

reg images not useful for flux i tested

Furkan Gözükara SECourses•9/7/24, 11:38 PM

you can use swarm ui forge comfy

Furkan Gözükara SECourses•9/7/24, 11:38 PM

i prefer swarm

FFurkan Gözükara SECourses i prefer swarm

xlads•9/7/24, 11:39 PM

https://youtu.be/HKX8_F1Er_w?feature=shared
I will follow this video after training is down just installing part and lora part

YouTubeSECourses

Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD We...

Do not skip any part of this tutorial to master how to use Stable Diffusion 3 (SD3) with the most advanced generative AI open source APP SwarmUI. Automatic1111 SD Web UI or Fooocus are not supporting the #SD3 yet. Therefore, I am starting to make tutorials for SwarmUI as well. #StableSwarmUI is officially developed by the StabilityAI and your m...

Xxlads https://youtu.be/HKX8_F1Er_w?feature=shared I will follow this video after trai...

Furkan Gözükara SECourses•9/7/24, 11:39 PM

yep great one

LucianiOP•9/7/24, 11:39 PM

so does it not matter if the training images are kinda "high res" like 4000px instead of 1024 on the wide side?

LLuciani so does it not matter if the training images are kinda "high res" like 4000px in...

Furkan Gözükara SECourses•9/7/24, 11:39 PM

it will auto downscale

Furkan Gözükara SECourses•9/7/24, 11:39 PM

to your train res

DEXperience Solutions•9/7/24, 11:41 PM

not available

LucianiOP•9/7/24, 11:42 PM

I now have unified the aspect ratios -- so now all pics are one of the following aspect ratio: 0.5, 0.666, 0.8, 1, 1.5, 2
I let it train over night and we´ll see -- also I add some more images for training

Furkan Gözükara SECourses•9/7/24, 11:44 PM

pick alt config but at least get 2 GPUs so to get more ram

or maybe it is because of my pics are being oversized for training? Or is it rather the mixed aspect

Similar Threads